@@ -100,7 +100,7 @@ Considering that the features of some channels will be suppressed if the convolu
The recognition module of PP-OCRv3 is optimized based on the text recognition algorithm [SVTR](https://arxiv.org/abs/2205.00159). RNN is abandoned in SVTR, and the context information of the text line image is more effectively mined by introducing the Transformers structure, thereby improving the text recognition ability.
-The recognition accuracy of SVTR_inty outperforms PP-OCRv2 recognition model by 5.3%, while the prediction speed nearly 11 times slower. It takes nearly 100ms to predict a text line on CPU. Therefore, as shown in the figure below, PP-OCRv3 adopts the following six optimization strategies to accelerate the recognition model.
+The recognition accuracy of SVTR_tiny outperforms PP-OCRv2 recognition model by 5.3%, while the prediction speed nearly 11 times slower. It takes nearly 100ms to predict a text line on CPU. Therefore, as shown in the figure below, PP-OCRv3 adopts the following six optimization strategies to accelerate the recognition model.
diff --git a/doc/doc_en/algorithm_rec_starnet.md b/doc/doc_en/algorithm_rec_starnet.md
new file mode 100644
index 0000000000..dbb53a9c73
--- /dev/null
+++ b/doc/doc_en/algorithm_rec_starnet.md
@@ -0,0 +1,139 @@
+# STAR-Net
+
+- [1. Introduction](#1)
+- [2. Environment](#2)
+- [3. Model Training / Evaluation / Prediction](#3)
+ - [3.1 Training](#3-1)
+ - [3.2 Evaluation](#3-2)
+ - [3.3 Prediction](#3-3)
+- [4. Inference and Deployment](#4)
+ - [4.1 Python Inference](#4-1)
+ - [4.2 C++ Inference](#4-2)
+ - [4.3 Serving](#4-3)
+ - [4.4 More](#4-4)
+- [5. FAQ](#5)
+
+
+## 1. Introduction
+
+Paper information:
+> [STAR-Net: a spatial attention residue network for scene text recognition.](http://www.bmva.org/bmvc/2016/papers/paper043/paper043.pdf)
+> Wei Liu, Chaofeng Chen, Kwan-Yee K. Wong, Zhizhong Su and Junyu Han.
+> BMVC, pages 43.1-43.13, 2016
+
+Refer to [DTRB](https://arxiv.org/abs/1904.01906) text Recognition Training and Evaluation Process . Using MJSynth and SynthText two text recognition datasets for training, and evaluating on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE datasets, the algorithm reproduction effect is as follows:
+
+|Models|Backbone Networks|Avg Accuracy|Configuration Files|Download Links|
+| --- | --- | --- | --- | --- |
+|StarNet|Resnet34_vd|84.44%|[configs/rec/rec_r34_vd_tps_bilstm_ctc.yml](../../configs/rec/rec_r34_vd_tps_bilstm_ctc.yml)|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_ctc_v2.0_train.tar)|
+|StarNet|MobileNetV3|81.42%|[configs/rec/rec_mv3_tps_bilstm_ctc.yml](../../configs/rec/rec_mv3_tps_bilstm_ctc.yml)|[ trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_ctc_v2.0_train.tar)|
+
+
+
+## 2. Environment
+Please refer to [Operating Environment Preparation](./environment_en.md) to configure the PaddleOCR operating environment, and refer to [Project Clone](./clone_en.md) to clone the project code.
+
+
+## 3. Model Training / Evaluation / Prediction
+
+Please refer to [Text Recognition Training Tutorial](./recognition_en.md). PaddleOCR modularizes the code, and training different recognition models only requires **changing the configuration file**. Take the backbone network based on Resnet34_vd as an example:
+
+
+### 3.1 Training
+After the data preparation is complete, the training can be started. The training command is as follows:
+
+````
+#Single card training (long training period, not recommended)
+python3 tools/train.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml #Multi-card training, specify the card number through the --gpus parameter
+python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c rec_r34_vd_tps_bilstm_ctc.yml
+ ````
+
+
+### 3.2 Evaluation
+
+````
+# GPU evaluation, Global.pretrained_model is the model to be evaluated
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy
+ ````
+
+
+### 3.3 Prediction
+
+````
+# The configuration file used for prediction must match the training
+python3 tools/infer_rec.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png
+ ````
+
+
+## 4. Inference
+
+
+### 4.1 Python Inference
+First, convert the model saved during the STAR-Net text recognition training process into an inference model. Take the model trained on the MJSynth and SynthText text recognition datasets based on the Resnet34_vd backbone network as an example [Model download address]( https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_none_bilstm_ctc_v2.0_train.tar) , which can be converted using the following command:
+
+```shell
+python3 tools/export_model.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o Global.pretrained_model=./rec_r34_vd_tps_bilstm_ctc_v2.0_train/best_accuracy Global.save_inference_dir=./inference/rec_starnet
+ ````
+
+STAR-Net text recognition model inference, you can execute the following commands:
+
+```shell
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rec_starnet/" --rec_image_shape="3, 32, 100" --rec_char_dict_path="./ppocr/utils/ic15_dict.txt"
+ ````
+
+
+
+The inference results are as follows:
+
+
+```bash
+Predicts of ./doc/imgs_words_en/word_336.png:('super', 0.9999073)
+```
+
+**Attention** Since the above model refers to the [DTRB](https://arxiv.org/abs/1904.01906) text recognition training and evaluation process, it is different from the ultra-lightweight Chinese recognition model training in two aspects:
+
+- The image resolutions used during training are different. The image resolutions used for training the above models are [3, 32, 100], while for Chinese model training, in order to ensure the recognition effect of long texts, the image resolutions used during training are [ 3, 32, 320]. The default shape parameter of the predictive inference program is the image resolution used for training Chinese, i.e. [3, 32, 320]. Therefore, when inferring the above English model here, it is necessary to set the shape of the recognized image through the parameter rec_image_shape.
+
+- Character list, the experiment in the DTRB paper is only for 26 lowercase English letters and 10 numbers, a total of 36 characters. All uppercase and lowercase characters are converted to lowercase characters, and characters not listed above are ignored and considered spaces. Therefore, there is no input character dictionary here, but a dictionary is generated by the following command. Therefore, the parameter rec_char_dict_path needs to be set during inference, which is specified as an English dictionary "./ppocr/utils/ic15_dict.txt".
+
+```
+self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
+dict_character = list(self.character_str)
+
+
+ ```
+
+
+### 4.2 C++ Inference
+
+After preparing the inference model, refer to the [cpp infer](../../deploy/cpp_infer/) tutorial to operate.
+
+
+### 4.3 Serving
+
+After preparing the inference model, refer to the [pdserving](../../deploy/pdserving/) tutorial for Serving deployment, including two modes: Python Serving and C++ Serving.
+
+
+### 4.4 More
+
+The STAR-Net model also supports the following inference deployment methods:
+
+- Paddle2ONNX Inference: After preparing the inference model, refer to the [paddle2onnx](../../deploy/paddle2onnx/) tutorial.
+
+
+## 5. FAQ
+
+## Quote
+
+```bibtex
+@inproceedings{liu2016star,
+ title={STAR-Net: a spatial attention residue network for scene text recognition.},
+ author={Liu, Wei and Chen, Chaofeng and Wong, Kwan-Yee K and Su, Zhizhong and Han, Junyu},
+ booktitle={BMVC},
+ volume={2},
+ pages={7},
+ year={2016}
+}
+```
+
+
diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md
index 76e0f8509b..f85bf585cb 100644
--- a/doc/doc_en/detection_en.md
+++ b/doc/doc_en/detection_en.md
@@ -159,7 +159,7 @@ python3 -m paddle.distributed.launch --ips="xx.xx.xx.xx,xx.xx.xx.xx" --gpus '0,1
-o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
```
-**Note:** When using multi-machine and multi-gpu training, you need to replace the ips value in the above command with the address of your machine, and the machines need to be able to ping each other. In addition, training needs to be launched separately on multiple machines. The command to view the ip address of the machine is `ifconfig`.
+**Note:** (1) When using multi-machine and multi-gpu training, you need to replace the ips value in the above command with the address of your machine, and the machines need to be able to ping each other. (2) Training needs to be launched separately on multiple machines. The command to view the ip address of the machine is `ifconfig`. (3) For more details about the distributed training speedup ratio, please refer to [Distributed Training Tutorial](./distributed_training_en.md).
### 2.6 Training with knowledge distillation
diff --git a/doc/doc_en/distributed_training.md b/doc/doc_en/distributed_training_en.md
similarity index 70%
rename from doc/doc_en/distributed_training.md
rename to doc/doc_en/distributed_training_en.md
index 2822ee5e4e..5a219ed2b4 100644
--- a/doc/doc_en/distributed_training.md
+++ b/doc/doc_en/distributed_training_en.md
@@ -40,11 +40,17 @@ python3 -m paddle.distributed.launch \
## Performance comparison
-* Based on 26W public recognition dataset (LSVT, rctw, mtwi), training on single 8-card P40 and dual 8-card P40, the final time consumption is as follows.
+* On two 8-card P40 graphics cards, the final time consumption and speedup ratio for public recognition dataset (LSVT, RCTW, MTWI) containing 260k images are as follows.
-| Model | Config file | Number of machines | Number of GPUs per machine | Training time | Recognition acc | Speedup ratio |
-| :-------: | :------------: | :----------------: | :----------------------------: | :------------------: | :--------------: | :-----------: |
-| CRNN | configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml | 1 | 8 | 60h | 66.7% | - |
-| CRNN | configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml | 2 | 8 | 40h | 67.0% | 150% |
-It can be seen that the training time is shortened from 60h to 40h, the speedup ratio can reach 150% (60h / 40h), and the efficiency is 75% (60h / (40h * 2)).
+| Model | Config file | Recognition acc | single 8-card training time | two 8-card training time | Speedup ratio |
+|------|-----|--------|--------|--------|-----|
+| CRNN | [rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml) | 67.0% | 2.50d | 1.67d | **1.5** |
+
+
+* On four 8-card V100 graphics cards, the final time consumption and speedup ratio for full data are as follows.
+
+
+| Model | Config file | Recognition acc | single 8-card training time | four 8-card training time | Speedup ratio |
+|------|-----|--------|--------|--------|-----|
+| SVTR | [ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml) | 74.0% | 10d | 2.84d | **3.5** |
diff --git a/doc/doc_en/ppocr_introduction_en.md b/doc/doc_en/ppocr_introduction_en.md
index b13d7f9bf1..d28ccb3529 100644
--- a/doc/doc_en/ppocr_introduction_en.md
+++ b/doc/doc_en/ppocr_introduction_en.md
@@ -29,10 +29,10 @@ PP-OCR pipeline is as follows:
PP-OCR system is in continuous optimization. At present, PP-OCR and PP-OCRv2 have been released:
-PP-OCR adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module (as shown in the green box above). The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941).
+PP-OCR adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module (as shown in the green box above). The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to [PP-OCR technical report](https://arxiv.org/abs/2009.09941).
#### PP-OCRv2
-On the basis of PP-OCR, PP-OCRv2 is further optimized in five aspects. The detection model adopts CML(Collaborative Mutual Learning) knowledge distillation strategy and CopyPaste data expansion strategy. The recognition model adopts LCNet lightweight backbone network, U-DML knowledge distillation strategy and enhanced CTC loss function improvement (as shown in the red box above), which further improves the inference speed and prediction effect. For more details, please refer to the technical report of PP-OCRv2 (https://arxiv.org/abs/2109.03144).
+On the basis of PP-OCR, PP-OCRv2 is further optimized in five aspects. The detection model adopts CML(Collaborative Mutual Learning) knowledge distillation strategy and CopyPaste data expansion strategy. The recognition model adopts LCNet lightweight backbone network, U-DML knowledge distillation strategy and enhanced CTC loss function improvement (as shown in the red box above), which further improves the inference speed and prediction effect. For more details, please refer to [PP-OCRv2 technical report](https://arxiv.org/abs/2109.03144).
#### PP-OCRv3
@@ -46,7 +46,7 @@ PP-OCRv3 pipeline is as follows:
-For more details, please refer to [PP-OCRv3 technical report](./PP-OCRv3_introduction_en.md).
+For more details, please refer to [PP-OCRv3 technical report](https://arxiv.org/abs/2206.03001v2).
## 2. Features
diff --git a/doc/doc_en/quickstart_en.md b/doc/doc_en/quickstart_en.md
index d7aeb77730..c678dc4762 100644
--- a/doc/doc_en/quickstart_en.md
+++ b/doc/doc_en/quickstart_en.md
@@ -119,7 +119,18 @@ If you do not use the provided test image, you can replace the following `--imag
['PAIN', 0.9934559464454651]
```
-If you need to use the 2.0 model, please specify the parameter `--ocr_version PP-OCR`, paddleocr uses the PP-OCRv3 model by default(`--ocr_version PP-OCRv3`). More whl package usage can be found in [whl package](./whl_en.md)
+**Version**
+paddleocr uses the PP-OCRv3 model by default(`--ocr_version PP-OCRv3`). If you want to use other versions, you can set the parameter `--ocr_version`, the specific version description is as follows:
+| version name | description |
+| --- | --- |
+| PP-OCRv3 | support Chinese and English detection and recognition, direction classifier, support multilingual recognition |
+| PP-OCRv2 | only supports Chinese and English detection and recognition, direction classifier, multilingual model is not updated |
+| PP-OCR | support Chinese and English detection and recognition, direction classifier, support multilingual recognition |
+
+If you want to add your own trained model, you can add model links and keys in [paddleocr](../../paddleocr.py) and recompile.
+
+More whl package usage can be found in [whl package](./whl_en.md)
+
#### 2.1.2 Multi-language Model
diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md
index 60b4a1b26b..7d31b0ffe2 100644
--- a/doc/doc_en/recognition_en.md
+++ b/doc/doc_en/recognition_en.md
@@ -306,7 +306,7 @@ python3 -m paddle.distributed.launch --ips="xx.xx.xx.xx,xx.xx.xx.xx" --gpus '0,1
-o Global.pretrained_model=./pretrain_models/rec_mv3_none_bilstm_ctc_v2.0_train
```
-**Note:** When using multi-machine and multi-gpu training, you need to replace the ips value in the above command with the address of your machine, and the machines need to be able to ping each other. In addition, training needs to be launched separately on multiple machines. The command to view the ip address of the machine is `ifconfig`.
+**Note:** (1) When using multi-machine and multi-gpu training, you need to replace the ips value in the above command with the address of your machine, and the machines need to be able to ping each other. (2) Training needs to be launched separately on multiple machines. The command to view the ip address of the machine is `ifconfig`. (3) For more details about the distributed training speedup ratio, please refer to [Distributed Training Tutorial](./distributed_training_en.md).
### 2.6 Training with Knowledge Distillation
diff --git a/paddleocr.py b/paddleocr.py
index a1265f79de..470dc60da3 100644
--- a/paddleocr.py
+++ b/paddleocr.py
@@ -154,7 +154,13 @@ MODEL_URLS = {
'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar',
'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
}
- }
+ },
+ 'cls': {
+ 'ch': {
+ 'url':
+ 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
+ }
+ },
},
'PP-OCR': {
'det': {
diff --git a/ppocr/data/imaug/__init__.py b/ppocr/data/imaug/__init__.py
index 548832fb0d..f0fd578f61 100644
--- a/ppocr/data/imaug/__init__.py
+++ b/ppocr/data/imaug/__init__.py
@@ -22,7 +22,7 @@ from .make_shrink_map import MakeShrinkMap
from .random_crop_data import EastRandomCropData, RandomCropImgMask
from .make_pse_gt import MakePseGt
-from .rec_img_aug import RecAug, RecConAug, RecResizeImg, ClsResizeImg, \
+from .rec_img_aug import BaseDataAugmentation, RecAug, RecConAug, RecResizeImg, ClsResizeImg, \
SRNRecResizeImg, NRTRRecResizeImg, SARRecResizeImg, PRENResizeImg
from .ssl_img_aug import SSLRotateResize
from .randaugment import RandAugment
diff --git a/ppocr/data/imaug/rec_img_aug.py b/ppocr/data/imaug/rec_img_aug.py
index 7483dffe5b..32de2b3fc3 100644
--- a/ppocr/data/imaug/rec_img_aug.py
+++ b/ppocr/data/imaug/rec_img_aug.py
@@ -22,13 +22,74 @@ from .text_image_aug import tia_perspective, tia_stretch, tia_distort
class RecAug(object):
- def __init__(self, use_tia=True, aug_prob=0.4, **kwargs):
- self.use_tia = use_tia
- self.aug_prob = aug_prob
+ def __init__(self,
+ tia_prob=0.4,
+ crop_prob=0.4,
+ reverse_prob=0.4,
+ noise_prob=0.4,
+ jitter_prob=0.4,
+ blur_prob=0.4,
+ hsv_aug_prob=0.4,
+ **kwargs):
+ self.tia_prob = tia_prob
+ self.bda = BaseDataAugmentation(crop_prob, reverse_prob, noise_prob,
+ jitter_prob, blur_prob, hsv_aug_prob)
def __call__(self, data):
img = data['image']
- img = warp(img, 10, self.use_tia, self.aug_prob)
+ h, w, _ = img.shape
+
+ # tia
+ if random.random() <= self.tia_prob:
+ if h >= 20 and w >= 20:
+ img = tia_distort(img, random.randint(3, 6))
+ img = tia_stretch(img, random.randint(3, 6))
+ img = tia_perspective(img)
+
+ # bda
+ data['image'] = img
+ data = self.bda(data)
+ return data
+
+
+class BaseDataAugmentation(object):
+ def __init__(self,
+ crop_prob=0.4,
+ reverse_prob=0.4,
+ noise_prob=0.4,
+ jitter_prob=0.4,
+ blur_prob=0.4,
+ hsv_aug_prob=0.4,
+ **kwargs):
+ self.crop_prob = crop_prob
+ self.reverse_prob = reverse_prob
+ self.noise_prob = noise_prob
+ self.jitter_prob = jitter_prob
+ self.blur_prob = blur_prob
+ self.hsv_aug_prob = hsv_aug_prob
+
+ def __call__(self, data):
+ img = data['image']
+ h, w, _ = img.shape
+
+ if random.random() <= self.crop_prob and h >= 20 and w >= 20:
+ img = get_crop(img)
+
+ if random.random() <= self.blur_prob:
+ img = blur(img)
+
+ if random.random() <= self.hsv_aug_prob:
+ img = hsv_aug(img)
+
+ if random.random() <= self.jitter_prob:
+ img = jitter(img)
+
+ if random.random() <= self.noise_prob:
+ img = add_gasuss_noise(img)
+
+ if random.random() <= self.reverse_prob:
+ img = 255 - img
+
data['image'] = img
return data
@@ -359,7 +420,7 @@ def flag():
return 1 if random.random() > 0.5000001 else -1
-def cvtColor(img):
+def hsv_aug(img):
"""
cvtColor
"""
@@ -427,50 +488,6 @@ def get_crop(image):
return crop_img
-class Config:
- """
- Config
- """
-
- def __init__(self, use_tia):
- self.anglex = random.random() * 30
- self.angley = random.random() * 15
- self.anglez = random.random() * 10
- self.fov = 42
- self.r = 0
- self.shearx = random.random() * 0.3
- self.sheary = random.random() * 0.05
- self.borderMode = cv2.BORDER_REPLICATE
- self.use_tia = use_tia
-
- def make(self, w, h, ang):
- """
- make
- """
- self.anglex = random.random() * 5 * flag()
- self.angley = random.random() * 5 * flag()
- self.anglez = -1 * random.random() * int(ang) * flag()
- self.fov = 42
- self.r = 0
- self.shearx = 0
- self.sheary = 0
- self.borderMode = cv2.BORDER_REPLICATE
- self.w = w
- self.h = h
-
- self.perspective = self.use_tia
- self.stretch = self.use_tia
- self.distort = self.use_tia
-
- self.crop = True
- self.affine = False
- self.reverse = True
- self.noise = True
- self.jitter = True
- self.blur = True
- self.color = True
-
-
def rad(x):
"""
rad
@@ -554,48 +571,3 @@ def get_warpAffine(config):
rz = np.array([[np.cos(rad(anglez)), np.sin(rad(anglez)), 0],
[-np.sin(rad(anglez)), np.cos(rad(anglez)), 0]], np.float32)
return rz
-
-
-def warp(img, ang, use_tia=True, prob=0.4):
- """
- warp
- """
- h, w, _ = img.shape
- config = Config(use_tia=use_tia)
- config.make(w, h, ang)
- new_img = img
-
- if config.distort:
- img_height, img_width = img.shape[0:2]
- if random.random() <= prob and img_height >= 20 and img_width >= 20:
- new_img = tia_distort(new_img, random.randint(3, 6))
-
- if config.stretch:
- img_height, img_width = img.shape[0:2]
- if random.random() <= prob and img_height >= 20 and img_width >= 20:
- new_img = tia_stretch(new_img, random.randint(3, 6))
-
- if config.perspective:
- if random.random() <= prob:
- new_img = tia_perspective(new_img)
-
- if config.crop:
- img_height, img_width = img.shape[0:2]
- if random.random() <= prob and img_height >= 20 and img_width >= 20:
- new_img = get_crop(new_img)
-
- if config.blur:
- if random.random() <= prob:
- new_img = blur(new_img)
- if config.color:
- if random.random() <= prob:
- new_img = cvtColor(new_img)
- if config.jitter:
- new_img = jitter(new_img)
- if config.noise:
- if random.random() <= prob:
- new_img = add_gasuss_noise(new_img)
- if config.reverse:
- if random.random() <= prob:
- new_img = 255 - new_img
- return new_img
diff --git a/ppocr/data/simple_dataset.py b/ppocr/data/simple_dataset.py
index b5da9b8898..402f1e38fe 100644
--- a/ppocr/data/simple_dataset.py
+++ b/ppocr/data/simple_dataset.py
@@ -33,7 +33,7 @@ class SimpleDataSet(Dataset):
self.delimiter = dataset_config.get('delimiter', '\t')
label_file_list = dataset_config.pop('label_file_list')
data_source_num = len(label_file_list)
- ratio_list = dataset_config.get("ratio_list", [1.0])
+ ratio_list = dataset_config.get("ratio_list", 1.0)
if isinstance(ratio_list, (float, int)):
ratio_list = [float(ratio_list)] * int(data_source_num)
diff --git a/ppocr/losses/rec_aster_loss.py b/ppocr/losses/rec_aster_loss.py
index fbb99d29a6..52605e46db 100644
--- a/ppocr/losses/rec_aster_loss.py
+++ b/ppocr/losses/rec_aster_loss.py
@@ -27,12 +27,12 @@ class CosineEmbeddingLoss(nn.Layer):
self.epsilon = 1e-12
def forward(self, x1, x2, target):
- similarity = paddle.fluid.layers.reduce_sum(
+ similarity = paddle.sum(
x1 * x2, dim=-1) / (paddle.norm(
x1, axis=-1) * paddle.norm(
x2, axis=-1) + self.epsilon)
one_list = paddle.full_like(target, fill_value=1)
- out = paddle.fluid.layers.reduce_mean(
+ out = paddle.mean(
paddle.where(
paddle.equal(target, one_list), 1. - similarity,
paddle.maximum(
diff --git a/ppocr/losses/table_att_loss.py b/ppocr/losses/table_att_loss.py
index d7fd99e695..51377efa2b 100644
--- a/ppocr/losses/table_att_loss.py
+++ b/ppocr/losses/table_att_loss.py
@@ -19,7 +19,6 @@ from __future__ import print_function
import paddle
from paddle import nn
from paddle.nn import functional as F
-from paddle import fluid
class TableAttentionLoss(nn.Layer):
def __init__(self, structure_weight, loc_weight, use_giou=False, giou_weight=1.0, **kwargs):
@@ -36,13 +35,13 @@ class TableAttentionLoss(nn.Layer):
:param bbox:[[x1,y1,x2,y2], [x1,y1,x2,y2],,,]
:return: loss
'''
- ix1 = fluid.layers.elementwise_max(preds[:, 0], bbox[:, 0])
- iy1 = fluid.layers.elementwise_max(preds[:, 1], bbox[:, 1])
- ix2 = fluid.layers.elementwise_min(preds[:, 2], bbox[:, 2])
- iy2 = fluid.layers.elementwise_min(preds[:, 3], bbox[:, 3])
+ ix1 = paddle.maximum(preds[:, 0], bbox[:, 0])
+ iy1 = paddle.maximum(preds[:, 1], bbox[:, 1])
+ ix2 = paddle.minimum(preds[:, 2], bbox[:, 2])
+ iy2 = paddle.minimum(preds[:, 3], bbox[:, 3])
- iw = fluid.layers.clip(ix2 - ix1 + 1e-3, 0., 1e10)
- ih = fluid.layers.clip(iy2 - iy1 + 1e-3, 0., 1e10)
+ iw = paddle.clip(ix2 - ix1 + 1e-3, 0., 1e10)
+ ih = paddle.clip(iy2 - iy1 + 1e-3, 0., 1e10)
# overlap
inters = iw * ih
@@ -55,12 +54,12 @@ class TableAttentionLoss(nn.Layer):
# ious
ious = inters / uni
- ex1 = fluid.layers.elementwise_min(preds[:, 0], bbox[:, 0])
- ey1 = fluid.layers.elementwise_min(preds[:, 1], bbox[:, 1])
- ex2 = fluid.layers.elementwise_max(preds[:, 2], bbox[:, 2])
- ey2 = fluid.layers.elementwise_max(preds[:, 3], bbox[:, 3])
- ew = fluid.layers.clip(ex2 - ex1 + 1e-3, 0., 1e10)
- eh = fluid.layers.clip(ey2 - ey1 + 1e-3, 0., 1e10)
+ ex1 = paddle.minimum(preds[:, 0], bbox[:, 0])
+ ey1 = paddle.minimum(preds[:, 1], bbox[:, 1])
+ ex2 = paddle.maximum(preds[:, 2], bbox[:, 2])
+ ey2 = paddle.maximum(preds[:, 3], bbox[:, 3])
+ ew = paddle.clip(ex2 - ex1 + 1e-3, 0., 1e10)
+ eh = paddle.clip(ey2 - ey1 + 1e-3, 0., 1e10)
# enclose erea
enclose = ew * eh + eps
diff --git a/ppocr/modeling/backbones/kie_unet_sdmgr.py b/ppocr/modeling/backbones/kie_unet_sdmgr.py
index 545e4e7511..4b1bd80300 100644
--- a/ppocr/modeling/backbones/kie_unet_sdmgr.py
+++ b/ppocr/modeling/backbones/kie_unet_sdmgr.py
@@ -175,12 +175,7 @@ class Kie_backbone(nn.Layer):
img, relations, texts, gt_bboxes, tag, img_size)
x = self.img_feat(img)
boxes, rois_num = self.bbox2roi(gt_bboxes)
- feats = paddle.fluid.layers.roi_align(
- x,
- boxes,
- spatial_scale=1.0,
- pooled_height=7,
- pooled_width=7,
- rois_num=rois_num)
+ feats = paddle.vision.ops.roi_align(
+ x, boxes, spatial_scale=1.0, output_size=7, boxes_num=rois_num)
feats = self.maxpool(feats).squeeze(-1).squeeze(-1)
return [relations, texts, feats]
diff --git a/ppocr/modeling/backbones/rec_resnet_fpn.py b/ppocr/modeling/backbones/rec_resnet_fpn.py
index a7e876a2bd..79efd6e41e 100644
--- a/ppocr/modeling/backbones/rec_resnet_fpn.py
+++ b/ppocr/modeling/backbones/rec_resnet_fpn.py
@@ -18,7 +18,6 @@ from __future__ import print_function
from paddle import nn, ParamAttr
from paddle.nn import functional as F
-import paddle.fluid as fluid
import paddle
import numpy as np
diff --git a/ppocr/modeling/heads/rec_srn_head.py b/ppocr/modeling/heads/rec_srn_head.py
index 8d59e4711a..1070d8cd64 100644
--- a/ppocr/modeling/heads/rec_srn_head.py
+++ b/ppocr/modeling/heads/rec_srn_head.py
@@ -20,13 +20,11 @@ import math
import paddle
from paddle import nn, ParamAttr
from paddle.nn import functional as F
-import paddle.fluid as fluid
import numpy as np
from .self_attention import WrapEncoderForFeature
from .self_attention import WrapEncoder
from paddle.static import Program
from ppocr.modeling.backbones.rec_resnet_fpn import ResNetFPN
-import paddle.fluid.framework as framework
from collections import OrderedDict
gradient_clip = 10
diff --git a/ppocr/modeling/heads/self_attention.py b/ppocr/modeling/heads/self_attention.py
index 6c27fdbe43..6e4c65e393 100644
--- a/ppocr/modeling/heads/self_attention.py
+++ b/ppocr/modeling/heads/self_attention.py
@@ -22,7 +22,6 @@ import paddle
from paddle import ParamAttr, nn
from paddle import nn, ParamAttr
from paddle.nn import functional as F
-import paddle.fluid as fluid
import numpy as np
gradient_clip = 10
@@ -288,10 +287,10 @@ class PrePostProcessLayer(nn.Layer):
"layer_norm_%d" % len(self.sublayers()),
paddle.nn.LayerNorm(
normalized_shape=d_model,
- weight_attr=fluid.ParamAttr(
- initializer=fluid.initializer.Constant(1.)),
- bias_attr=fluid.ParamAttr(
- initializer=fluid.initializer.Constant(0.)))))
+ weight_attr=paddle.ParamAttr(
+ initializer=paddle.nn.initializer.Constant(1.)),
+ bias_attr=paddle.ParamAttr(
+ initializer=paddle.nn.initializer.Constant(0.)))))
elif cmd == "d": # add dropout
self.functors.append(lambda x: F.dropout(
x, p=dropout_rate, mode="downscale_in_infer")
@@ -324,7 +323,7 @@ class PrepareEncoder(nn.Layer):
def forward(self, src_word, src_pos):
src_word_emb = src_word
- src_word_emb = fluid.layers.cast(src_word_emb, 'float32')
+ src_word_emb = paddle.cast(src_word_emb, 'float32')
src_word_emb = paddle.scale(x=src_word_emb, scale=self.src_emb_dim**0.5)
src_pos = paddle.squeeze(src_pos, axis=-1)
src_pos_enc = self.emb(src_pos)
@@ -367,7 +366,7 @@ class PrepareDecoder(nn.Layer):
self.dropout_rate = dropout_rate
def forward(self, src_word, src_pos):
- src_word = fluid.layers.cast(src_word, 'int64')
+ src_word = paddle.cast(src_word, 'int64')
src_word = paddle.squeeze(src_word, axis=-1)
src_word_emb = self.emb0(src_word)
src_word_emb = paddle.scale(x=src_word_emb, scale=self.src_emb_dim**0.5)
diff --git a/ppstructure/table/README.md b/ppstructure/table/README.md
index d21ef4aa38..b6804c6f09 100644
--- a/ppstructure/table/README.md
+++ b/ppstructure/table/README.md
@@ -18,7 +18,7 @@ The table recognition mainly contains three models
The table recognition flow chart is as follows
-
+
1. The coordinates of single-line text is detected by DB model, and then sends it to the recognition model to get the recognition result.
2. The table structure and cell coordinates is predicted by RARE model.
diff --git a/ppstructure/table/predict_table.py b/ppstructure/table/predict_table.py
index 402d6c2418..aa05459589 100644
--- a/ppstructure/table/predict_table.py
+++ b/ppstructure/table/predict_table.py
@@ -28,6 +28,7 @@ import numpy as np
import time
import tools.infer.predict_rec as predict_rec
import tools.infer.predict_det as predict_det
+import tools.infer.utility as utility
from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from ppocr.utils.logging import get_logger
from ppstructure.table.matcher import distance, compute_iou
@@ -59,11 +60,37 @@ class TableSystem(object):
self.text_recognizer = predict_rec.TextRecognizer(
args) if text_recognizer is None else text_recognizer
self.table_structurer = predict_strture.TableStructurer(args)
+ self.benchmark = args.benchmark
+ self.predictor, self.input_tensor, self.output_tensors, self.config = utility.create_predictor(
+ args, 'table', logger)
+ if args.benchmark:
+ import auto_log
+ pid = os.getpid()
+ gpu_id = utility.get_infer_gpuid()
+ self.autolog = auto_log.AutoLogger(
+ model_name="table",
+ model_precision=args.precision,
+ batch_size=1,
+ data_shape="dynamic",
+ save_path=None, #args.save_log_path,
+ inference_config=self.config,
+ pids=pid,
+ process_name=None,
+ gpu_ids=gpu_id if args.use_gpu else None,
+ time_keys=[
+ 'preprocess_time', 'inference_time', 'postprocess_time'
+ ],
+ warmup=0,
+ logger=logger)
def __call__(self, img, return_ocr_result_in_table=False):
result = dict()
ori_im = img.copy()
+ if self.benchmark:
+ self.autolog.times.start()
structure_res, elapse = self.table_structurer(copy.deepcopy(img))
+ if self.benchmark:
+ self.autolog.times.stamp()
dt_boxes, elapse = self.text_detector(copy.deepcopy(img))
dt_boxes = sorted_boxes(dt_boxes)
if return_ocr_result_in_table:
@@ -77,13 +104,11 @@ class TableSystem(object):
box = [x_min, y_min, x_max, y_max]
r_boxes.append(box)
dt_boxes = np.array(r_boxes)
-
logger.debug("dt_boxes num : {}, elapse : {}".format(
len(dt_boxes), elapse))
if dt_boxes is None:
return None, None
img_crop_list = []
-
for i in range(len(dt_boxes)):
det_box = dt_boxes[i]
x0, y0, x1, y1 = expand(2, det_box, ori_im.shape)
@@ -92,10 +117,14 @@ class TableSystem(object):
rec_res, elapse = self.text_recognizer(img_crop_list)
logger.debug("rec_res num : {}, elapse : {}".format(
len(rec_res), elapse))
+ if self.benchmark:
+ self.autolog.times.stamp()
if return_ocr_result_in_table:
result['rec_res'] = rec_res
pred_html, pred = self.rebuild_table(structure_res, dt_boxes, rec_res)
result['html'] = pred_html
+ if self.benchmark:
+ self.autolog.times.end(stamp=True)
return result
def rebuild_table(self, structure_res, dt_boxes, rec_res):
@@ -213,6 +242,8 @@ def main(args):
logger.info('excel saved to {}'.format(excel_path))
elapse = time.time() - starttime
logger.info("Predict time : {:.3f}s".format(elapse))
+ if args.benchmark:
+ text_sys.autolog.report()
if __name__ == "__main__":
diff --git a/test_tipc/build_server.sh b/test_tipc/build_server.sh
new file mode 100644
index 0000000000..3173359785
--- /dev/null
+++ b/test_tipc/build_server.sh
@@ -0,0 +1,69 @@
+#使用镜像：
+#registry.baidubce.com/paddlepaddle/paddle:latest-dev-cuda10.1-cudnn7-gcc82
+
+#编译Serving Server：
+
+#client和app可以直接使用release版本
+
+#server因为加入了自定义OP，需要重新编译
+
+apt-get update
+apt install -y libcurl4-openssl-dev libbz2-dev
+wget https://paddle-serving.bj.bcebos.com/others/centos_ssl.tar && tar xf centos_ssl.tar && rm -rf centos_ssl.tar && mv libcrypto.so.1.0.2k /usr/lib/libcrypto.so.1.0.2k && mv libssl.so.1.0.2k /usr/lib/libssl.so.1.0.2k && ln -sf /usr/lib/libcrypto.so.1.0.2k /usr/lib/libcrypto.so.10 && ln -sf /usr/lib/libssl.so.1.0.2k /usr/lib/libssl.so.10 && ln -sf /usr/lib/libcrypto.so.10 /usr/lib/libcrypto.so && ln -sf /usr/lib/libssl.so.10 /usr/lib/libssl.so
+
+# 安装go依赖
+rm -rf /usr/local/go
+wget -qO- https://paddle-ci.cdn.bcebos.com/go1.17.2.linux-amd64.tar.gz | tar -xz -C /usr/local
+export GOROOT=/usr/local/go
+export GOPATH=/root/gopath
+export PATH=$PATH:$GOPATH/bin:$GOROOT/bin
+go env -w GO111MODULE=on
+go env -w GOPROXY=https://goproxy.cn,direct
+go install github.com/grpc-ecosystem/grpc-gateway/protoc-gen-grpc-gateway@v1.15.2
+go install github.com/grpc-ecosystem/grpc-gateway/protoc-gen-swagger@v1.15.2
+go install github.com/golang/protobuf/protoc-gen-go@v1.4.3
+go install google.golang.org/grpc@v1.33.0
+go env -w GO111MODULE=auto
+
+# 下载opencv库
+wget https://paddle-qa.bj.bcebos.com/PaddleServing/opencv3.tar.gz && tar -xvf opencv3.tar.gz && rm -rf opencv3.tar.gz
+export OPENCV_DIR=$PWD/opencv3
+
+# clone Serving
+git clone https://github.com/PaddlePaddle/Serving.git -b develop --depth=1
+cd Serving
+export Serving_repo_path=$PWD
+git submodule update --init --recursive
+python -m pip install -r python/requirements.txt
+
+
+export PYTHON_INCLUDE_DIR=$(python -c "from distutils.sysconfig import get_python_inc; print(get_python_inc())")
+export PYTHON_LIBRARIES=$(python -c "import distutils.sysconfig as sysconfig; print(sysconfig.get_config_var('LIBDIR'))")
+export PYTHON_EXECUTABLE=`which python`
+
+export CUDA_PATH='/usr/local/cuda'
+export CUDNN_LIBRARY='/usr/local/cuda/lib64/'
+export CUDA_CUDART_LIBRARY='/usr/local/cuda/lib64/'
+export TENSORRT_LIBRARY_PATH='/usr/local/TensorRT6-cuda10.1-cudnn7/targets/x86_64-linux-gnu/'
+
+# cp 自定义OP代码
+cp -rf ../deploy/pdserving/general_detection_op.cpp ${Serving_repo_path}/core/general-server/op
+
+# 编译Server, export SERVING_BIN
+mkdir server-build-gpu-opencv && cd server-build-gpu-opencv
+cmake -DPYTHON_INCLUDE_DIR=$PYTHON_INCLUDE_DIR \
+ -DPYTHON_LIBRARIES=$PYTHON_LIBRARIES \
+ -DPYTHON_EXECUTABLE=$PYTHON_EXECUTABLE \
+ -DCUDA_TOOLKIT_ROOT_DIR=${CUDA_PATH} \
+ -DCUDNN_LIBRARY=${CUDNN_LIBRARY} \
+ -DCUDA_CUDART_LIBRARY=${CUDA_CUDART_LIBRARY} \
+ -DTENSORRT_ROOT=${TENSORRT_LIBRARY_PATH} \
+ -DOPENCV_DIR=${OPENCV_DIR} \
+ -DWITH_OPENCV=ON \
+ -DSERVER=ON \
+ -DWITH_GPU=ON ..
+make -j32
+
+python -m pip install python/dist/paddle*
+export SERVING_BIN=$PWD/core/general-server/serving
+cd ../../
diff --git a/test_tipc/common_func.sh b/test_tipc/common_func.sh
index 85dfe21725..f7d8a1e04a 100644
--- a/test_tipc/common_func.sh
+++ b/test_tipc/common_func.sh
@@ -57,10 +57,11 @@ function status_check(){
last_status=$1 # the exit code
run_command=$2
run_log=$3
+ model_name=$4
if [ $last_status -eq 0 ]; then
- echo -e "\033[33m Run successfully with command - ${run_command}! \033[0m" | tee -a ${run_log}
+ echo -e "\033[33m Run successfully with command - ${model_name} - ${run_command}! \033[0m" | tee -a ${run_log}
else
- echo -e "\033[33m Run failed with command - ${run_command}! \033[0m" | tee -a ${run_log}
+ echo -e "\033[33m Run failed with command - ${model_name} - ${run_command}! \033[0m" | tee -a ${run_log}
fi
}
diff --git a/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..a0c49a0812
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_PP-OCRv2_rec_infer/
+--benchmark:True
+--det:True
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index fcac6e3984..32b290a9ed 100644
--- a/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -6,10 +6,10 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_system.py
--use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
new file mode 100644
index 0000000000..24eb620eeb
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -0,0 +1,17 @@
+===========================paddle2onnx_params===========================
+model_name:ch_PP-OCRv2
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/ch_PP-OCRv2_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/det_v2_onnx/model.onnx
+--rec_model_dir:./inference/ch_PP-OCRv2_rec_infer/
+--rec_save_file:./inference/rec_v2_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_system.py --rec_image_shape="3,32,320"
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/00008790.jpg
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..f0456b5c35
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_client/
+--rec_dirname:./inference/ch_PP-OCRv2_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..4ad64db03c
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_client/
+--rec_dirname:./inference/ch_PP-OCRv2_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_client/
+serving_dir:./deploy/pdserving
+web_service:web_service.py --config=config.yml --opt op.det.concurrency="1" op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..7eccbd725c
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2_det
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
new file mode 100644
index 0000000000..2e7906076f
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -0,0 +1,17 @@
+===========================paddle2onnx_params===========================
+model_name:ch_PP-OCRv2_det
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/ch_PP-OCRv2_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/det_v2_onnx/model.onnx
+--rec_model_dir:
+--rec_save_file:
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..587a7d7ea6
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_det
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt
index 797cf53a1d..cab0cb0aa3 100644
--- a/test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv2_det
+model_name:ch_PP-OCRv2_det
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..91a6288eb0
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_PP-OCRv2_det
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o
+quant_export:null
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 033d40a80a..85b0ebcb9d 100644
--- a/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv2_det
+model_name:ch_PP-OCRv2_det
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..1975e099d7
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2_det_KL
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_det_klquant_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 1aad65b687..ccc9e5ced0 100644
--- a/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -1,5 +1,5 @@
===========================kl_quant_params===========================
-model_name:PPOCRv2_ocr_det_kl
+model_name:ch_PP-OCRv2_det_KL
python:python3.7
Global.pretrained_model:null
Global.save_inference_dir:null
@@ -8,10 +8,10 @@ infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_PP-OCRv2/ch_
infer_quant:True
inference:tools/infer/predict_det.py
--use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:int8
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..e306b0a92a
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_det_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_kl_client/
+--rec_dirname:./inference/ch_PP-OCRv2_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_kl_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..2c96d2bfd8
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_det_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_kl_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..43ef97d506
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2_det_PACT
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_det_pact_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..b2d929b99c
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_det_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_pact_client/
+--rec_dirname:./inference/ch_PP-OCRv2_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_pact_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..d5d99ab56d
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_det_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_pact_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_infer_python.txt
index 038fa85061..1a20f97fdb 100644
--- a/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv2_det_PACT
+model_name:ch_PP-OCRv2_det_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=1|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index d922a4a5da..3afc0acb79 100644
--- a/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv2_det_PACT
+model_name:ch_PP-OCRv2_det_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..b1bff00b09
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2_rec
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_rec_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
new file mode 100644
index 0000000000..e374a5d821
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -0,0 +1,17 @@
+===========================paddle2onnx_params===========================
+model_name:ch_PP-OCRv2_rec
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:
+--rec_model_dir:./inference/ch_PP-OCRv2_rec_infer/
+--rec_save_file:./inference/rec_v2_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..e9e90d372e
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_rec
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_PP-OCRv2_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt
index 188eb3ccc5..df42b342ba 100644
--- a/test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:PPOCRv2_ocr_rec
+model_name:ch_PP-OCRv2_rec
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..5795bc27e6
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_PP-OCRv2_rec
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o
+quant_export:
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_rec_infer
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1|6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,320]}]
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 7c438cb8a3..1b8800f5cf 100644
--- a/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:PPOCRv2_ocr_rec
+model_name:ch_PP-OCRv2_rec
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..95e4062d14
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2_rec_KL
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_rec_klquant_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 083a3ae26e..c30e0858ef 100644
--- a/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -1,17 +1,17 @@
===========================kl_quant_params===========================
-model_name:PPOCRv2_ocr_rec_kl
+model_name:ch_PP-OCRv2_rec_KL
python:python3.7
Global.pretrained_model:null
Global.save_inference_dir:null
infer_model:./inference/ch_PP-OCRv2_rec_infer/
infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o
infer_quant:True
-inference:tools/infer/predict_rec.py
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
--use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True
+--use_tensorrt:False
--precision:int8
--rec_model_dir:
--image_dir:./inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..34d4007b15
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_rec_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_kl_client/
+--rec_dirname:./inference/ch_PP-OCRv2_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_kl_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..3405f2b587
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_rec_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_PP-OCRv2_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_kl_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..b807eadd3f
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv2_rec_PACT
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv2_rec_pact_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..2a174b9e31
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_rec_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv2_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v2_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v2_pact_client/
+--rec_dirname:./inference/ch_PP-OCRv2_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_pact_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..2b7ed81172
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv2_rec_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_PP-OCRv2_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v2_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v2_pact_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_infer_python.txt
index 98c125229d..0ac75eff07 100644
--- a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv2_rec_PACT
+model_name:ch_PP-OCRv2_rec_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=6|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:pretrain_models/ch_PP-OCRv2_rec_train/best_accuracy
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:True
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index e22d8a564b..e0f86d9020 100644
--- a/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,13 +1,13 @@
===========================train_params===========================
-model_name:ch_PPOCRv2_rec_PACT
+model_name:ch_PP-OCRv2_rec_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
-Global.pretrained_model:null
+Global.pretrained_model:pretrain_models/ch_PP-OCRv2_rec_train/best_accuracy
train_model_name:latest
train_infer_img_dir:./inference/rec_inference
null:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:True
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
index da17069a96..794af27d90 100644
--- a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -1,15 +1,15 @@
===========================cpp_infer_params===========================
-model_name:ocr_system_v3
+model_name:ch_PP-OCRv3
use_opencv:True
infer_model:./inference/ch_PP-OCRv3_det_infer/
infer_quant:False
inference:./deploy/cpp_infer/build/ppocr --rec_img_h=48 --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--rec_model_dir:./inference/ch_PP-OCRv3_rec_infer/
diff --git a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index a044826501..afacdc1405 100644
--- a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -6,10 +6,10 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_system.py --rec_image_shape="3,48,320"
--use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
new file mode 100644
index 0000000000..bf2556ef17
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -0,0 +1,17 @@
+===========================paddle2onnx_params===========================
+model_name:ch_PP-OCRv3
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/ch_PP-OCRv3_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/det_v3_onnx/model.onnx
+--rec_model_dir:./inference/ch_PP-OCRv3_rec_infer/
+--rec_save_file:./inference/rec_v3_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_system.py --rec_image_shape="3,48,320"
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/00008790.jpg
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..91c57bed1b
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_client/
+--rec_dirname:./inference/ch_PP-OCRv3_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..6f699ef5c0
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_client/
+--rec_dirname:./inference/ch_PP-OCRv3_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_client/
+serving_dir:./deploy/pdserving
+web_service:web_service.py --config=config.yml --opt op.det.concurrency="1" op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
index c7a37ddd59..aecd0dd437 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -1,15 +1,15 @@
===========================cpp_infer_params===========================
-model_name:ocr_det_v3
+model_name:ch_PP-OCRv3_det
use_opencv:True
infer_model:./inference/ch_PP-OCRv3_det_infer/
infer_quant:False
inference:./deploy/cpp_infer/build/ppocr
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
index b4c681c0aa..a448713b1c 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -1,14 +1,17 @@
===========================paddle2onnx_params===========================
-model_name:ocr_det_v3
+model_name:ch_PP-OCRv3_det
python:python3.7
2onnx: paddle2onnx
---model_dir:./inference/ch_PP-OCRv3_det_infer/
+--det_model_dir:./inference/ch_PP-OCRv3_det_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---save_file:./inference/det_v3_onnx/model.onnx
+--det_save_file:./inference/det_v3_onnx/model.onnx
+--rec_model_dir:
+--rec_save_file:
--opset_version:10
--enable_onnx_checker:True
inference:tools/infer/predict_det.py
--use_gpu:True|False
--det_model_dir:
+--rec_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
index 624b13e0d5..6e2ec22cbd 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -1,18 +1,23 @@
===========================serving_params===========================
-model_name:ocr_det_v3
+model_name:ch_PP-OCRv3_det
python:python3.7
trans_model:-m paddle_serving_client.convert
---dirname:./inference/ch_PP-OCRv3_det_infer/
+--det_dirname:./inference/ch_PP-OCRv3_det_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---serving_server:./deploy/pdserving/ppocr_det_v3_serving/
---serving_client:./deploy/pdserving/ppocr_det_v3_client/
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
serving_dir:./deploy/pdserving
web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
op.det.local_service_conf.devices:gpu|null
-op.det.local_service_conf.use_mkldnn:True|False
-op.det.local_service_conf.thread_num:1|6
-op.det.local_service_conf.use_trt:False|True
-op.det.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_rpc_client.py|pipeline_http_client.py
---image_dir:../../doc/imgs
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt
index 93f673289a..a69e0ab81e 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv3_det
+model_name:ch_PP-OCRv3_det
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..7e987125a6
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_PP-OCRv3_det
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o
+quant_export:null
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 98bc36a80d..fe72cfb4e9 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv3_det
+model_name:ch_PP-OCRv3_det
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..a34ffe22ae
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv3_det_KL
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv3_det_klquant_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index e4a3aa6c61..c27e08a640 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -1,5 +1,5 @@
===========================kl_quant_params===========================
-model_name:PPOCRv3_ocr_det_kl
+model_name:ch_PP-OCRv3_det_KL
python:python3.7
Global.pretrained_model:null
Global.save_inference_dir:null
@@ -8,10 +8,10 @@ infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_PP-OCRv3/ch_
infer_quant:True
inference:tools/infer/predict_det.py
--use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:int8
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..22b429760c
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_det_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_kl_client/
+--rec_dirname:./inference/ch_PP-OCRv3_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_kl_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..23dbc49a38
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_det_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_kl_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..3198b87552
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv3_det_PACT
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv3_det_pact_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..7d300f4456
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_det_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_pact_client/
+--rec_dirname:./inference/ch_PP-OCRv3_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_pact_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..4546644cbc
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_det_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_pact_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_infer_python.txt
index f1ea7de5e5..b536e69b05 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv3_det_PACT
+model_name:ch_PP-OCRv3_det_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=1|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 6d6862607a..252378e4dc 100644
--- a/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv3_det_PACT
+model_name:ch_PP-OCRv3_det_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml b/test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml
index 4c8ba0a6fa..f704a1dfb5 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml
@@ -153,7 +153,7 @@ Train:
data_dir: ./train_data/ic15_data/
ext_op_transform_idx: 1
label_file_list:
- - ./train_data/ic15_data/rec_gt_train.txt
+ - ./train_data/ic15_data/rec_gt_train_lite.txt
transforms:
- DecodeImage:
img_mode: BGR
@@ -183,7 +183,7 @@ Eval:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list:
- - ./train_data/ic15_data/rec_gt_test.txt
+ - ./train_data/ic15_data/rec_gt_test_lite.txt
transforms:
- DecodeImage:
img_mode: BGR
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
index 46b1c96c92..9d6ca2cf5e 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -1,15 +1,15 @@
===========================cpp_infer_params===========================
-model_name:ocr_rec_v3
+model_name:ch_PP-OCRv3_rec
use_opencv:True
infer_model:./inference/ch_PP-OCRv3_rec_infer/
infer_quant:False
inference:./deploy/cpp_infer/build/ppocr --rec_img_h=48 --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:6
---use_tensorrt:False|True
---precision:fp32|fp16
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference/
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
index eb1cbb9044..9114c0acfd 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -1,14 +1,17 @@
===========================paddle2onnx_params===========================
-model_name:ocr_rec_v3
+model_name:ch_PP-OCRv3_rec
python:python3.7
2onnx: paddle2onnx
---model_dir:./inference/ch_PP-OCRv3_rec_infer/
+--det_model_dir:
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---save_file:./inference/rec_v3_onnx/model.onnx
+--det_save_file:
+--rec_model_dir:./inference/ch_PP-OCRv3_rec_infer/
+--rec_save_file:./inference/rec_v3_onnx/model.onnx
--opset_version:10
--enable_onnx_checker:True
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
+--det_model_dir:
--rec_model_dir:
---image_dir:./inference/rec_inference
\ No newline at end of file
+--image_dir:./inference/rec_inference/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
index 89bde9c8ce..f01db2e950 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -1,18 +1,23 @@
===========================serving_params===========================
-model_name:ocr_rec_v3
+model_name:ch_PP-OCRv3_rec
python:python3.7
trans_model:-m paddle_serving_client.convert
---dirname:./inference/ch_PP-OCRv3_rec_infer/
+--det_dirname:null
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---serving_server:./deploy/pdserving/ppocr_rec_v3_serving/
---serving_client:./deploy/pdserving/ppocr_rec_v3_client/
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_PP-OCRv3_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_client/
serving_dir:./deploy/pdserving
web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
-op.rec.local_service_conf.devices:gpu|null
-op.rec.local_service_conf.use_mkldnn:False
-op.rec.local_service_conf.thread_num:1|6
-op.rec.local_service_conf.use_trt:False|True
-op.rec.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_rpc_client.py|pipeline_http_client.py
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt
index c333c08330..1feb9d49fc 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:PPOCRv3_ocr_rec
+model_name:ch_PP-OCRv3_rec
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..7fcc8b4418
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_PP-OCRv3_rec
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o
+quant_export:
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv3_rec_infer
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1|6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,48,320]}]
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 47cc3e2f53..99e3c42477 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:PPOCRv3_ocr_rec
+model_name:ch_PP-OCRv3_rec
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
---rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..f1a308fcc8
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv3_rec_KL
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv3_rec_klquant_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_img_h=48 --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 51ad29a4ed..d1a8c7c001 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -1,17 +1,17 @@
===========================kl_quant_params===========================
-model_name:PPOCRv3_ocr_rec_kl
+model_name:ch_PP-OCRv3_rec_KL
python:python3.7
-Global.pretrained_model:null
+Global.pretrained_model:
Global.save_inference_dir:null
infer_model:./inference/ch_PP-OCRv3_rec_infer/
infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o
infer_quant:True
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True
+--use_tensorrt:False
--precision:int8
--rec_model_dir:
--image_dir:./inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..fa6f04e48c
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_rec_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_kl_client/
+--rec_dirname:./inference/ch_PP-OCRv3_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_kl_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..68586af0d9
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_rec_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_PP-OCRv3_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_kl_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..8fc1132ca6
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_PP-OCRv3_rec_PACT
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv3_rec_pact_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_img_h=48 --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..008df50d6d
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_rec_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_PP-OCRv3_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_v3_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_v3_pact_client/
+--rec_dirname:./inference/ch_PP-OCRv3_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_pact_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..826f586f0c
--- /dev/null
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_PP-OCRv3_rec_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_PP-OCRv3_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_v3_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_v3_pact_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_infer_python.txt
index fd7d61c372..24469a91cf 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_infer_python.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_infer_python.txt
@@ -1,10 +1,10 @@
===========================train_params===========================
-model_name:ch_PPOCRv3_rec_PACT
+model_name:ch_PP-OCRv3_rec_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=6|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
Global.pretrained_model:pretrain_models/ch_PP-OCRv3_rec_train/best_accuracy
@@ -34,16 +34,16 @@ distill_export:null
export1:null
export2:null
inference_dir:Student
-infer_model:./inference/ch_PP-OCRv3_rec_slim_quant_infer
+infer_model:./inference/ch_PP-OCRv3_rec_slim_infer
infer_export:null
infer_quant:True
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 6049a377a6..c93b307deb 100644
--- a/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -1,13 +1,13 @@
===========================train_params===========================
-model_name:ch_PPOCRv3_rec_PACT
+model_name:ch_PP-OCRv3_rec_PACT
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
-Global.pretrained_model:null
+Global.pretrained_model:pretrain_models/ch_PP-OCRv3_rec_train/best_accuracy
train_model_name:latest
train_infer_img_dir:./inference/rec_inference
null:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:True
inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
---rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..b42ab9db36
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_mobile_v2.0
+use_opencv:True
+infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--benchmark:True
+--det:True
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 4a46f0cf09..becad991ea 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -6,10 +6,10 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_system.py
--use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
new file mode 100644
index 0000000000..17c2fbbae2
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -0,0 +1,17 @@
+===========================paddle2onnx_params===========================
+model_name:ch_ppocr_mobile_v2.0
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/det_mobile_onnx/model.onnx
+--rec_model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--rec_save_file:./inference/rec_mobile_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_system.py --rec_image_shape="3,32,320"
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..d18e9f11fd
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_client/
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..842c934017
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_client/
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_client/
+serving_dir:./deploy/pdserving
+web_service:web_service.py --config=config.yml --opt op.det.concurrency="1" op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
index d0ae17ccb5..1d1c2ae283 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -1,15 +1,15 @@
===========================cpp_infer_params===========================
-model_name:ocr_det
+model_name:ch_ppocr_mobile_v2.0_det
use_opencv:True
infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
infer_quant:False
inference:./deploy/cpp_infer/build/ppocr
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt
index 7d3f60bd42..24bb8746ab 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt
@@ -1,5 +1,5 @@
===========================infer_params===========================
-model_name:ocr_det
+model_name:ch_ppocr_mobile_v2.0_det
python:python
infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer
infer_export:null
@@ -7,10 +7,10 @@ infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
--enable_mkldnn:False
---cpu_threads:1|6
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp16|fp32
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
index 160bcdbd88..00473d1062 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -1,14 +1,17 @@
===========================paddle2onnx_params===========================
-model_name:ocr_det_mobile
+model_name:ch_ppocr_mobile_v2.0_det
python:python3.7
2onnx: paddle2onnx
---model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--det_model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---save_file:./inference/det_mobile_onnx/model.onnx
+--det_save_file:./inference/det_mobile_onnx/model.onnx
+--rec_model_dir:
+--rec_save_file:
--opset_version:10
--enable_onnx_checker:True
inference:tools/infer/predict_det.py
--use_gpu:True|False
--det_model_dir:
+--rec_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
index ed72889970..c9dd5ad920 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -1,18 +1,23 @@
===========================serving_params===========================
-model_name:ocr_det_mobile
-python:python3.7|cpp
+model_name:ch_ppocr_mobile_v2.0_det
+python:python3.7
trans_model:-m paddle_serving_client.convert
---dirname:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---serving_server:./deploy/pdserving/ppocr_det_mobile_2.0_serving/
---serving_client:./deploy/pdserving/ppocr_det_mobile_2.0_client/
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
serving_dir:./deploy/pdserving
web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
op.det.local_service_conf.devices:gpu|null
-op.det.local_service_conf.use_mkldnn:True|False
-op.det.local_service_conf.thread_num:1|6
-op.det.local_service_conf.use_trt:False|True
-op.det.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_rpc_client.py|pipeline_http_client.py
---image_dir:../../doc/imgs
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt
index 269693a86e..789ed4d23d 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt
deleted file mode 100644
index bfb71b7810..0000000000
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_fleet_amp_infer_python_linux_gpu_cpu.txt
+++ /dev/null
@@ -1,51 +0,0 @@
-===========================train_params===========================
-model_name:ocr_det
-python:python3.7
-gpu_list:xx.xx.xx.xx,yy.yy.yy.yy;0,1
-Global.use_gpu:True
-Global.auto_cast:fp32|amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
-Global.save_model_dir:./output/
-Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
-Global.pretrained_model:null
-train_model_name:latest
-train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
-null:null
-##
-trainer:norm_train|pact_train|fpgm_train
-norm_train:tools/train.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
-pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o
-fpgm_train:deploy/slim/prune/sensitivity_anal.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/det_mv3_db_v2.0_train/best_accuracy
-distill_train:null
-null:null
-null:null
-##
-===========================eval_params===========================
-eval:null
-null:null
-##
-===========================infer_params===========================
-Global.save_inference_dir:./output/
-Global.pretrained_model:
-norm_export:tools/export_model.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o
-quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o
-fpgm_export:deploy/slim/prune/export_prune_model.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o
-distill_export:null
-export1:null
-export2:null
-inference_dir:null
-train_model:./inference/ch_ppocr_mobile_v2.0_det_train/best_accuracy
-infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o
-infer_quant:False
-inference:tools/infer/predict_det.py
---use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
---rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
---det_model_dir:
---image_dir:./inference/ch_det_data_50/all-sum-510/
-null:null
---benchmark:True
-null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..5271f78bb7
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_det
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:null
+Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_dir:null
+train_model:./inference/ch_ppocr_mobile_v2.0_det_train/best_accuracy
+infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 593e7ec7ed..6b3352f741 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_mac_cpu_normal_normal_infer_python_mac_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_mac_cpu_normal_normal_infer_python_mac_cpu.txt
index 014dad5fc9..3f321a1903 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_mac_cpu_normal_normal_infer_python_mac_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_mac_cpu_normal_normal_infer_python_mac_cpu.txt
@@ -4,7 +4,7 @@ python:python
gpu_list:-1
Global.use_gpu:False
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt
index 6a63b39d97..a3f6933a64 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_windows_gpu_normal_normal_infer_python_windows_cpu_gpu.txt
@@ -4,7 +4,7 @@ python:python
gpu_list:0
Global.use_gpu:True
Global.auto_cast:fp32|amp
-Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,10 +39,10 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
+--enable_mkldnn:False
--cpu_threads:1|6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:fp32|fp16|int8
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_infer_python.txt
index 47ccf2e69e..dae3f8053a 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 5a95f02685..150a8a0315 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..eb2fd0a001
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_KL
+use_opencv:True
+infer_model:./inference/ch_ppocr_mobile_v2.0_det_klquant_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 1039dcad06..2bdec84883 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -8,10 +8,10 @@ infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_ppocr_v2.0/c
infer_quant:True
inference:tools/infer/predict_det.py
--use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:int8
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..d9de1cc19a
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_kl_client/
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_kl_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..049ec78458
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_kl_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..17723f41ab
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_PACT
+use_opencv:True
+infer_model:./inference/ch_ppocr_mobile_v2.0_det_pact_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..1a49a10f9b
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_pact_client/
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_pact_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..909d738919
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_pact_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_infer_python.txt
index 9d2855d824..04c8d0e194 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=20|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 1f9bec12ad..3a5d8faf3f 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=20|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..480fb16cdd
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec
+use_opencv:True
+infer_model:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
index f29b303879..5bab0c9e4c 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -1,14 +1,17 @@
===========================paddle2onnx_params===========================
-model_name:ocr_rec_mobile
+model_name:ch_ppocr_mobile_v2.0_rec
python:python3.7
2onnx: paddle2onnx
---model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--det_model_dir:
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---save_file:./inference/rec_mobile_onnx/model.onnx
+--det_save_file:
+--rec_model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--rec_save_file:./inference/rec_mobile_onnx/model.onnx
--opset_version:10
--enable_onnx_checker:True
-inference:tools/infer/predict_rec.py
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
--use_gpu:True|False
+--det_model_dir:
--rec_model_dir:
---image_dir:./inference/rec_inference
\ No newline at end of file
+--image_dir:./inference/rec_inference/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
index f890eff469..c0c5291cc4 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -1,18 +1,23 @@
===========================serving_params===========================
-model_name:ocr_rec_mobile
-python:python3.7|cpp
+model_name:ch_ppocr_mobile_v2.0_rec
+python:python3.7
trans_model:-m paddle_serving_client.convert
---dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--det_dirname:null
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---serving_server:./deploy/pdserving/ppocr_rec_mobile_2.0_serving/
---serving_client:./deploy/pdserving/ppocr_rec_mobile_2.0_client/
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_client/
serving_dir:./deploy/pdserving
-web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1
-op.rec.local_service_conf.devices:"0"|null
-op.rec.local_service_conf.use_mkldnn:True|False
-op.rec.local_service_conf.thread_num:1|6
-op.rec.local_service_conf.use_trt:False|True
-op.rec.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_rpc_client.py|pipeline_http_client.py
---image_dir:../../doc/imgs_words_en
\ No newline at end of file
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt
index 5086f80d7b..f02b93926c 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..631118c0a9
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:null
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/rec/rec_icdar15_train.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c configs/rec/rec_icdar15_train.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/ch_ppocr_mobile_v2.0_rec_train/best_accuracy
+infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1|6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,100]}]
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 30fb939bff..bd9c4a8df2 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_infer_python.txt
index 77494ac347..89daceeb5f 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index fda9cf4dde..7abc3e9340 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
null:null
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..adf06257a7
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_KL
+use_opencv:True
+infer_model:./inference/ch_ppocr_mobile_v2.0_rec_klquant_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 4b77994f3f..f63fe4c2bb 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -6,12 +6,12 @@ Global.save_inference_dir:null
infer_model:./inference/ch_ppocr_mobile_v2.0_rec_infer/
infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/rec_chinese_lite_train_v2.0.yml -o
infer_quant:True
-inference:tools/infer/predict_rec.py
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
--use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
--precision:int8
--rec_model_dir:
--image_dir:./inference/rec_inference
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..ab518de55a
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_klquant_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_kl_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_kl_client/
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_kl_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..948e3dceb3
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_KL
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_klquant_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_kl_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_kl_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..ba2df90f75
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_PACT
+use_opencv:True
+infer_model:./inference/ch_ppocr_mobile_v2.0_rec_pact_infer
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..229f70cf35
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_mobile_v2.0_det_pact_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_mobile_pact_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_mobile_pact_client/
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_pact_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..f123f36543
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_PACT
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:null
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_ppocr_mobile_v2.0_rec_pact_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_mobile_pact_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_mobile_pact_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_infer_python.txt
index 94909ec340..77472fbdfb 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.checkpoints:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index abed3cfba9..a1a2a8e63d 100644
--- a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
Global.checkpoints:null
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:False|True
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..7c980b2bae
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_server_v2.0
+use_opencv:True
+infer_model:./inference/ch_ppocr_server_v2.0_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+--benchmark:True
+--det:True
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
index 92d7031e88..b20596f7a1 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -6,8 +6,8 @@ infer_export:null
infer_quant:True
inference:tools/infer/predict_system.py
--use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
--precision:fp32
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
new file mode 100644
index 0000000000..e478896a54
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -0,0 +1,17 @@
+===========================paddle2onnx_params===========================
+model_name:ch_ppocr_server_v2.0
+python:python3.7
+2onnx: paddle2onnx
+--det_model_dir:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_save_file:./inference/det_server_onnx/model.onnx
+--rec_model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+--rec_save_file:./inference/rec_server_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_system.py --rec_image_shape="3,32,320"
+--use_gpu:True|False
+--det_model_dir:
+--rec_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/00008790.jpg
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..bbfec44dba
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,19 @@
+===========================serving_params===========================
+model_name:ch_ppocr_server_v2.0
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_server_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_server_client/
+--rec_dirname:./inference/ch_ppocr_server_v2.0_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_server_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_server_client/
+serving_dir:./deploy/pdserving
+web_service:-m paddle_serving_server.serve
+--op:GeneralDetectionOp GeneralInferOp
+--port:8181
+--gpu_id:"0"|null
+cpp_client:ocr_cpp_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..8853e709d4
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -0,0 +1,23 @@
+===========================serving_params===========================
+model_name:ch_ppocr_server_v2.0
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--det_dirname:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--det_serving_server:./deploy/pdserving/ppocr_det_server_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_server_client/
+--rec_dirname:./inference/ch_ppocr_server_v2.0_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_server_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_server_client/
+serving_dir:./deploy/pdserving
+web_service:web_service.py --config=config.yml --opt op.det.concurrency="1" op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..69ae939e2b
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_server_v2.0_det
+use_opencv:True
+infer_model:./inference/ch_ppocr_server_v2.0_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
index 40fdc11241..c8bebf54f2 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -1,14 +1,17 @@
===========================paddle2onnx_params===========================
-model_name:ocr_det_server
+model_name:ch_ppocr_server_v2.0_det
python:python3.7
2onnx: paddle2onnx
---model_dir:./inference/ch_ppocr_server_v2.0_det_infer/
+--det_model_dir:./inference/ch_ppocr_server_v2.0_det_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---save_file:./inference/det_server_onnx/model.onnx
+--det_save_file:./inference/det_server_onnx/model.onnx
+--rec_model_dir:
+--rec_save_file:
--opset_version:10
--enable_onnx_checker:True
inference:tools/infer/predict_det.py
--use_gpu:True|False
--det_model_dir:
---image_dir:./inference/det_inference
\ No newline at end of file
+--rec_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/00008790.jpg
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
index ec54646046..018dd1a227 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -1,18 +1,23 @@
===========================serving_params===========================
-model_name:ocr_det_server
-python:python3.7|cpp
+model_name:ch_ppocr_server_v2.0_det
+python:python3.7
trans_model:-m paddle_serving_client.convert
---dirname:./inference/ch_ppocr_server_v2.0_det_infer/
+--det_dirname:./inference/ch_ppocr_server_v2.0_det_infer/
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---serving_server:./deploy/pdserving/ppocr_det_server_2.0_serving/
---serving_client:./deploy/pdserving/ppocr_det_server_2.0_client/
+--det_serving_server:./deploy/pdserving/ppocr_det_server_serving/
+--det_serving_client:./deploy/pdserving/ppocr_det_server_client/
+--rec_dirname:null
+--rec_serving_server:null
+--rec_serving_client:null
serving_dir:./deploy/pdserving
-web_service:web_service_det.py --config=config.yml --opt op.det.concurrency=1
-op.det.local_service_conf.devices:"0"|null
-op.det.local_service_conf.use_mkldnn:True|False
-op.det.local_service_conf.thread_num:1|6
-op.det.local_service_conf.use_trt:False|True
-op.det.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_rpc_client.py|pipeline_http_client.py
---image_dir:../../doc/imgs
\ No newline at end of file
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py
+--image_dir:../../doc/imgs/1.jpg
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt
index 52489fe529..c16ca15002 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_lite_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_res18_db_
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..12388d9677
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_ppocr_server_v2.0_det
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:null
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_lite_infer=4
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml -o
+quant_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/ch_ppocr_server_v2.0_det_train/best_accuracy
+infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml -o
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--save_log_path:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 3e3764e8c6..93ed14cb60 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -4,7 +4,7 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_lite_infer=4
Global.pretrained_model:null
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_res18_db_
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..cbec272cce
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ch_ppocr_server_v2.0_rec
+use_opencv:True
+infer_model:./inference/ch_ppocr_server_v2.0_rec_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_img_h=32
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+--det:False
+--rec:True
+--cls:False
+--use_angle_cls:False
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
index 05542332e9..462f6090d9 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
@@ -1,14 +1,17 @@
===========================paddle2onnx_params===========================
-model_name:ocr_rec_server
+model_name:ch_ppocr_server_v2.0_rec
python:python3.7
2onnx: paddle2onnx
---model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+--det_model_dir:
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---save_file:./inference/rec_server_onnx/model.onnx
+--det_save_file:
+--rec_model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+--rec_save_file:./inference/rec_server_onnx/model.onnx
--opset_version:10
--enable_onnx_checker:True
-inference:tools/infer/predict_rec.py
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
--use_gpu:True|False
+--det_model_dir:
--rec_model_dir:
---image_dir:./inference/rec_inference
\ No newline at end of file
+--image_dir:./inference/rec_inference/
\ No newline at end of file
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
index d72abc6054..7f456320b6 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_rec/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
@@ -1,18 +1,23 @@
===========================serving_params===========================
-model_name:ocr_rec_server
-python:python3.7|cpp
+model_name:ch_ppocr_server_v2.0_rec
+python:python3.7
trans_model:-m paddle_serving_client.convert
---dirname:./inference/ch_ppocr_server_v2.0_rec_infer/
+--det_dirname:null
--model_filename:inference.pdmodel
--params_filename:inference.pdiparams
---serving_server:./deploy/pdserving/ppocr_rec_server_2.0_serving/
---serving_client:./deploy/pdserving/ppocr_rec_server_2.0_client/
+--det_serving_server:null
+--det_serving_client:null
+--rec_dirname:./inference/ch_ppocr_server_v2.0_rec_infer/
+--rec_serving_server:./deploy/pdserving/ppocr_rec_server_serving/
+--rec_serving_client:./deploy/pdserving/ppocr_rec_server_client/
serving_dir:./deploy/pdserving
-web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1
-op.rec.local_service_conf.devices:"0"|null
-op.rec.local_service_conf.use_mkldnn:True|False
-op.rec.local_service_conf.thread_num:1|6
-op.rec.local_service_conf.use_trt:False|True
-op.rec.local_service_conf.precision:fp32|fp16|int8
-pipline:pipeline_rpc_client.py|pipeline_http_client.py
---image_dir:../../doc/imgs_words_en
\ No newline at end of file
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:False
+op.det.local_service_conf.thread_num:6
+op.det.local_service_conf.use_trt:False
+op.det.local_service_conf.precision:fp32
+op.det.local_service_conf.model_config:
+op.rec.local_service_conf.model_config:
+pipline:pipeline_http_client.py --det=False
+--image_dir:../../inference/rec_inference
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
index 78a046c503..64c0cf455c 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..9884ab247b
--- /dev/null
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_ppocr_server_v2.0_rec
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:null
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=100
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/ch_ppocr_server_v2.0_rec_train/best_accuracy
+infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1|6
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,100]}]
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
index 78c15047fb..63ddaa4a8b 100644
--- a/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
+++ b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec
infer_quant:False
inference:tools/infer/predict_rec.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt b/test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt
index fab8f50d54..ab3aa59b60 100644
--- a/test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt
+++ b/test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/det_mv3_db.yml -o
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt b/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt
index 5634297973..1ec1597a4d 100644
--- a/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/det_mv3_east_v2.0/det_mv
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|fp16|int8
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/det_mv3_pse_v2.0/train_infer_python.txt b/test_tipc/configs/det_mv3_pse_v2.0/train_infer_python.txt
index 661adc4a32..daeec69f84 100644
--- a/test_tipc/configs/det_mv3_pse_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/det_mv3_pse_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/det_mv3_pse_v2.0/det_mv3
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|fp16
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/det_r18_vd_db_v2_0/train_infer_python.txt b/test_tipc/configs/det_r18_vd_db_v2_0/train_infer_python.txt
index 77023ef2c1..33e4dbf233 100644
--- a/test_tipc/configs/det_r18_vd_db_v2_0/train_infer_python.txt
+++ b/test_tipc/configs/det_r18_vd_db_v2_0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt b/test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt
index 3fd875711e..151f2769cc 100644
--- a/test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/det/det_r50_vd_db.yml -o
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
---use_tensorrt:False|True
---precision:fp32|fp16|int8
+--use_tensorrt:False
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/det_r50_vd_east_v2_0/train_infer_python.txt b/test_tipc/configs/det_r50_vd_east_v2_0/train_infer_python.txt
index c1748c5d2f..8477a4fa74 100644
--- a/test_tipc/configs/det_r50_vd_east_v2_0/train_infer_python.txt
+++ b/test_tipc/configs/det_r50_vd_east_v2_0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_east_v2_0/det
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|fp16|int8
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/det_r50_vd_pse_v2_0/train_infer_python.txt b/test_tipc/configs/det_r50_vd_pse_v2_0/train_infer_python.txt
index 55ebcd3547..62da89fe1c 100644
--- a/test_tipc/configs/det_r50_vd_pse_v2_0/train_infer_python.txt
+++ b/test_tipc/configs/det_r50_vd_pse_v2_0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_pse_v2_0/det_
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|fp16|int8
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
diff --git a/test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/train_infer_python.txt b/test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/train_infer_python.txt
index 16f37ace6f..b70ef46b4a 100644
--- a/test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/train_infer_python.txt
@@ -4,16 +4,16 @@ python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=5000
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
-Global.pretrained_model:null
+Global.pretrained_model:./pretrain_models/det_r50_vd_sast_icdar15_v2.0_train/best_accuracy
train_model_name:latest
train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
null:null
##
trainer:norm_train
-norm_train:tools/train.py -c test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/det_r50_vd_sast_icdar2015.yml -o Global.pretrained_model=./pretrain_models/ResNet50_vd_ssld_pretrained
+norm_train:tools/train.py -c test_tipc/configs/det_r50_vd_sast_icdar15_v2.0/det_r50_vd_sast_icdar2015.yml -o
pact_train:null
fpgm_train:null
distill_train:null
@@ -39,13 +39,13 @@ infer_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_sast_icdar15_
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|int8
+--precision:fp32
--det_model_dir:
---image_dir:./inference/ch_det_data_50/all-sum-510/
+--image_dir:./inference/ch_det_data_50/all-sum-510/00008790.jpg
null:null
--benchmark:True
--det_algorithm:SAST
diff --git a/test_tipc/configs/det_r50_vd_sast_totaltext_v2.0/train_infer_python.txt b/test_tipc/configs/det_r50_vd_sast_totaltext_v2.0/train_infer_python.txt
index 5e4c5666b7..7be5af7dde 100644
--- a/test_tipc/configs/det_r50_vd_sast_totaltext_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/det_r50_vd_sast_totaltext_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_sast_totaltex
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|int8
+--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/en_server_pgnetA/train_infer_python.txt b/test_tipc/configs/en_server_pgnetA/train_infer_python.txt
index 8a1509baab..a9dd4e676b 100644
--- a/test_tipc/configs/en_server_pgnetA/train_infer_python.txt
+++ b/test_tipc/configs/en_server_pgnetA/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c configs/e2e/e2e_r50_vd_pg.yml -o
infer_quant:False
inference:tools/infer/predict_e2e.py
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
---precision:fp32|fp16|int8
+--precision:fp32
--e2e_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
null:null
diff --git a/test_tipc/configs/en_table_structure/table_mv3.yml b/test_tipc/configs/en_table_structure/table_mv3.yml
new file mode 100755
index 0000000000..adf326bd02
--- /dev/null
+++ b/test_tipc/configs/en_table_structure/table_mv3.yml
@@ -0,0 +1,117 @@
+Global:
+ use_gpu: true
+ epoch_num: 10
+ log_smooth_window: 20
+ print_batch_step: 5
+ save_model_dir: ./output/table_mv3/
+ save_epoch_step: 3
+ # evaluation is run every 400 iterations after the 0th iteration
+ eval_batch_step: [0, 400]
+ cal_metric_during_train: True
+ pretrained_model:
+ checkpoints:
+ save_inference_dir:
+ use_visualdl: False
+ infer_img: doc/table/table.jpg
+ # for data or label process
+ character_dict_path: ppocr/utils/dict/table_structure_dict.txt
+ character_type: en
+ max_text_length: 100
+ max_elem_length: 800
+ max_cell_num: 500
+ infer_mode: False
+ process_total_num: 0
+ process_cut_num: 0
+
+Optimizer:
+ name: Adam
+ beta1: 0.9
+ beta2: 0.999
+ clip_norm: 5.0
+ lr:
+ learning_rate: 0.001
+ regularizer:
+ name: 'L2'
+ factor: 0.00000
+
+Architecture:
+ model_type: table
+ algorithm: TableAttn
+ Backbone:
+ name: MobileNetV3
+ scale: 1.0
+ model_name: large
+ Head:
+ name: TableAttentionHead
+ hidden_size: 256
+ l2_decay: 0.00001
+ loc_type: 2
+ max_text_length: 100
+ max_elem_length: 800
+ max_cell_num: 500
+
+Loss:
+ name: TableAttentionLoss
+ structure_weight: 100.0
+ loc_weight: 10000.0
+
+PostProcess:
+ name: TableLabelDecode
+
+Metric:
+ name: TableMetric
+ main_indicator: acc
+
+Train:
+ dataset:
+ name: PubTabDataSet
+ data_dir: ./train_data/pubtabnet/train
+ label_file_path: ./train_data/pubtabnet/train.jsonl
+ transforms:
+ - DecodeImage: # load image
+ img_mode: BGR
+ channel_first: False
+ - ResizeTableImage:
+ max_len: 488
+ - TableLabelEncode:
+ - NormalizeImage:
+ scale: 1./255.
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: 'hwc'
+ - PaddingTableImage:
+ - ToCHWImage:
+ - KeepKeys:
+ keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
+ loader:
+ shuffle: True
+ batch_size_per_card: 32
+ drop_last: True
+ num_workers: 1
+
+Eval:
+ dataset:
+ name: PubTabDataSet
+ data_dir: ./train_data/pubtabnet/test/
+ label_file_path: ./train_data/pubtabnet/test.jsonl
+ transforms:
+ - DecodeImage: # load image
+ img_mode: BGR
+ channel_first: False
+ - ResizeTableImage:
+ max_len: 488
+ - TableLabelEncode:
+ - NormalizeImage:
+ scale: 1./255.
+ mean: [0.485, 0.456, 0.406]
+ std: [0.229, 0.224, 0.225]
+ order: 'hwc'
+ - PaddingTableImage:
+ - ToCHWImage:
+ - KeepKeys:
+ keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
+ loader:
+ shuffle: False
+ drop_last: False
+ batch_size_per_card: 16
+ num_workers: 1
diff --git a/test_tipc/configs/en_table_structure/train_infer_python.txt b/test_tipc/configs/en_table_structure/train_infer_python.txt
new file mode 100644
index 0000000000..d9f3b30e16
--- /dev/null
+++ b/test_tipc/configs/en_table_structure/train_infer_python.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:en_table_structure
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+quant_export:
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:False
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]
diff --git a/test_tipc/configs/en_table_structure/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/en_table_structure/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..31ac1ed53f
--- /dev/null
+++ b/test_tipc/configs/en_table_structure/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:en_table_structure
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+quant_export:
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:False
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]
diff --git a/test_tipc/configs/en_table_structure_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/en_table_structure_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..e8f7bbaa50
--- /dev/null
+++ b/test_tipc/configs/en_table_structure_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,21 @@
+===========================train_params===========================
+model_name:en_table_structure_KL
+python:python3.7
+Global.pretrained_model:
+Global.save_inference_dir:null
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer/
+infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+infer_quant:True
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:int8
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+null:null
diff --git a/test_tipc/configs/en_table_structure_PACT/train_infer_python.txt b/test_tipc/configs/en_table_structure_PACT/train_infer_python.txt
new file mode 100644
index 0000000000..f62e8b68bc
--- /dev/null
+++ b/test_tipc/configs/en_table_structure_PACT/train_infer_python.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:en_table_structure_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:null
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:True
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]
diff --git a/test_tipc/configs/en_table_structure_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt b/test_tipc/configs/en_table_structure_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
new file mode 100644
index 0000000000..d7c847fcdc
--- /dev/null
+++ b/test_tipc/configs/en_table_structure_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt
@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:en_table_structure_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:./pretrain_models/en_ppocr_mobile_v2.0_table_structure_train/best_accuracy
+train_model_name:latest
+train_infer_img_dir:./ppstructure/docs/table/table.jpg
+null:null
+##
+trainer:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:null
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
+fpgm_export:
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/en_ppocr_mobile_v2.0_table_structure_infer
+infer_export:null
+infer_quant:True
+inference:ppstructure/table/predict_table.py --det_model_dir=./inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=./inference/en_ppocr_mobile_v2.0_table_rec_infer --rec_char_dict_path=./ppocr/utils/dict/table_dict.txt --table_char_dict_path=./ppocr/utils/dict/table_structure_dict.txt --image_dir=./ppstructure/docs/table/table.jpg --det_limit_side_len=736 --det_limit_type=min --output ./output/table
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--table_model_dir:
+--image_dir:./ppstructure/docs/table/table.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,488,488]}]
diff --git a/test_tipc/configs/rec_mtb_nrtr/train_infer_python.txt b/test_tipc/configs/rec_mtb_nrtr/train_infer_python.txt
index de6de5a0ca..fed8ba2675 100644
--- a/test_tipc/configs/rec_mtb_nrtr/train_infer_python.txt
+++ b/test_tipc/configs/rec_mtb_nrtr/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_mtb_nrtr/rec_mtb_nrt
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/EN_symbol_dict.txt --rec_image_shape="1,32,100" --rec_algorithm="NRTR"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt b/test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
index e67dd15090..39bf922790 100644
--- a/test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_none_bilstm_ctc_
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt b/test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt
index aa3e88d284..593de3ff20 100644
--- a/test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_none_none_ctc_v2
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/train_infer_python.txt b/test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/train_infer_python.txt
index c22767c60f..1b2d9abb0f 100644
--- a/test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_tps_bilstm_att_v
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100" --rec_algorithm="RARE" --min_subgraph_size=5
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt b/test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt
index 7a3096eb1e..1367c7abd4 100644
--- a/test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_tps_bilstm_ctc_v
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100" --rec_algorithm="StarNet"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_r31_sar/train_infer_python.txt b/test_tipc/configs/rec_r31_sar/train_infer_python.txt
index 1a32a3d507..03ec54abb6 100644
--- a/test_tipc/configs/rec_r31_sar/train_infer_python.txt
+++ b/test_tipc/configs/rec_r31_sar/train_infer_python.txt
@@ -38,12 +38,12 @@ train_model:./inference/rec_r31_sar_train/best_accuracy
infer_export:tools/export_model.py -c test_tipc/configs/rec_r31_sar/rec_r31_sar.yml -o
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/dict90.txt --rec_image_shape="3,48,48,160" --rec_algorithm="SAR"
---use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--use_gpu:True
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt b/test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt
index 02cea56fbe..46aa3d7190 100644
--- a/test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_none_bilstm_c
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt b/test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt
index 5e7c1d3431..3e066d7b72 100644
--- a/test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_none_none_ctc
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_r34_vd_tps_bilstm_att_v2.0/train_infer_python.txt b/test_tipc/configs/rec_r34_vd_tps_bilstm_att_v2.0/train_infer_python.txt
index 55e937881b..1e4f46633e 100644
--- a/test_tipc/configs/rec_r34_vd_tps_bilstm_att_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_r34_vd_tps_bilstm_att_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_tps_bilstm_at
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100" --rec_algorithm="RARE" --min_subgraph_size=5
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt b/test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt
index 5b5ba0fd01..9e795b6645 100644
--- a/test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt
+++ b/test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_tps_bilstm_ct
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100" --rec_algorithm="StarNet"
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/configs/rec_r50_fpn_vd_none_srn/train_infer_python.txt b/test_tipc/configs/rec_r50_fpn_vd_none_srn/train_infer_python.txt
index 4877512b68..b5a5286010 100644
--- a/test_tipc/configs/rec_r50_fpn_vd_none_srn/train_infer_python.txt
+++ b/test_tipc/configs/rec_r50_fpn_vd_none_srn/train_infer_python.txt
@@ -39,11 +39,11 @@ infer_export:tools/export_model.py -c test_tipc/configs/rec_r50_fpn_vd_none_srn/
infer_quant:False
inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="1,64,256" --rec_algorithm="SRN" --use_space_char=False --min_subgraph_size=3
--use_gpu:True|False
---enable_mkldnn:True|False
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
--rec_batch_num:1|6
---use_tensorrt:True|False
---precision:fp32|int8
+--use_tensorrt:False
+--precision:fp32
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
diff --git a/test_tipc/docs/test_serving.md b/test_tipc/docs/test_serving.md
index 8600eff3b9..71f01c0d5f 100644
--- a/test_tipc/docs/test_serving.md
+++ b/test_tipc/docs/test_serving.md
@@ -1,6 +1,6 @@
# PaddleServing预测功能测试
-PaddleServing预测功能测试的主程序为`test_serving.sh`，可以测试基于PaddleServing的部署功能。
+PaddleServing预测功能测试的主程序为`test_serving_infer_python.sh`和`test_serving_infer_cpp.sh`，可以测试基于PaddleServing的部署功能。
## 1. 测试结论汇总
@@ -17,13 +17,23 @@ PaddleServing预测功能测试的主程序为`test_serving.sh`，可以测试
运行环境配置请参考[文档](./install.md)的内容配置TIPC的运行环境。
### 2.1 功能测试
-先运行`prepare.sh`准备数据和模型，然后运行`test_serving.sh`进行测试，最终在```test_tipc/output```目录下生成`serving_infer_*.log`后缀的日志文件。
+**python serving**
+先运行`prepare.sh`准备数据和模型，然后运行`test_serving_infer_python.sh`进行测试，最终在```test_tipc/output```目录下生成`serving_infer_python*.log`后缀的日志文件。
```shell
bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt "serving_infer"
# 用法:
-bash test_tipc/test_serving.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
+bash test_tipc/test_serving_infer_python.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt "serving_infer"
+```
+**cpp serving**
+先运行`prepare.sh`准备数据和模型，然后运行`test_serving_infer_cpp.sh`进行测试，最终在```test_tipc/output```目录下生成`serving_infer_cpp*.log`后缀的日志文件。
+
+```shell
+bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt "serving_infer"
+
+# 用法:
+bash test_tipc/test_serving_infer_cpp.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0/model_linux_gpu_normal_normal_serving_cpp_linux_gpu_cpu.txt "serving_infer"
```
#### 运行结果
diff --git a/test_tipc/docs/test_train_fleet_inference_python.md b/test_tipc/docs/test_train_fleet_inference_python.md
new file mode 100644
index 0000000000..9fddb5d163
--- /dev/null
+++ b/test_tipc/docs/test_train_fleet_inference_python.md
@@ -0,0 +1,107 @@
+# Linux GPU/CPU 多机多卡训练推理测试
+
+Linux GPU/CPU 多机多卡训练推理测试的主程序为`test_train_inference_python.sh`，可以测试基于Python的模型训练、评估、推理等基本功能。
+
+## 1. 测试结论汇总
+
+- 训练相关：
+
+| 算法名称 | 模型名称 | 多机多卡 |
+| :----: | :----: | :----: |
+| PP-OCRv3 | ch_PP-OCRv3_rec | 分布式训练 |
+
+
+- 推理相关：
+
+| 算法名称 | 模型名称 | device_CPU | device_GPU | batchsize |
+| :----: | :----: | :----: | :----: | :----: |
+| PP-OCRv3 | ch_PP-OCRv3_rec | 支持 | - | 1/6 |
+
+
+## 2. 测试流程
+
+运行环境配置请参考[文档](./install.md)的内容配置TIPC的运行环境。
+
+### 2.1 功能测试
+
+#### 2.1.1 修改配置文件
+
+首先，修改配置文件中的`ip`设置: 假设两台机器的`ip`地址分别为`192.168.0.1`和`192.168.0.2`，则对应的配置文件`gpu_list`字段需要修改为`gpu_list:192.168.0.1,192.168.0.2;0,1`； `ip`地址查看命令为`ifconfig`。
+
+
+#### 2.1.2 准备数据
+
+运行`prepare.sh`准备数据和模型，以配置文件`test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt`为例，数据准备命令如下所示。
+
+```shell
+bash test_tipc/prepare.sh test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt lite_train_lite_infer
+```
+
+**注意：** 由于是多机训练，这里需要在所有的节点上均运行启动上述命令，准备数据。
+
+#### 2.1.3 修改起始端口并开始测试
+
+在多机的节点上使用下面的命令设置分布式的起始端口（否则后面运行的时候会由于无法找到运行端口而hang住），一般建议设置在`10000~20000`之间。
+
+```shell
+export FLAGS_START_PORT=17000
+```
+
+以配置文件`test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt`为例，测试方法如下所示。
+
+```shell
+bash test_tipc/test_train_inference_python.sh test_tipc/configs/ch_PP-OCRv3_rec/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt lite_train_lite_infer
+```
+
+**注意：** 由于是多机训练，这里需要在所有的节点上均运行启动上述命令进行测试。
+
+
+#### 2.1.4 输出结果
+
+输出结果如下，表示命令运行成功。
+
+```bash
+ Run successfully with command - ch_PP-OCRv3_rec - python3.7 -m paddle.distributed.launch --ips=192.168.0.1,192.168.0.2 --gpus=0,1 tools/train.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o Global.use_gpu=True Global.save_model_dir=./test_tipc/output/ch_PP-OCRv3_rec/lite_train_lite_infer/norm_train_gpus_0,1_autocast_fp32_nodes_2 Global.epoch_num=3 Global.auto_cast=fp32 Train.loader.batch_size_per_card=16 !
+ ......
+ Run successfully with command - ch_PP-OCRv3_rec - python3.7 tools/infer/predict_rec.py --rec_image_shape="3,48,320" --use_gpu=False --enable_mkldnn=False --cpu_threads=6 --rec_model_dir=./test_tipc/output/ch_PP-OCRv3_rec/lite_train_lite_infer/norm_train_gpus_0,1_autocast_fp32_nodes_2/Student --rec_batch_num=1 --image_dir=./inference/rec_inference --benchmark=True --precision=fp32 > ./test_tipc/output/ch_PP-OCRv3_rec/lite_train_lite_infer/python_infer_cpu_usemkldnn_False_threads_6_precision_fp32_batchsize_1.log 2>&1 !
+```
+
+在开启benchmark参数时，可以得到测试的详细数据，包含运行环境信息（系统版本、CUDA版本、CUDNN版本、驱动版本），Paddle版本信息，参数设置信息（运行设备、线程数、是否开启内存优化等），模型信息（模型名称、精度），数据信息（batchsize、是否为动态shape等），性能信息（CPU,GPU的占用、运行耗时、预处理耗时、推理耗时、后处理耗时），内容如下所示：
+
+```
+[2022/06/02 22:53:35] ppocr INFO:
+
+[2022/06/02 22:53:35] ppocr INFO: ---------------------- Env info ----------------------
+[2022/06/02 22:53:35] ppocr INFO: OS_version: Ubuntu 16.04
+[2022/06/02 22:53:35] ppocr INFO: CUDA_version: 10.1.243
+[2022/06/02 22:53:35] ppocr INFO: CUDNN_version: 7.6.5
+[2022/06/02 22:53:35] ppocr INFO: drivier_version: 460.32.03
+[2022/06/02 22:53:35] ppocr INFO: ---------------------- Paddle info ----------------------
+[2022/06/02 22:53:35] ppocr INFO: paddle_version: 2.3.0-rc0
+[2022/06/02 22:53:35] ppocr INFO: paddle_commit: 5d4980c052583fec022812d9c29460aff7cdc18b
+[2022/06/02 22:53:35] ppocr INFO: log_api_version: 1.0
+[2022/06/02 22:53:35] ppocr INFO: ----------------------- Conf info -----------------------
+[2022/06/02 22:53:35] ppocr INFO: runtime_device: cpu
+[2022/06/02 22:53:35] ppocr INFO: ir_optim: True
+[2022/06/02 22:53:35] ppocr INFO: enable_memory_optim: True
+[2022/06/02 22:53:35] ppocr INFO: enable_tensorrt: False
+[2022/06/02 22:53:35] ppocr INFO: enable_mkldnn: False
+[2022/06/02 22:53:35] ppocr INFO: cpu_math_library_num_threads: 6
+[2022/06/02 22:53:35] ppocr INFO: ----------------------- Model info ----------------------
+[2022/06/02 22:53:35] ppocr INFO: model_name: rec
+[2022/06/02 22:53:35] ppocr INFO: precision: fp32
+[2022/06/02 22:53:35] ppocr INFO: ----------------------- Data info -----------------------
+[2022/06/02 22:53:35] ppocr INFO: batch_size: 1
+[2022/06/02 22:53:35] ppocr INFO: input_shape: dynamic
+[2022/06/02 22:53:35] ppocr INFO: data_num: 6
+[2022/06/02 22:53:35] ppocr INFO: ----------------------- Perf info -----------------------
+[2022/06/02 22:53:35] ppocr INFO: cpu_rss(MB): 288.957, gpu_rss(MB): None, gpu_util: None%
+[2022/06/02 22:53:35] ppocr INFO: total time spent(s): 0.4824
+[2022/06/02 22:53:35] ppocr INFO: preprocess_time(ms): 0.1136, inference_time(ms): 79.5877, postprocess_time(ms): 0.6945
+```
+
+该信息可以在运行log中查看，以上面的`ch_PP-OCRv3_rec`为例，log位置在`./test_tipc/output/ch_PP-OCRv3_rec/lite_train_lite_infer/results_python.log`。
+
+如果运行失败，也会在终端中输出运行失败的日志信息以及对应的运行命令。可以基于该命令，分析运行失败的原因。
+
+**注意：** 由于分布式训练时，仅在`trainer_id=0`所在的节点中保存模型，因此其他的节点中在运行模型导出与推理时会报错，为正常现象。
diff --git a/test_tipc/prepare.sh b/test_tipc/prepare.sh
index a5c5bd2d06..cac373dedc 100644
--- a/test_tipc/prepare.sh
+++ b/test_tipc/prepare.sh
@@ -44,37 +44,46 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
# pretrain lite train data
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar --no-check-certificate
- if [[ ${model_name} =~ "PPOCRv2_det" ]];then
+ if [[ ${model_name} =~ "ch_PP-OCRv2_det" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv2_det_distill_train.tar && cd ../
fi
- if [[ ${model_name} =~ "PPOCRv3_det" ]];then
- # TODO check model link
+ if [[ ${model_name} =~ "ch_PP-OCRv3_det" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv3_det_distill_train.tar && cd ../
fi
+ if [ ${model_name} == "en_table_structure" ];then
+ wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar --no-check-certificate
+ cd ./pretrain_models/ && tar xf en_ppocr_mobile_v2.0_table_structure_train.tar && cd ../
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+ cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+ fi
cd ./pretrain_models/ && tar xf det_mv3_db_v2.0_train.tar && cd ../
rm -rf ./train_data/icdar2015
rm -rf ./train_data/ic15_data
+ rm -rf ./train_data/pubtabnet
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_lite.tar --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar --no-check-certificate
+ wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/pubtabnet.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./deploy/slim/prune https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/sen.pickle --no-check-certificate
- cd ./train_data/ && tar xf icdar2015_lite.tar && tar xf ic15_data.tar
+ cd ./train_data/ && tar xf icdar2015_lite.tar && tar xf ic15_data.tar && tar xf pubtabnet.tar
ln -s ./icdar2015_lite ./icdar2015
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_train_lite.txt --no-check-certificate
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_test_lite.txt --no-check-certificate
cd ../
cd ./inference && tar xf rec_inference.tar && cd ../
- if [ ${model_name} == "ch_PPOCRv2_det" ] || [ ${model_name} == "ch_PPOCRv2_det_PACT" ]; then
+ if [ ${model_name} == "ch_PP-OCRv2_det" ] || [ ${model_name} == "ch_PP-OCRv2_det_PACT" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_ppocr_server_v2.0_det_train.tar && cd ../
fi
- if [ ${model_name} == "ch_PPOCRv2_rec" ] || [ ${model_name} == "ch_PPOCRv2_rec_PACT" ]; then
+ if [ ${model_name} == "ch_PP-OCRv2_rec" ] || [ ${model_name} == "ch_PP-OCRv2_rec_PACT" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv2_rec_train.tar && cd ../
fi
- if [ ${model_name} == "ch_PPOCRv3_rec" ] || [ ${model_name} == "ch_PPOCRv3_rec_PACT" ]; then
- # TODO check model link
+ if [ ${model_name} == "ch_PP-OCRv3_rec" ] || [ ${model_name} == "ch_PP-OCRv3_rec_PACT" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv3_rec_train.tar && cd ../
fi
@@ -89,8 +98,9 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
fi
if [ ${model_name} == "det_r50_vd_sast_icdar15_v2.0" ] || [ ${model_name} == "det_r50_vd_sast_totaltext_v2.0" ]; then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams --no-check-certificate
+ wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/total_text_lite.tar --no-check-certificate
- cd ./train_data && tar xf total_text_lite.tar && ln -s total_text_lite total_text && cd ../
+ cd ./train_data && tar xf total_text_lite.tar && ln -s total_text_lite total_text && tar xf det_r50_vd_sast_icdar15_v2.0_train.tar && cd ../
fi
if [ ${model_name} == "det_mv3_db_v2_0" ]; then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar --no-check-certificate
@@ -114,15 +124,19 @@ elif [ ${MODE} = "whole_train_whole_infer" ];then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate
rm -rf ./train_data/icdar2015
rm -rf ./train_data/ic15_data
+ rm -rf ./train_data/pubtabnet
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar --no-check-certificate
- cd ./train_data/ && tar xf icdar2015.tar && tar xf ic15_data.tar && cd ../
- if [ ${model_name} == "ch_PPOCRv2_det" ]; then
+ wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/pubtabnet.tar --no-check-certificate
+ cd ./train_data/ && tar xf icdar2015.tar && tar xf ic15_data.tar && tar xf pubtabnet.tar
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_train_lite.txt --no-check-certificate
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_test_lite.txt --no-check-certificate
+ cd ../
+ if [ ${model_name} == "ch_PP-OCRv2_det" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv2_det_distill_train.tar && cd ../
fi
- if [ ${model_name} == "ch_PPOCRv3_det" ]; then
- # TODO check model link
+ if [ ${model_name} == "ch_PP-OCRv3_det" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv3_det_distill_train.tar && cd ../
fi
@@ -137,24 +151,41 @@ elif [ ${MODE} = "whole_train_whole_infer" ];then
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/total_text_lite.tar --no-check-certificate
cd ./train_data && tar xf total_text.tar && ln -s total_text_lite total_text && cd ../
fi
+ if [[ ${model_name} =~ "en_table_structure" ]];then
+ wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar --no-check-certificate
+ cd ./pretrain_models/ && tar xf en_ppocr_mobile_v2.0_table_structure_train.tar && cd ../
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+ cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+ fi
elif [ ${MODE} = "lite_train_whole_infer" ];then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate
rm -rf ./train_data/icdar2015
rm -rf ./train_data/ic15_data
+ rm -rf ./train_data/pubtabnet
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_infer.tar --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar --no-check-certificate
- cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar
+ wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/pubtabnet.tar --no-check-certificate
+ cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar && tar xf pubtabnet.tar
ln -s ./icdar2015_infer ./icdar2015
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_train_lite.txt --no-check-certificate
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_test_lite.txt --no-check-certificate
cd ../
- if [ ${model_name} == "ch_PPOCRv2_det" ]; then
+ if [ ${model_name} == "ch_PP-OCRv2_det" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv2_det_distill_train.tar && cd ../
fi
- if [ ${model_name} == "ch_PPOCRv3_det" ]; then
- # TODO check model link
+ if [ ${model_name} == "ch_PP-OCRv3_det" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_PP-OCRv3_det_distill_train.tar && cd ../
fi
+ if [[ ${model_name} =~ "en_table_structure" ]];then
+ wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar --no-check-certificate
+ cd ./pretrain_models/ && tar xf en_ppocr_mobile_v2.0_table_structure_train.tar && cd ../
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+ cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+ fi
elif [ ${MODE} = "whole_infer" ];then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
@@ -199,31 +230,31 @@ elif [ ${MODE} = "whole_infer" ];then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
fi
- if [[ ${model_name} =~ "ch_PPOCRv2_det" ]]; then
+ if [[ ${model_name} =~ "ch_PP-OCRv2_det" ]]; then
eval_model_name="ch_PP-OCRv2_det_infer"
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar --no-check-certificate
cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_det_data_50.tar && cd ../
fi
- if [[ ${model_name} =~ "ch_PPOCRv3_det" ]]; then
- # TODO check model link
+ if [[ ${model_name} =~ "ch_PP-OCRv3_det" ]]; then
eval_model_name="ch_PP-OCRv3_det_infer"
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_det_data_50.tar && cd ../
fi
- if [[ ${model_name} =~ "PPOCRv2_ocr_rec" ]]; then
+ if [[ ${model_name} =~ "ch_PP-OCRv2_rec" ]]; then
eval_model_name="ch_PP-OCRv2_rec_infer"
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar --no-check-certificate
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar --no-check-certificate
cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar && cd ../
fi
- if [[ ${model_name} =~ "PPOCRv3_ocr_rec" ]]; then
- # TODO check model link
+ if [[ ${model_name} =~ "ch_PP-OCRv3_rec" ]]; then
eval_model_name="ch_PP-OCRv3_rec_infer"
- echo $(pwd)
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
- # wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_quant_infer.tar --no-check-certificate
- cd ./inference && tar xf ${eval_model_name}.tar && cd ../
- # cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_PP-OCRv3_rec_slim_quant_infer.tar && cd ../
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar --no-check-certificate
+ cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar && cd ../
+ fi
+ if [[ ${model_name} == "ch_PP-OCRv3_rec_PACT" ]]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_rec_slim_infer.tar && cd ../
fi
if [ ${model_name} == "en_server_pgnetA" ]; then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/pgnet/en_server_pgnetA.tar --no-check-certificate
@@ -314,6 +345,12 @@ elif [ ${MODE} = "whole_infer" ];then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar --no-check-certificate
cd ./inference/ && tar xf det_r50_vd_east_v2.0_train.tar & cd ../
fi
+ if [[ ${model_name} =~ "en_table_structure" ]];then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+ cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+ fi
fi
if [ ${MODE} = "klquant_whole_infer" ]; then
@@ -324,28 +361,29 @@ if [ ${MODE} = "klquant_whole_infer" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
fi
- if [ ${model_name} = "PPOCRv2_ocr_rec_kl" ]; then
+ if [ ${model_name} = "ch_PP-OCRv2_rec_KL" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar --no-check-certificate
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar --no-check-certificate
cd ./train_data/ && tar xf ic15_data.tar && cd ../
cd ./inference && tar xf rec_inference.tar && tar xf ch_PP-OCRv2_rec_infer.tar && cd ../
fi
- if [ ${model_name} = "PPOCRv3_ocr_rec_kl" ]; then
- # TODO check model link
+ if [ ${model_name} = "ch_PP-OCRv3_rec_KL" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar --no-check-certificate
- cd ./train_data/ && tar xf ic15_data.tar && cd ../
+ cd ./train_data/ && tar xf ic15_data.tar
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_train_lite.txt --no-check-certificate
+ wget -nc -P ./ic15_data/ https://paddleocr.bj.bcebos.com/dataset/rec_gt_test_lite.txt --no-check-certificate
+ cd ../
cd ./inference && tar xf rec_inference.tar && tar xf ch_PP-OCRv3_rec_infer.tar && cd ../
fi
- if [ ${model_name} = "PPOCRv2_ocr_det_kl" ]; then
+ if [ ${model_name} = "ch_PP-OCRv2_det_KL" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar --no-check-certificate
cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
fi
- if [ ${model_name} = "PPOCRv3_ocr_det_kl" ]; then
- # TODO check model link
+ if [ ${model_name} = "ch_PP-OCRv3_det_KL" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
@@ -356,32 +394,114 @@ if [ ${MODE} = "klquant_whole_infer" ]; then
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar --no-check-certificate
cd ./train_data/ && tar xf ic15_data.tar && cd ../
cd ./inference && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf rec_inference.tar && cd ../
- fi
+ fi
+ if [ ${model_name} = "en_table_structure_KL" ];then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar --no-check-certificate
+ wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/pubtabnet.tar --no-check-certificate
+ cd ./inference/ && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar && cd ../
+ cd ./train_data/ && tar xf pubtabnet.tar && cd ../
+ fi
fi
if [ ${MODE} = "cpp_infer" ];then
- if [ ${model_name} = "ocr_det" ]; then
+ if [ ${model_name} = "ch_ppocr_mobile_v2.0_det" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
- elif [ ${model_name} = "ocr_det_v3" ]; then
+ elif [ ${model_name} = "ch_ppocr_mobile_v2.0_det_KL" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
- cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
- elif [ ${model_name} = "ocr_rec_v3" ]; then
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
- cd ./inference && tar xf ch_PP-OCRv3_rec_infer.tar && tar xf rec_inference.tar && cd ../
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_det_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_klquant_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_ppocr_mobile_v2.0_det_PACT" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_det_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_pact_infer.tar && tar xf ch_det_data_50.tar && cd ../
elif [ ${model_name} = "ch_ppocr_mobile_v2.0_rec" ]; then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf rec_inference.tar && cd ../
- elif [ ${model_name} = "ocr_system" ]; then
+ elif [ ${model_name} = "ch_ppocr_mobile_v2.0_rec_KL" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_rec_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_rec_klquant_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_ppocr_mobile_v2.0_rec_PACT" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_rec_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_rec_pact_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_ppocr_server_v2.0_det" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_ppocr_server_v2.0_rec" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2_det" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2_det_KL" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_det_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_klquant_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2_det_PACT" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_det_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_pact_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2_rec" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_rec_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2_rec_KL" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_rec_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_rec_klquant_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2_rec_PACT" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_rec_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_rec_pact_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3_det" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3_det_KL" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_det_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_klquant_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3_det_PACT" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_det_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_pact_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3_rec" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_rec_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3_rec_KL" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_rec_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_rec_klquant_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3_rec_PACT" ]; then
+ wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_rec_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_rec_pact_infer.tar && tar xf rec_inference.tar && cd ../
+ elif [ ${model_name} = "ch_ppocr_mobile_v2.0" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
- elif [ ${model_name} = "ocr_system_v3" ]; then
+ elif [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv2" ]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && tar xf ch_PP-OCRv2_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
+ elif [ ${model_name} = "ch_PP-OCRv3" ]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
@@ -395,36 +515,84 @@ if [ ${MODE} = "serving_infer" ];then
IFS='|'
array=(${python_name_list})
python_name=${array[0]}
- ${python_name} -m pip install paddle-serving-server-gpu==0.8.3.post101
- ${python_name} -m pip install paddle_serving_client==0.8.3
- ${python_name} -m pip install paddle-serving-app==0.8.3
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
+ ${python_name} -m pip install paddle-serving-server-gpu
+ ${python_name} -m pip install paddle_serving_client
+ ${python_name} -m pip install paddle-serving-app
+ # wget model
+ if [ ${model_name} == "ch_ppocr_mobile_v2.0_det_KL" ] || [ ${model_name} == "ch_ppocr_mobile_v2.0_rec_KL" ] ; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_det_klquant_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_rec_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_klquant_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_klquant_infer.tar && cd ../
+ elif [ ${model_name} == "ch_PP-OCRv2_det_KL" ] || [ ${model_name} == "ch_PP-OCRv2_rec_KL" ] ; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_det_klquant_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_rec_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_klquant_infer.tar && tar xf ch_PP-OCRv2_rec_klquant_infer.tar && cd ../
+ elif [ ${model_name} == "ch_PP-OCRv3_det_KL" ] || [ ${model_name} == "ch_PP-OCRv3_rec_KL" ] ; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_det_klquant_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_rec_klquant_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_klquant_infer.tar && tar xf ch_PP-OCRv3_rec_klquant_infer.tar && cd ../
+ elif [ ${model_name} == "ch_ppocr_mobile_v2.0_det_PACT" ] || [ ${model_name} == "ch_ppocr_mobile_v2.0_rec_PACT" ] ; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_det_pact_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_ppocr_mobile_v2.0_rec_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_pact_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_pact_infer.tar && cd ../
+ elif [ ${model_name} == "ch_PP-OCRv2_det_PACT" ] || [ ${model_name} == "ch_PP-OCRv2_rec_PACT" ] ; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_det_pact_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv2_rec_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_pact_infer.tar && tar xf ch_PP-OCRv2_rec_pact_infer.tar && cd ../
+ elif [ ${model_name} == "ch_PP-OCRv3_det_PACT" ] || [ ${model_name} == "ch_PP-OCRv3_rec_PACT" ] ; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_det_pact_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/tipc_fake_model/ch_PP-OCRv3_rec_pact_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_pact_infer.tar && tar xf ch_PP-OCRv3_rec_pact_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_ppocr_mobile_v2.0" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_ppocr_server_v2.0" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_PP-OCRv2" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && tar xf ch_PP-OCRv2_rec_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_PP-OCRv3" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && cd ../
+ fi
+ # wget data
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
- cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && tar xf rec_inference.tar && cd ../
- cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf ch_ppocr_server_v2.0_det_infer.tar && cd ../
+ cd ./inference && tar xf ch_det_data_50.tar && tar xf rec_inference.tar && cd ../
fi
if [ ${MODE} = "paddle2onnx_infer" ];then
# prepare serving env
python_name=$(func_parser_value "${lines[2]}")
${python_name} -m pip install paddle2onnx
- ${python_name} -m pip install onnxruntime==1.4.0
+ ${python_name} -m pip install onnxruntime
# wget model
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
- wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
- cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && cd ../
+ if [[ ${model_name} =~ "ch_ppocr_mobile_v2.0" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_ppocr_server_v2.0" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_PP-OCRv2" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv2_det_infer.tar && tar xf ch_PP-OCRv2_rec_infer.tar && cd ../
+ elif [[ ${model_name} =~ "ch_PP-OCRv3" ]]; then
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar --no-check-certificate
+ wget -nc -P ./inference https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar --no-check-certificate
+ cd ./inference && tar xf ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar && cd ../
+ fi
+
# wget data
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar
- cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_det_data_50.tar && tar xf rec_inference.tar && cd ../
+ cd ./inference && tar xf ch_det_data_50.tar && tar xf rec_inference.tar && cd ../
fi
diff --git a/test_tipc/readme.md b/test_tipc/readme.md
index 8110f0073b..effb2f168b 100644
--- a/test_tipc/readme.md
+++ b/test_tipc/readme.md
@@ -138,6 +138,7 @@ bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/ch_ppocr_mobil
## 4. 开始测试
各功能测试中涉及混合精度、裁剪、量化等训练相关，及mkldnn、Tensorrt等多种预测相关参数配置，请点击下方相应链接了解更多细节和使用教程：
- [test_train_inference_python 使用](docs/test_train_inference_python.md) ：测试基于Python的模型训练、评估、推理等基本功能，包括裁剪、量化、蒸馏。
+- [test_train_fleet_inference_python 使用](./docs/test_train_fleet_inference_python.md)：测试基于Python的多机多卡训练与推理等基本功能。
- [test_inference_cpp 使用](docs/test_inference_cpp.md)：测试基于C++的模型推理。
- [test_serving 使用](docs/test_serving.md)：测试基于Paddle Serving的服务化部署功能。
- [test_lite_arm_cpp 使用](docs/test_lite_arm_cpp.md)：测试基于Paddle-Lite的ARM CPU端c++预测部署功能。
diff --git a/test_tipc/test_inference_cpp.sh b/test_tipc/test_inference_cpp.sh
index 2bef621d98..c0c7c18a38 100644
--- a/test_tipc/test_inference_cpp.sh
+++ b/test_tipc/test_inference_cpp.sh
@@ -43,7 +43,7 @@ cpp_cls_value=$(func_parser_value "${lines[18]}")
cpp_use_angle_cls_key=$(func_parser_key "${lines[19]}")
cpp_use_angle_cls_value=$(func_parser_value "${lines[19]}")
-LOG_PATH="./test_tipc/output/cpp_infer/${model_name}"
+LOG_PATH="./test_tipc/output/${model_name}/cpp_infer"
mkdir -p ${LOG_PATH}
status_log="${LOG_PATH}/results_cpp.log"
@@ -84,7 +84,7 @@ function func_cpp_inference(){
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${command}" "${status_log}"
+ status_check $last_status "${command}" "${status_log}" "${model_name}"
done
done
done
@@ -117,7 +117,7 @@ function func_cpp_inference(){
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${command}" "${status_log}"
+ status_check $last_status "${command}" "${status_log}" "${model_name}"
done
done
@@ -178,6 +178,22 @@ if [ ${use_opencv} = "True" ]; then
else
OPENCV_DIR=''
fi
+if [ -d "paddle_inference/" ] ;then
+ echo "################### download paddle inference skipped ###################"
+else
+ echo "################### download paddle inference ###################"
+ PADDLEInfer=$3
+ if [ "" = "$PADDLEInfer" ];then
+ wget -nc https://paddle-inference-lib.bj.bcebos.com/2.3.0/cxx_c/Linux/GPU/x86-64_gcc8.2_avx_mkl_cuda10.1_cudnn7.6.5_trt6.0.1.5/paddle_inference.tgz --no-check-certificate
+ else
+ wget -nc $PADDLEInfer --no-check-certificate
+ fi
+ tar zxf paddle_inference.tgz
+ if [ ! -d "paddle_inference" ]; then
+ ln -s paddle_inference_install_dir paddle_inference
+ fi
+ echo "################### download paddle inference finished ###################"
+fi
LIB_DIR=$(pwd)/paddle_inference/
CUDA_LIB_DIR=$(dirname `find /usr -name libcudart.so`)
CUDNN_LIB_DIR=$(dirname `find /usr -name libcudnn.so`)
@@ -205,11 +221,10 @@ echo "################### build PaddleOCR demo finished ###################"
# set cuda device
GPUID=$2
if [ ${#GPUID} -le 0 ];then
- env=" "
+ env="export CUDA_VISIBLE_DEVICES=0"
else
env="export CUDA_VISIBLE_DEVICES=${GPUID}"
fi
-set CUDA_VISIBLE_DEVICES
eval $env
diff --git a/test_tipc/test_inference_python.sh b/test_tipc/test_inference_python.sh
index a416d623d8..2a31a468f0 100644
--- a/test_tipc/test_inference_python.sh
+++ b/test_tipc/test_inference_python.sh
@@ -88,7 +88,7 @@ function func_inference(){
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${command}" "${status_log}"
+ status_check $last_status "${command}" "${status_log}" "${model_name}"
done
done
done
@@ -119,7 +119,7 @@ function func_inference(){
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${command}" "${status_log}"
+ status_check $last_status "${command}" "${status_log}" "${model_name}"
done
done
@@ -153,7 +153,7 @@ if [ ${MODE} = "whole_infer" ]; then
echo ${infer_run_exports[Count]}
eval $export_cmd
status_export=$?
- status_check $status_export "${export_cmd}" "${status_log}"
+ status_check $status_export "${export_cmd}" "${status_log}" "${model_name}"
else
save_infer_dir=${infer_model}
fi
diff --git a/test_tipc/test_paddle2onnx.sh b/test_tipc/test_paddle2onnx.sh
index 4d1712cfda..4ad2035f48 100644
--- a/test_tipc/test_paddle2onnx.sh
+++ b/test_tipc/test_paddle2onnx.sh
@@ -11,7 +11,7 @@ python=$(func_parser_value "${lines[2]}")
# parser params
-dataline=$(awk 'NR==1, NR==14{print}' $FILENAME)
+dataline=$(awk 'NR==1, NR==17{print}' $FILENAME)
IFS=$'\n'
lines=(${dataline})
@@ -19,27 +19,32 @@ lines=(${dataline})
model_name=$(func_parser_value "${lines[1]}")
python=$(func_parser_value "${lines[2]}")
padlle2onnx_cmd=$(func_parser_value "${lines[3]}")
-infer_model_dir_key=$(func_parser_key "${lines[4]}")
-infer_model_dir_value=$(func_parser_value "${lines[4]}")
+det_infer_model_dir_key=$(func_parser_key "${lines[4]}")
+det_infer_model_dir_value=$(func_parser_value "${lines[4]}")
model_filename_key=$(func_parser_key "${lines[5]}")
model_filename_value=$(func_parser_value "${lines[5]}")
params_filename_key=$(func_parser_key "${lines[6]}")
params_filename_value=$(func_parser_value "${lines[6]}")
-save_file_key=$(func_parser_key "${lines[7]}")
-save_file_value=$(func_parser_value "${lines[7]}")
-opset_version_key=$(func_parser_key "${lines[8]}")
-opset_version_value=$(func_parser_value "${lines[8]}")
-enable_onnx_checker_key=$(func_parser_key "${lines[9]}")
-enable_onnx_checker_value=$(func_parser_value "${lines[9]}")
+det_save_file_key=$(func_parser_key "${lines[7]}")
+det_save_file_value=$(func_parser_value "${lines[7]}")
+rec_infer_model_dir_key=$(func_parser_key "${lines[8]}")
+rec_infer_model_dir_value=$(func_parser_value "${lines[8]}")
+rec_save_file_key=$(func_parser_key "${lines[9]}")
+rec_save_file_value=$(func_parser_value "${lines[9]}")
+opset_version_key=$(func_parser_key "${lines[10]}")
+opset_version_value=$(func_parser_value "${lines[10]}")
+enable_onnx_checker_key=$(func_parser_key "${lines[11]}")
+enable_onnx_checker_value=$(func_parser_value "${lines[11]}")
# parser onnx inference
-inference_py=$(func_parser_value "${lines[10]}")
-use_gpu_key=$(func_parser_key "${lines[11]}")
-use_gpu_list=$(func_parser_value "${lines[11]}")
-det_model_key=$(func_parser_key "${lines[12]}")
-image_dir_key=$(func_parser_key "${lines[13]}")
-image_dir_value=$(func_parser_value "${lines[13]}")
+inference_py=$(func_parser_value "${lines[12]}")
+use_gpu_key=$(func_parser_key "${lines[13]}")
+use_gpu_list=$(func_parser_value "${lines[13]}")
+det_model_key=$(func_parser_key "${lines[14]}")
+rec_model_key=$(func_parser_key "${lines[15]}")
+image_dir_key=$(func_parser_key "${lines[16]}")
+image_dir_value=$(func_parser_value "${lines[16]}")
-LOG_PATH="./test_tipc/output/paddle2onnx/${model_name}"
+LOG_PATH="./test_tipc/output/${model_name}/paddle2onnx"
mkdir -p ${LOG_PATH}
status_log="${LOG_PATH}/results_paddle2onnx.log"
@@ -49,38 +54,95 @@ function func_paddle2onnx(){
_script=$1
# paddle2onnx
- set_dirname=$(func_set_params "${infer_model_dir_key}" "${infer_model_dir_value}")
- set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
- set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
- set_save_model=$(func_set_params "${save_file_key}" "${save_file_value}")
- set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}")
- set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}")
- trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker}"
- eval $trans_model_cmd
- last_status=${PIPESTATUS[0]}
- status_check $last_status "${trans_model_cmd}" "${status_log}"
+ if [ ${model_name} = "ch_PP-OCRv2" ] || [ ${model_name} = "ch_PP-OCRv3" ] || [ ${model_name} = "ch_ppocr_mobile_v2.0" ] || [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ # trans det
+ set_dirname=$(func_set_params "--model_dir" "${det_infer_model_dir_value}")
+ set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+ set_save_model=$(func_set_params "--save_file" "${det_save_file_value}")
+ set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}")
+ set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}")
+ trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker}"
+ eval $trans_model_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}"
+ # trans rec
+ set_dirname=$(func_set_params "--model_dir" "${rec_infer_model_dir_value}")
+ set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+ set_save_model=$(func_set_params "--save_file" "${rec_save_file_value}")
+ set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}")
+ set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}")
+ trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker}"
+ eval $trans_model_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}"
+ elif [[ ${model_name} =~ "det" ]]; then
+ # trans det
+ set_dirname=$(func_set_params "--model_dir" "${det_infer_model_dir_value}")
+ set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+ set_save_model=$(func_set_params "--save_file" "${det_save_file_value}")
+ set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}")
+ set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}")
+ trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker}"
+ eval $trans_model_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}"
+ elif [[ ${model_name} =~ "rec" ]]; then
+ # trans rec
+ set_dirname=$(func_set_params "--model_dir" "${rec_infer_model_dir_value}")
+ set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+ set_save_model=$(func_set_params "--save_file" "${rec_save_file_value}")
+ set_opset_version=$(func_set_params "${opset_version_key}" "${opset_version_value}")
+ set_enable_onnx_checker=$(func_set_params "${enable_onnx_checker_key}" "${enable_onnx_checker_value}")
+ trans_model_cmd="${padlle2onnx_cmd} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_save_model} ${set_opset_version} ${set_enable_onnx_checker}"
+ eval $trans_model_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}"
+ fi
+
# python inference
for use_gpu in ${use_gpu_list[*]}; do
if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
_save_log_path="${LOG_PATH}/paddle2onnx_infer_cpu.log"
set_gpu=$(func_set_params "${use_gpu_key}" "${use_gpu}")
- set_model_dir=$(func_set_params "${det_model_key}" "${save_file_value}")
set_img_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}")
- infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ if [ ${model_name} = "ch_PP-OCRv2" ] || [ ${model_name} = "ch_PP-OCRv3" ] || [ ${model_name} = "ch_ppocr_mobile_v2.0" ] || [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
+ set_rec_model_dir=$(func_set_params "${rec_model_key}" "${rec_save_file_value}")
+ infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} ${set_rec_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ elif [[ ${model_name} =~ "det" ]]; then
+ set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
+ infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ elif [[ ${model_name} =~ "rec" ]]; then
+ set_rec_model_dir=$(func_set_params "${rec_model_key}" "${rec_save_file_value}")
+ infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_rec_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ fi
eval $infer_model_cmd
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${infer_model_cmd}" "${status_log}"
+ status_check $last_status "${infer_model_cmd}" "${status_log}" "${model_name}"
elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then
_save_log_path="${LOG_PATH}/paddle2onnx_infer_gpu.log"
set_gpu=$(func_set_params "${use_gpu_key}" "${use_gpu}")
- set_model_dir=$(func_set_params "${det_model_key}" "${save_file_value}")
set_img_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}")
- infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ if [ ${model_name} = "ch_PP-OCRv2" ] || [ ${model_name} = "ch_PP-OCRv3" ] || [ ${model_name} = "ch_ppocr_mobile_v2.0" ] || [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
+ set_rec_model_dir=$(func_set_params "${rec_model_key}" "${rec_save_file_value}")
+ infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} ${set_rec_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ elif [[ ${model_name} =~ "det" ]]; then
+ set_det_model_dir=$(func_set_params "${det_model_key}" "${det_save_file_value}")
+ infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_det_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ elif [[ ${model_name} =~ "rec" ]]; then
+ set_rec_model_dir=$(func_set_params "${rec_model_key}" "${rec_save_file_value}")
+ infer_model_cmd="${python} ${inference_py} ${set_gpu} ${set_img_dir} ${set_rec_model_dir} --use_onnx=True > ${_save_log_path} 2>&1 "
+ fi
eval $infer_model_cmd
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${infer_model_cmd}" "${status_log}"
+ status_check $last_status "${infer_model_cmd}" "${status_log}" "${model_name}"
else
echo "Does not support hardware other than CPU and GPU Currently!"
fi
diff --git a/test_tipc/test_serving.sh b/test_tipc/test_serving.sh
deleted file mode 100644
index 3a6c88f313..0000000000
--- a/test_tipc/test_serving.sh
+++ /dev/null
@@ -1,191 +0,0 @@
-#!/bin/bash
-source test_tipc/common_func.sh
-
-FILENAME=$1
-dataline=$(awk 'NR==1, NR==18{print}' $FILENAME)
-
-# parser params
-IFS=$'\n'
-lines=(${dataline})
-
-# parser serving
-model_name=$(func_parser_value "${lines[1]}")
-python_list=$(func_parser_value "${lines[2]}")
-trans_model_py=$(func_parser_value "${lines[3]}")
-infer_model_dir_key=$(func_parser_key "${lines[4]}")
-infer_model_dir_value=$(func_parser_value "${lines[4]}")
-model_filename_key=$(func_parser_key "${lines[5]}")
-model_filename_value=$(func_parser_value "${lines[5]}")
-params_filename_key=$(func_parser_key "${lines[6]}")
-params_filename_value=$(func_parser_value "${lines[6]}")
-serving_server_key=$(func_parser_key "${lines[7]}")
-serving_server_value=$(func_parser_value "${lines[7]}")
-serving_client_key=$(func_parser_key "${lines[8]}")
-serving_client_value=$(func_parser_value "${lines[8]}")
-serving_dir_value=$(func_parser_value "${lines[9]}")
-web_service_py=$(func_parser_value "${lines[10]}")
-web_use_gpu_key=$(func_parser_key "${lines[11]}")
-web_use_gpu_list=$(func_parser_value "${lines[11]}")
-web_use_mkldnn_key=$(func_parser_key "${lines[12]}")
-web_use_mkldnn_list=$(func_parser_value "${lines[12]}")
-web_cpu_threads_key=$(func_parser_key "${lines[13]}")
-web_cpu_threads_list=$(func_parser_value "${lines[13]}")
-web_use_trt_key=$(func_parser_key "${lines[14]}")
-web_use_trt_list=$(func_parser_value "${lines[14]}")
-web_precision_key=$(func_parser_key "${lines[15]}")
-web_precision_list=$(func_parser_value "${lines[15]}")
-pipeline_py=$(func_parser_value "${lines[16]}")
-image_dir_key=$(func_parser_key "${lines[17]}")
-image_dir_value=$(func_parser_value "${lines[17]}")
-
-LOG_PATH="$(pwd)/test_tipc/output/pdserving/${model_name}"
-mkdir -p ${LOG_PATH}
-status_log="${LOG_PATH}/results_serving.log"
-
-function func_serving(){
- IFS='|'
- _python=$1
- _script=$2
- _model_dir=$3
- # pdserving
- set_dirname=$(func_set_params "${infer_model_dir_key}" "${infer_model_dir_value}")
- set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
- set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
- set_serving_server=$(func_set_params "${serving_server_key}" "${serving_server_value}")
- set_serving_client=$(func_set_params "${serving_client_key}" "${serving_client_value}")
- set_image_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}")
- python_list=(${python_list})
- trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
- eval $trans_model_cmd
- cd ${serving_dir_value}
- unset https_proxy
- unset http_proxy
- for python in ${python_list[*]}; do
- if [ ${python} = "cpp" ]; then
- for use_gpu in ${web_use_gpu_list[*]}; do
- if [ ${use_gpu} = "null" ]; then
- if [ ${model_name} = "ocr_det_mobile" ]; then
- web_service_cpp_cmd="${python_list[0]} -m paddle_serving_server.serve --model ppocr_det_mobile_2.0_serving/ ppocr_rec_mobile_2.0_serving/ --op GeneralDetectionOp GeneralInferOp --port 9293"
- elif [ ${model_name} = "ocr_det_v3" ] || [ ${model_name} = "ocr_rec_v3" ]; then
- web_service_cpp_cmd="${python_list[0]} -m paddle_serving_server.serve --model ppocr_det_v3_serving/ ppocr_rec_v3_serving/ --op GeneralDetectionOp GeneralInferOp --port 9293"
- fi
- eval $web_service_cpp_cmd
- last_status=${PIPESTATUS[0]}
- status_check $last_status "${web_service_cpp_cmd}" "${status_log}"
- sleep 2s
- _save_log_path="${LOG_PATH}/server_infer_cpp_cpu_pipeline_usemkldnn_False_threads_4_batchsize_1.log"
- if [ ${model_name} = "ocr_det_mobile" ]; then
- pipeline_cmd="${python_list[0]} ocr_cpp_client.py ppocr_det_mobile_2.0_client/ ppocr_rec_mobile_2.0_client/"
- elif [ ${model_name} = "ocr_det_v3" ] || [ ${model_name} = "ocr_rec_v3" ]; then
- pipeline_cmd="${python_list[0]} ocr_cpp_client.py ppocr_det_v3_client/ ppocr_rec_v3_client/"
- fi
- eval $pipeline_cmd
- last_status=${PIPESTATUS[0]}
- status_check $last_status "${pipeline_cmd}" "${status_log}"
- sleep 2s
- ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9
- else
- if [ ${model_name} = "ocr_det_mobile" ]; then
- web_service_cpp_cmd="${python_list[0]} -m paddle_serving_server.serve --model ppocr_det_mobile_2.0_serving/ ppocr_rec_mobile_2.0_serving/ --op GeneralDetectionOp GeneralInferOp --port 9293 --gpu_id=0"
- elif [ ${model_name} = "ocr_det_v3" ] || [ ${model_name} = "ocr_rec_v3" ]; then
- web_service_cpp_cmd="${python_list[0]} -m paddle_serving_server.serve --model ppocr_det_v3_serving/ ppocr_rec_v3_serving/ --op GeneralDetectionOp GeneralInferOp --port 9293 --gpu_id=0"
- fi
- eval $web_service_cpp_cmd
- sleep 2s
- _save_log_path="${LOG_PATH}/server_infer_cpp_cpu_pipeline_usemkldnn_False_threads_4_batchsize_1.log"
- if [ ${model_name} = "ocr_det_mobile" ]; then
- pipeline_cmd="${python_list[0]} ocr_cpp_client.py ppocr_det_mobile_2.0_client/ ppocr_rec_mobile_2.0_client/"
- elif [ ${model_name} = "ocr_det_v3" ] || [ ${model_name} = "ocr_rec_v3" ]; then
- pipeline_cmd="${python_list[0]} ocr_cpp_client.py ppocr_det_v3_client/ ppocr_rec_v3_client/"
- fi
- eval $pipeline_cmd
- last_status=${PIPESTATUS[0]}
- status_check $last_status "${pipeline_cmd}" "${status_log}"
- sleep 2s
- ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9
- fi
- done
- else
- # python serving
- for use_gpu in ${web_use_gpu_list[*]}; do
- if [ ${use_gpu} = "null" ]; then
- for use_mkldnn in ${web_use_mkldnn_list[*]}; do
- for threads in ${web_cpu_threads_list[*]}; do
- set_cpu_threads=$(func_set_params "${web_cpu_threads_key}" "${threads}")
- web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}="" ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} &"
- eval $web_service_cmd
- last_status=${PIPESTATUS[0]}
- status_check $last_status "${web_service_cmd}" "${status_log}"
- sleep 2s
- for pipeline in ${pipeline_py[*]}; do
- _save_log_path="${LOG_PATH}/server_infer_cpu_${pipeline%_client*}_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_1.log"
- pipeline_cmd="${python} ${pipeline} ${set_image_dir} > ${_save_log_path} 2>&1 "
- eval $pipeline_cmd
- last_status=${PIPESTATUS[0]}
- eval "cat ${_save_log_path}"
- status_check $last_status "${pipeline_cmd}" "${status_log}"
- sleep 2s
- done
- ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9
- done
- done
- elif [ ${use_gpu} = "gpu" ]; then
- for use_trt in ${web_use_trt_list[*]}; do
- for precision in ${web_precision_list[*]}; do
- if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then
- continue
- fi
- if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
- continue
- fi
- if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [[ ${_flag_quant} = "True" ]]; then
- continue
- fi
- set_tensorrt=$(func_set_params "${web_use_trt_key}" "${use_trt}")
- if [ ${use_trt} = True ]; then
- device_type=2
- fi
- set_precision=$(func_set_params "${web_precision_key}" "${precision}")
- web_service_cmd="${python} ${web_service_py} ${set_tensorrt} ${set_precision} & "
- eval $web_service_cmd
- last_status=${PIPESTATUS[0]}
- status_check $last_status "${web_service_cmd}" "${status_log}"
-
- sleep 2s
- for pipeline in ${pipeline_py[*]}; do
- _save_log_path="${LOG_PATH}/server_infer_gpu_${pipeline%_client*}_usetrt_${use_trt}_precision_${precision}_batchsize_1.log"
- pipeline_cmd="${python} ${pipeline} ${set_image_dir}> ${_save_log_path} 2>&1"
- eval $pipeline_cmd
- last_status=${PIPESTATUS[0]}
- eval "cat ${_save_log_path}"
- status_check $last_status "${pipeline_cmd}" "${status_log}"
- sleep 2s
- done
- ps ux | grep -E 'web_service|pipeline' | awk '{print $2}' | xargs kill -s 9
- done
- done
- else
- echo "Does not support hardware other than CPU and GPU Currently!"
- fi
- done
- fi
- done
-}
-
-
-#set cuda device
-GPUID=$2
-if [ ${#GPUID} -le 0 ];then
- env="export CUDA_VISIBLE_DEVICES=0"
-else
- env="export CUDA_VISIBLE_DEVICES=${GPUID}"
-fi
-eval $env
-echo $env
-
-
-echo "################### run test ###################"
-
-export Count=0
-IFS="|"
-func_serving "${web_service_cmd}"
diff --git a/test_tipc/test_serving_infer_cpp.sh b/test_tipc/test_serving_infer_cpp.sh
new file mode 100644
index 0000000000..f9f7ac1aa5
--- /dev/null
+++ b/test_tipc/test_serving_infer_cpp.sh
@@ -0,0 +1,133 @@
+#!/bin/bash
+source test_tipc/common_func.sh
+
+function func_parser_model_config(){
+ strs=$1
+ IFS="/"
+ array=(${strs})
+ tmp=${array[-1]}
+ echo ${tmp}
+}
+
+FILENAME=$1
+dataline=$(awk 'NR==1, NR==19{print}' $FILENAME)
+MODE=$2
+
+# parser params
+IFS=$'\n'
+lines=(${dataline})
+
+# parser serving
+model_name=$(func_parser_value "${lines[1]}")
+python_list=$(func_parser_value "${lines[2]}")
+trans_model_py=$(func_parser_value "${lines[3]}")
+det_infer_model_dir_key=$(func_parser_key "${lines[4]}")
+det_infer_model_dir_value=$(func_parser_value "${lines[4]}")
+model_filename_key=$(func_parser_key "${lines[5]}")
+model_filename_value=$(func_parser_value "${lines[5]}")
+params_filename_key=$(func_parser_key "${lines[6]}")
+params_filename_value=$(func_parser_value "${lines[6]}")
+det_serving_server_key=$(func_parser_key "${lines[7]}")
+det_serving_server_value=$(func_parser_value "${lines[7]}")
+det_serving_client_key=$(func_parser_key "${lines[8]}")
+det_serving_client_value=$(func_parser_value "${lines[8]}")
+rec_infer_model_dir_key=$(func_parser_key "${lines[9]}")
+rec_infer_model_dir_value=$(func_parser_value "${lines[9]}")
+rec_serving_server_key=$(func_parser_key "${lines[10]}")
+rec_serving_server_value=$(func_parser_value "${lines[10]}")
+rec_serving_client_key=$(func_parser_key "${lines[11]}")
+rec_serving_client_value=$(func_parser_value "${lines[11]}")
+det_server_value=$(func_parser_model_config "${lines[7]}")
+det_client_value=$(func_parser_model_config "${lines[8]}")
+rec_server_value=$(func_parser_model_config "${lines[10]}")
+rec_client_value=$(func_parser_model_config "${lines[11]}")
+serving_dir_value=$(func_parser_value "${lines[12]}")
+web_service_py=$(func_parser_value "${lines[13]}")
+op_key=$(func_parser_key "${lines[14]}")
+op_value=$(func_parser_value "${lines[14]}")
+port_key=$(func_parser_key "${lines[15]}")
+port_value=$(func_parser_value "${lines[15]}")
+gpu_key=$(func_parser_key "${lines[16]}")
+gpu_value=$(func_parser_value "${lines[16]}")
+cpp_client_py=$(func_parser_value "${lines[17]}")
+image_dir_key=$(func_parser_key "${lines[18]}")
+image_dir_value=$(func_parser_value "${lines[18]}")
+
+LOG_PATH="$(pwd)/test_tipc/output/${model_name}/${MODE}/cpp"
+mkdir -p ${LOG_PATH}
+status_log="${LOG_PATH}/results_cpp_serving.log"
+
+function func_serving(){
+ IFS='|'
+ _python=$1
+ _script=$2
+ _model_dir=$3
+ # pdserving
+ set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+ # trans det
+ set_dirname=$(func_set_params "--dirname" "${det_infer_model_dir_value}")
+ set_serving_server=$(func_set_params "--serving_server" "${det_serving_server_value}")
+ set_serving_client=$(func_set_params "--serving_client" "${det_serving_client_value}")
+ python_list=(${python_list})
+ trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
+ eval $trans_model_cmd
+ cp "deploy/pdserving/serving_client_conf.prototxt" ${det_serving_client_value}
+ # trans rec
+ set_dirname=$(func_set_params "--dirname" "${rec_infer_model_dir_value}")
+ set_serving_server=$(func_set_params "--serving_server" "${rec_serving_server_value}")
+ set_serving_client=$(func_set_params "--serving_client" "${rec_serving_client_value}")
+ python_list=(${python_list})
+ trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
+ eval $trans_model_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${trans_model_cmd}" "${status_log}" "${model_name}"
+ set_image_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}")
+ python_list=(${python_list})
+ cd ${serving_dir_value}
+ # cpp serving
+ for gpu_id in ${gpu_value[*]}; do
+ if [ ${gpu_id} = "null" ]; then
+ web_service_cpp_cmd="${python_list[0]} ${web_service_py} --model ${det_server_value} ${rec_server_value} ${op_key} ${op_value} ${port_key} ${port_value} > serving_log_cpu.log &"
+ eval $web_service_cpp_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cpp_cmd}" "${status_log}" "${model_name}"
+ sleep 5s
+ _save_log_path="${LOG_PATH}/server_infer_cpp_cpu.log"
+ cpp_client_cmd="${python_list[0]} ${cpp_client_py} ${det_client_value} ${rec_client_value} > ${_save_log_path} 2>&1"
+ eval $cpp_client_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${cpp_client_cmd}" "${status_log}" "${model_name}"
+ ps ux | grep -i ${port_value} | awk '{print $2}' | xargs kill -s 9
+ else
+ web_service_cpp_cmd="${python_list[0]} ${web_service_py} --model ${det_server_value} ${rec_server_value} ${op_key} ${op_value} ${port_key} ${port_value} ${gpu_key} ${gpu_id} > serving_log_gpu.log &"
+ eval $web_service_cpp_cmd
+ sleep 5s
+ _save_log_path="${LOG_PATH}/server_infer_cpp_gpu.log"
+ cpp_client_cmd="${python_list[0]} ${cpp_client_py} ${det_client_value} ${rec_client_value} > ${_save_log_path} 2>&1"
+ eval $cpp_client_cmd
+ last_status=${PIPESTATUS[0]}
+ eval "cat ${_save_log_path}"
+ status_check $last_status "${cpp_client_cmd}" "${status_log}" "${model_name}"
+ ps ux | grep -i ${port_value} | awk '{print $2}' | xargs kill -s 9
+ fi
+ done
+}
+
+
+#set cuda device
+GPUID=$3
+if [ ${#GPUID} -le 0 ];then
+ env="export CUDA_VISIBLE_DEVICES=0"
+else
+ env="export CUDA_VISIBLE_DEVICES=${GPUID}"
+fi
+eval $env
+echo $env
+
+
+echo "################### run test ###################"
+
+export Count=0
+IFS="|"
+func_serving "${web_service_cpp_cmd}"
diff --git a/test_tipc/test_serving_infer_python.sh b/test_tipc/test_serving_infer_python.sh
new file mode 100644
index 0000000000..c76d6f5d19
--- /dev/null
+++ b/test_tipc/test_serving_infer_python.sh
@@ -0,0 +1,223 @@
+#!/bin/bash
+source test_tipc/common_func.sh
+
+function func_parser_model_config(){
+ strs=$1
+ IFS="/"
+ array=(${strs})
+ tmp=${array[-1]}
+ echo ${tmp}
+}
+
+FILENAME=$1
+dataline=$(awk 'NR==1, NR==23{print}' $FILENAME)
+MODE=$2
+
+# parser params
+IFS=$'\n'
+lines=(${dataline})
+
+# parser serving
+model_name=$(func_parser_value "${lines[1]}")
+python_list=$(func_parser_value "${lines[2]}")
+trans_model_py=$(func_parser_value "${lines[3]}")
+det_infer_model_dir_key=$(func_parser_key "${lines[4]}")
+det_infer_model_dir_value=$(func_parser_value "${lines[4]}")
+model_filename_key=$(func_parser_key "${lines[5]}")
+model_filename_value=$(func_parser_value "${lines[5]}")
+params_filename_key=$(func_parser_key "${lines[6]}")
+params_filename_value=$(func_parser_value "${lines[6]}")
+det_serving_server_key=$(func_parser_key "${lines[7]}")
+det_serving_server_value=$(func_parser_value "${lines[7]}")
+det_serving_client_key=$(func_parser_key "${lines[8]}")
+det_serving_client_value=$(func_parser_value "${lines[8]}")
+rec_infer_model_dir_key=$(func_parser_key "${lines[9]}")
+rec_infer_model_dir_value=$(func_parser_value "${lines[9]}")
+rec_serving_server_key=$(func_parser_key "${lines[10]}")
+rec_serving_server_value=$(func_parser_value "${lines[10]}")
+rec_serving_client_key=$(func_parser_key "${lines[11]}")
+rec_serving_client_value=$(func_parser_value "${lines[11]}")
+serving_dir_value=$(func_parser_value "${lines[12]}")
+web_service_py=$(func_parser_value "${lines[13]}")
+web_use_gpu_key=$(func_parser_key "${lines[14]}")
+web_use_gpu_list=$(func_parser_value "${lines[14]}")
+web_use_mkldnn_key=$(func_parser_key "${lines[15]}")
+web_use_mkldnn_list=$(func_parser_value "${lines[15]}")
+web_cpu_threads_key=$(func_parser_key "${lines[16]}")
+web_cpu_threads_list=$(func_parser_value "${lines[16]}")
+web_use_trt_key=$(func_parser_key "${lines[17]}")
+web_use_trt_list=$(func_parser_value "${lines[17]}")
+web_precision_key=$(func_parser_key "${lines[18]}")
+web_precision_list=$(func_parser_value "${lines[18]}")
+det_server_key=$(func_parser_key "${lines[19]}")
+det_server_value=$(func_parser_model_config "${lines[7]}")
+det_client_value=$(func_parser_model_config "${lines[8]}")
+rec_server_key=$(func_parser_key "${lines[20]}")
+rec_server_value=$(func_parser_model_config "${lines[10]}")
+rec_client_value=$(func_parser_model_config "${lines[11]}")
+pipeline_py=$(func_parser_value "${lines[21]}")
+image_dir_key=$(func_parser_key "${lines[22]}")
+image_dir_value=$(func_parser_value "${lines[22]}")
+
+LOG_PATH="$(pwd)/test_tipc/output/${model_name}/${MODE}/python"
+mkdir -p ${LOG_PATH}
+status_log="${LOG_PATH}/results_python_serving.log"
+
+function func_serving(){
+ IFS='|'
+ _python=$1
+ _script=$2
+ _model_dir=$3
+ # pdserving
+ set_model_filename=$(func_set_params "${model_filename_key}" "${model_filename_value}")
+ set_params_filename=$(func_set_params "${params_filename_key}" "${params_filename_value}")
+ if [ ${model_name} = "ch_PP-OCRv2" ] || [ ${model_name} = "ch_PP-OCRv3" ] || [ ${model_name} = "ch_ppocr_mobile_v2.0" ] || [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ # trans det
+ set_dirname=$(func_set_params "--dirname" "${det_infer_model_dir_value}")
+ set_serving_server=$(func_set_params "--serving_server" "${det_serving_server_value}")
+ set_serving_client=$(func_set_params "--serving_client" "${det_serving_client_value}")
+ python_list=(${python_list})
+ trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
+ eval $trans_model_cmd
+ # trans rec
+ set_dirname=$(func_set_params "--dirname" "${rec_infer_model_dir_value}")
+ set_serving_server=$(func_set_params "--serving_server" "${rec_serving_server_value}")
+ set_serving_client=$(func_set_params "--serving_client" "${rec_serving_client_value}")
+ python_list=(${python_list})
+ trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
+ eval $trans_model_cmd
+ elif [[ ${model_name} =~ "det" ]]; then
+ # trans det
+ set_dirname=$(func_set_params "--dirname" "${det_infer_model_dir_value}")
+ set_serving_server=$(func_set_params "--serving_server" "${det_serving_server_value}")
+ set_serving_client=$(func_set_params "--serving_client" "${det_serving_client_value}")
+ python_list=(${python_list})
+ trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
+ eval $trans_model_cmd
+ elif [[ ${model_name} =~ "rec" ]]; then
+ # trans rec
+ set_dirname=$(func_set_params "--dirname" "${rec_infer_model_dir_value}")
+ set_serving_server=$(func_set_params "--serving_server" "${rec_serving_server_value}")
+ set_serving_client=$(func_set_params "--serving_client" "${rec_serving_client_value}")
+ python_list=(${python_list})
+ trans_model_cmd="${python_list[0]} ${trans_model_py} ${set_dirname} ${set_model_filename} ${set_params_filename} ${set_serving_server} ${set_serving_client}"
+ eval $trans_model_cmd
+ fi
+ set_image_dir=$(func_set_params "${image_dir_key}" "${image_dir_value}")
+ python_list=(${python_list})
+
+ cd ${serving_dir_value}
+ python=${python_list[0]}
+
+ # python serving
+ for use_gpu in ${web_use_gpu_list[*]}; do
+ if [ ${use_gpu} = "null" ]; then
+ for use_mkldnn in ${web_use_mkldnn_list[*]}; do
+ for threads in ${web_cpu_threads_list[*]}; do
+ set_cpu_threads=$(func_set_params "${web_cpu_threads_key}" "${threads}")
+ if [ ${model_name} = "ch_PP-OCRv2" ] || [ ${model_name} = "ch_PP-OCRv3" ] || [ ${model_name} = "ch_ppocr_mobile_v2.0" ] || [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ set_det_model_config=$(func_set_params "${det_server_key}" "${det_server_value}")
+ set_rec_model_config=$(func_set_params "${rec_server_key}" "${rec_server_value}")
+ web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}="" ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_det_model_config} ${set_rec_model_config} &"
+ eval $web_service_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cmd}" "${status_log}" "${model_name}"
+ elif [[ ${model_name} =~ "det" ]]; then
+ set_det_model_config=$(func_set_params "${det_server_key}" "${det_server_value}")
+ web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}="" ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_det_model_config} &"
+ eval $web_service_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cmd}" "${status_log}" "${model_name}"
+ elif [[ ${model_name} =~ "rec" ]]; then
+ set_rec_model_config=$(func_set_params "${rec_server_key}" "${rec_server_value}")
+ web_service_cmd="${python} ${web_service_py} ${web_use_gpu_key}="" ${web_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_rec_model_config} &"
+ eval $web_service_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cmd}" "${status_log}" "${model_name}"
+ fi
+ sleep 2s
+ for pipeline in ${pipeline_py[*]}; do
+ _save_log_path="${LOG_PATH}/server_infer_cpu_${pipeline%_client*}_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_1.log"
+ pipeline_cmd="${python} ${pipeline} ${set_image_dir} > ${_save_log_path} 2>&1 "
+ eval $pipeline_cmd
+ last_status=${PIPESTATUS[0]}
+ eval "cat ${_save_log_path}"
+ status_check $last_status "${pipeline_cmd}" "${status_log}" "${model_name}"
+ sleep 2s
+ done
+ ps ux | grep -E 'web_service' | awk '{print $2}' | xargs kill -s 9
+ done
+ done
+ elif [ ${use_gpu} = "gpu" ]; then
+ for use_trt in ${web_use_trt_list[*]}; do
+ for precision in ${web_precision_list[*]}; do
+ if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then
+ continue
+ fi
+ if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
+ continue
+ fi
+ if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [[ ${_flag_quant} = "True" ]]; then
+ continue
+ fi
+ set_tensorrt=$(func_set_params "${web_use_trt_key}" "${use_trt}")
+ if [ ${use_trt} = True ]; then
+ device_type=2
+ fi
+ set_precision=$(func_set_params "${web_precision_key}" "${precision}")
+ if [ ${model_name} = "ch_PP-OCRv2" ] || [ ${model_name} = "ch_PP-OCRv3" ] || [ ${model_name} = "ch_ppocr_mobile_v2.0" ] || [ ${model_name} = "ch_ppocr_server_v2.0" ]; then
+ set_det_model_config=$(func_set_params "${det_server_key}" "${det_server_value}")
+ set_rec_model_config=$(func_set_params "${rec_server_key}" "${rec_server_value}")
+ web_service_cmd="${python} ${web_service_py} ${set_tensorrt} ${set_precision} ${set_det_model_config} ${set_rec_model_config} &"
+ eval $web_service_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cmd}" "${status_log}" "${model_name}"
+ elif [[ ${model_name} =~ "det" ]]; then
+ set_det_model_config=$(func_set_params "${det_server_key}" "${det_server_value}")
+ web_service_cmd="${python} ${web_service_py} ${set_tensorrt} ${set_precision} ${set_det_model_config} &"
+ eval $web_service_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cmd}" "${status_log}" "${model_name}"
+ elif [[ ${model_name} =~ "rec" ]]; then
+ set_rec_model_config=$(func_set_params "${rec_server_key}" "${rec_server_value}")
+ web_service_cmd="${python} ${web_service_py} ${set_tensorrt} ${set_precision} ${set_rec_model_config} &"
+ eval $web_service_cmd
+ last_status=${PIPESTATUS[0]}
+ status_check $last_status "${web_service_cmd}" "${status_log}" "${model_name}"
+ fi
+ sleep 2s
+ for pipeline in ${pipeline_py[*]}; do
+ _save_log_path="${LOG_PATH}/server_infer_gpu_${pipeline%_client*}_usetrt_${use_trt}_precision_${precision}_batchsize_1.log"
+ pipeline_cmd="${python} ${pipeline} ${set_image_dir}> ${_save_log_path} 2>&1"
+ eval $pipeline_cmd
+ last_status=${PIPESTATUS[0]}
+ eval "cat ${_save_log_path}"
+ status_check $last_status "${pipeline_cmd}" "${status_log}" "${model_name}"
+ sleep 2s
+ done
+ ps ux | grep -E 'web_service' | awk '{print $2}' | xargs kill -s 9
+ done
+ done
+ else
+ echo "Does not support hardware other than CPU and GPU Currently!"
+ fi
+ done
+}
+
+
+#set cuda device
+GPUID=$3
+if [ ${#GPUID} -le 0 ];then
+ env="export CUDA_VISIBLE_DEVICES=0"
+else
+ env="export CUDA_VISIBLE_DEVICES=${GPUID}"
+fi
+eval $env
+echo $env
+
+
+echo "################### run test ###################"
+
+export Count=0
+IFS="|"
+func_serving "${web_service_cmd}"
diff --git a/test_tipc/test_train_inference_python.sh b/test_tipc/test_train_inference_python.sh
index 81d1bf8eef..62a56a32ce 100644
--- a/test_tipc/test_train_inference_python.sh
+++ b/test_tipc/test_train_inference_python.sh
@@ -142,9 +142,9 @@ function func_inference(){
for use_gpu in ${use_gpu_list[*]}; do
if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
for use_mkldnn in ${use_mkldnn_list[*]}; do
- if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
- continue
- fi
+ # if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
+ # continue
+ # fi
for threads in ${cpu_threads_list[*]}; do
for batch_size in ${batch_size_list[*]}; do
for precision in ${precision_list[*]}; do
@@ -169,7 +169,7 @@ function func_inference(){
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${command}" "${status_log}"
+ status_check $last_status "${command}" "${status_log}" "${model_name}"
done
done
done
@@ -200,7 +200,7 @@ function func_inference(){
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
- status_check $last_status "${command}" "${status_log}"
+ status_check $last_status "${command}" "${status_log}" "${model_name}"
done
done
@@ -240,7 +240,7 @@ if [ ${MODE} = "whole_infer" ] || [ ${MODE} = "klquant_whole_infer" ]; then
echo $export_cmd
eval $export_cmd
status_export=$?
- status_check $status_export "${export_cmd}" "${status_log}"
+ status_check $status_export "${export_cmd}" "${status_log}" "${model_name}"
else
save_infer_dir=${infer_model}
fi
@@ -315,7 +315,9 @@ else
set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}")
set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}")
set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${train_use_gpu}")
- if [ ${#ips} -le 26 ];then
+ # if length of ips >= 15, then it is seen as multi-machine
+ # 15 is the min length of ips info for multi-machine: 0.0.0.0,0.0.0.0
+ if [ ${#ips} -le 15 ];then
save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
nodes=1
else
@@ -330,14 +332,14 @@ else
set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
if [ ${#gpu} -le 2 ];then # train with cpu or single gpu
cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config} "
- elif [ ${#ips} -le 26 ];then # train with multi-gpu
+ elif [ ${#ips} -le 15 ];then # train with multi-gpu
cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}"
else # train with multi-machine
cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_use_gpu} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1} ${set_amp_config}"
fi
# run train
eval $cmd
- status_check $? "${cmd}" "${status_log}"
+ status_check $? "${cmd}" "${status_log}" "${model_name}"
set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}")
@@ -347,7 +349,7 @@ else
set_eval_params1=$(func_set_params "${eval_key1}" "${eval_value1}")
eval_cmd="${python} ${eval_py} ${set_eval_pretrain} ${set_use_gpu} ${set_eval_params1}"
eval $eval_cmd
- status_check $? "${eval_cmd}" "${status_log}"
+ status_check $? "${eval_cmd}" "${status_log}" "${model_name}"
fi
# run export model
if [ ${run_export} != "null" ]; then
@@ -357,7 +359,7 @@ else
set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_path}")
export_cmd="${python} ${run_export} ${set_export_weight} ${set_save_infer_key}"
eval $export_cmd
- status_check $? "${export_cmd}" "${status_log}"
+ status_check $? "${export_cmd}" "${status_log}" "${model_name}"
#run inference
eval $env
diff --git a/tools/end2end/convert_ppocr_label.py b/tools/end2end/convert_ppocr_label.py
index 8084cac785..c64b9ed168 100644
--- a/tools/end2end/convert_ppocr_label.py
+++ b/tools/end2end/convert_ppocr_label.py
@@ -85,10 +85,16 @@ def convert_label(label_dir, mode="gt", save_dir="./save_results/"):
print("The convert label saved in {}".format(save_dir))
+def parse_args():
+ import argparse
+ parser = argparse.ArgumentParser(description="args")
+ parser.add_argument("--label_path", type=str, required=True)
+ parser.add_argument("--save_folder", type=str, required=True)
+ parser.add_argument("--mode", type=str, default=False)
+ args = parser.parse_args()
+ return args
+
+
if __name__ == "__main__":
-
- ppocr_label_gt = "/paddle/Datasets/chinese/test_set/Label_refine_310_V2.txt"
- convert_label(ppocr_label_gt, "gt", "./save_gt_310_V2/")
-
- ppocr_label_gt = "./infer_results/ch_PPOCRV2_infer.txt"
- convert_label(ppocr_label_gt_en, "pred", "./save_PPOCRV2_infer/")
+ args = parse_args()
+ convert_label(args.label_path, args.mode, args.save_folder)
diff --git a/tools/end2end/readme.md b/tools/end2end/readme.md
index 69da06dcda..636ee764ae 100644
--- a/tools/end2end/readme.md
+++ b/tools/end2end/readme.md
@@ -23,19 +23,13 @@ all-sum-510/00224225.jpg [{"transcription": "超赞", "points": [[8.0, 48
**步骤二：**
将步骤一保存的数据转换为端对端评测需要的数据格式：
-修改 `tools/convert_ppocr_label.py`中的代码，convert_label函数中设置输入标签路径，Mode，保存标签路径等，对预测数据的GTlabel和预测结果的label格式进行转换。
+
+修改 `tools/end2end/convert_ppocr_label.py`中的代码，convert_label函数中设置输入标签路径，Mode，保存标签路径等，对预测数据的GTlabel和预测结果的label格式进行转换。
```
-ppocr_label_gt = "gt_label.txt"
-convert_label(ppocr_label_gt, "gt", "./save_gt_label/")
+python3 tools/end2end/convert_ppocr_label.py --mode=gt --label_path=path/to/label_txt --save_folder=save_gt_label
-ppocr_label_gt = "./ch_PP-OCRv2_results/system_results.txt"
-convert_label(ppocr_label_gt_en, "pred", "./save_PPOCRV2_infer/")
-```
-
-运行`convert_ppocr_label.py`:
-```
-python3 tools/convert_ppocr_label.py
+python3 tools/end2end/convert_ppocr_label.py --mode=pred --label_path=path/to/pred_txt --save_folder=save_PPOCRV2_infer
```
得到如下结果：
diff --git a/tools/export_model.py b/tools/export_model.py
index c0cbcd361c..3ea0228f85 100755
--- a/tools/export_model.py
+++ b/tools/export_model.py
@@ -76,7 +76,7 @@ def export_single_model(model, arch_config, save_path, logger, quanter=None):
else:
infer_shape = [3, -1, -1]
if arch_config["model_type"] == "rec":
- infer_shape = [3, 32, -1] # for rec model, H must be 32
+ infer_shape = [3, 48, -1] # for rec model, H must be 32
if "Transform" in arch_config and arch_config[
"Transform"] is not None and arch_config["Transform"][
"name"] == "TPS":
diff --git a/tools/infer/utility.py b/tools/infer/utility.py
index 48b16db4a0..366212f228 100644
--- a/tools/infer/utility.py
+++ b/tools/infer/utility.py
@@ -34,6 +34,7 @@ def init_args():
parser = argparse.ArgumentParser()
# params for prediction engine
parser.add_argument("--use_gpu", type=str2bool, default=True)
+ parser.add_argument("--use_xpu", type=str2bool, default=False)
parser.add_argument("--ir_optim", type=str2bool, default=True)
parser.add_argument("--use_tensorrt", type=str2bool, default=False)
parser.add_argument("--min_subgraph_size", type=int, default=15)
@@ -201,7 +202,8 @@ def create_predictor(args, mode, logger):
workspace_size=1 << 30,
precision_mode=precision,
max_batch_size=args.max_batch_size,
- min_subgraph_size=args.min_subgraph_size)
+ min_subgraph_size=args.min_subgraph_size,
+ use_calib_mode=False)
# skip the minmum trt subgraph
use_dynamic_shape = True
if mode == "det":
@@ -286,6 +288,8 @@ def create_predictor(args, mode, logger):
config.set_trt_dynamic_shape_info(
min_input_shape, max_input_shape, opt_input_shape)
+ elif args.use_xpu:
+ config.enable_xpu(10 * 1024 * 1024)
else:
config.disable_gpu()
if hasattr(args, "cpu_threads"):
diff --git a/tools/program.py b/tools/program.py
index 7c02dc0149..aa0d2698cf 100755
--- a/tools/program.py
+++ b/tools/program.py
@@ -112,20 +112,25 @@ def merge_config(config, opts):
return config
-def check_gpu(use_gpu):
+def check_device(use_gpu, use_xpu=False):
"""
Log error and exit when set use_gpu=true in paddlepaddle
cpu version.
"""
- err = "Config use_gpu cannot be set as true while you are " \
- "using paddlepaddle cpu version ! \nPlease try: \n" \
- "\t1. Install paddlepaddle-gpu to run model on GPU \n" \
- "\t2. Set use_gpu as false in config file to run " \
+ err = "Config {} cannot be set as true while your paddle " \
+ "is not compiled with {} ! \nPlease try: \n" \
+ "\t1. Install paddlepaddle to run model on {} \n" \
+ "\t2. Set {} as false in config file to run " \
"model on CPU"
try:
+ if use_gpu and use_xpu:
+ print("use_xpu and use_gpu can not both be ture.")
if use_gpu and not paddle.is_compiled_with_cuda():
- print(err)
+ print(err.format("use_gpu", "cuda", "gpu", "use_gpu"))
+ sys.exit(1)
+ if use_xpu and not paddle.device.is_compiled_with_xpu():
+ print(err.format("use_xpu", "xpu", "xpu", "use_xpu"))
sys.exit(1)
except Exception as e:
pass
@@ -547,7 +552,7 @@ def preprocess(is_train=False):
# check if set use_gpu=True in paddlepaddle cpu version
use_gpu = config['Global']['use_gpu']
- check_gpu(use_gpu)
+ use_xpu = config['Global'].get('use_xpu', False)
# check if set use_xpu=True in paddlepaddle cpu/gpu version
use_xpu = False
@@ -562,11 +567,13 @@ def preprocess(is_train=False):
'SEED', 'SDMGR', 'LayoutXLM', 'LayoutLM', 'PREN', 'FCE', 'SVTR'
]
- device = 'cpu'
- if use_gpu:
- device = 'gpu:{}'.format(dist.ParallelEnv().dev_id)
if use_xpu:
- device = 'xpu'
+ device = 'xpu:{0}'.format(os.getenv('FLAGS_selected_xpus', 0))
+ else:
+ device = 'gpu:{}'.format(dist.ParallelEnv()
+ .dev_id) if use_gpu else 'cpu'
+ check_device(use_gpu, use_xpu)
+
device = paddle.set_device(device)
config['Global']['distributed'] = dist.get_world_size() != 1
- 
+ 
+ 
- 
+ 
+ 
- 
+ 
+ 