From 242f0adbcd8abb9f96544d8a2c370831212a56d8 Mon Sep 17 00:00:00 2001 From: WenmuZhou <572459439@qq.com> Date: Mon, 22 Aug 2022 06:58:09 +0000 Subject: [PATCH 1/5] update inference_en.md --- ppstructure/docs/inference.md | 37 +++++++++++++++++++------------- ppstructure/docs/inference_en.md | 37 +++++++++++++++++++------------- ppstructure/utility.py | 2 +- 3 files changed, 45 insertions(+), 31 deletions(-) diff --git a/ppstructure/docs/inference.md b/ppstructure/docs/inference.md index 3f92a6046e..150471795a 100644 --- a/ppstructure/docs/inference.md +++ b/ppstructure/docs/inference.md @@ -16,23 +16,26 @@ cd ppstructure 下载模型 ```bash mkdir inference && cd inference -# 下载PP-OCRv2文本检测模型并解压 -wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar -# 下载PP-OCRv2文本识别模型并解压 -wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar -# 下载超轻量级英文表格预测模型并解压 -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar +# 下载PP-Structurev2版面分析模型并解压 +wget https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar && tar xf picodet_lcnet_x1_0_layout_infer.tar +# 下载PP-OCRv3文本检测模型并解压 +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +# 下载PP-OCRv3文本识别模型并解压 +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +# 下载PP-Structurev2表格识别模型并解压 +wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. ``` ### 1.1 版面分析+表格识别 ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \ - --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \ - --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ + --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \ --image_dir=./docs/table/1.png \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ - --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ --output=../output \ --vis_font_path=../doc/fonts/simfang.ttf ``` @@ -41,19 +44,23 @@ python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_i ### 1.2 版面分析 ```bash -python3 predict_system.py --image_dir=./docs/table/1.png --table=false --ocr=false --output=../output/ +python3 predict_system.py --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \ + --image_dir=./docs/table/1.png \ + --output=../output \ + --table=false \ + --ocr=false ``` 运行完成后，每张图片会在`output`字段指定的目录下的`structure`目录下有一个同名目录，图片区域会被裁剪之后保存下来，图片名为表格在图片里的坐标。版面分析结果会存储在`res.txt`文件中。 ### 1.3 表格识别 ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \ - --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \ - --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --image_dir=./docs/table/table.jpg \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ - --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ --output=../output \ --vis_font_path=../doc/fonts/simfang.ttf \ --layout=false diff --git a/ppstructure/docs/inference_en.md b/ppstructure/docs/inference_en.md index 126878378d..1e35e62f8e 100644 --- a/ppstructure/docs/inference_en.md +++ b/ppstructure/docs/inference_en.md @@ -18,23 +18,26 @@ download model ```bash mkdir inference && cd inference -# Download the PP-OCRv2 text detection model and unzip it -wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar -# Download the PP-OCRv2 text recognition model and unzip it -wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar -# Download the ultra-lightweight English table structure model and unzip it -wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar +# Download the PP-Structurev2 layout analysis model and unzip it +wget https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar && tar xf picodet_lcnet_x1_0_layout_infer.tar +# Download the PP-OCRv3 text detection model and unzip it +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +# Download the PP-OCRv3 text recognition model and unzip it +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +# Download the PP-Structurev2 form recognition model and unzip it +wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. ``` ### 1.1 layout analysis + table recognition ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \ - --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \ - --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ + --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \ --image_dir=./docs/table/1.png \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ - --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ --output=../output \ --vis_font_path=../doc/fonts/simfang.ttf ``` @@ -43,19 +46,23 @@ After the operation is completed, each image will have a directory with the same ### 1.2 layout analysis ```bash -python3 predict_system.py --image_dir=./docs/table/1.png --table=false --ocr=false --output=../output/ +python3 predict_system.py --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \ + --image_dir=./docs/table/1.png \ + --output=../output \ + --table=false \ + --ocr=false ``` After the operation is completed, each image will have a directory with the same name in the `structure` directory under the directory specified by the `output` field. Each picture in image will be cropped and saved. The filename of picture area is their coordinates in the image. Layout analysis results will be stored in the `res.txt` file ### 1.3 table recognition ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \ - --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \ - --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --image_dir=./docs/table/table.jpg \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ - --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \ + --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ --output=../output \ --vis_font_path=../doc/fonts/simfang.ttf \ --layout=false diff --git a/ppstructure/utility.py b/ppstructure/utility.py index 270ee3aef9..3bc275eba3 100644 --- a/ppstructure/utility.py +++ b/ppstructure/utility.py @@ -38,7 +38,7 @@ def init_args(): parser.add_argument( "--layout_dict_path", type=str, - default="../ppocr/utils/dict/layout_dict/layout_pubalynet_dict.txt") + default="../ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt") parser.add_argument( "--layout_score_threshold", type=float, From cb6c4f81662e975647329a70c94fb60b4a5d8add Mon Sep 17 00:00:00 2001 From: WenmuZhou <572459439@qq.com> Date: Mon, 22 Aug 2022 07:11:30 +0000 Subject: [PATCH 2/5] update en rec model desc --- ppstructure/docs/models_list.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ppstructure/docs/models_list.md b/ppstructure/docs/models_list.md index 0b2f41deb5..90c0bbe95d 100644 --- a/ppstructure/docs/models_list.md +++ b/ppstructure/docs/models_list.md @@ -24,8 +24,8 @@ |模型名称|模型简介|推理模型大小|下载地址| | --- | --- | --- | --- | -|en_ppocr_mobile_v2.0_table_det|PubLayNet数据集训练的英文表格场景的文字检测|4.7M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_det_train.tar) | -|en_ppocr_mobile_v2.0_table_rec|PubLayNet数据集训练的英文表格场景的文字识别|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_rec_train.tar) | +|en_ppocr_mobile_v2.0_table_det|PubTabNet数据集训练的英文表格场景的文字检测|4.7M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_det_train.tar) | +|en_ppocr_mobile_v2.0_table_rec|PubTabNet数据集训练的英文表格场景的文字识别|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_rec_train.tar) | 如需要使用其他OCR模型，可以在 [PP-OCR model_list](../../doc/doc_ch/models_list.md) 下载模型或者使用自己训练好的模型配置到 `det_model_dir`, `rec_model_dir`两个字段即可。 From 396eae907c22e4b357713098e1ae7393b0004cf3 Mon Sep 17 00:00:00 2001 From: WenmuZhou <572459439@qq.com> Date: Mon, 22 Aug 2022 07:24:37 +0000 Subject: [PATCH 3/5] update SLANet ch model desc --- ppstructure/README.md | 2 +- ppstructure/README_ch.md | 2 +- ppstructure/docs/models_list.md | 2 +- ppstructure/docs/models_list_en.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/ppstructure/README.md b/ppstructure/README.md index cff057e819..079db53fd1 100644 --- a/ppstructure/README.md +++ b/ppstructure/README.md @@ -108,7 +108,7 @@ PP-Structure Series Model List (Updating) | --- | --- | --- | --- | |ch_PP-OCRv3_det_slim|[New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection| 1.1M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_distill_train.tar)| |ch_PP-OCRv3_rec_slim |[New] Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition| 4.9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) | -|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model trained on PubTabNet dataset based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | +|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | ### 7.3 KIE model diff --git a/ppstructure/README_ch.md b/ppstructure/README_ch.md index efd25eb2cb..f30a7345fe 100644 --- a/ppstructure/README_ch.md +++ b/ppstructure/README_ch.md @@ -122,7 +122,7 @@ PP-Structure系列模型列表（更新中） | --- | --- | --- | --- | |ch_PP-OCRv3_det_slim|【最新】slim量化+蒸馏版超轻量模型，支持中英文、多语种文本检测| 1.1M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_distill_train.tar)| |ch_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型，支持中英文、数字识别| 4.9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) | -|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | +|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | diff --git a/ppstructure/docs/models_list.md b/ppstructure/docs/models_list.md index 90c0bbe95d..ef7048faa6 100644 --- a/ppstructure/docs/models_list.md +++ b/ppstructure/docs/models_list.md @@ -36,7 +36,7 @@ | --- | --- | --- | --- | |en_ppocr_mobile_v2.0_table_structure|基于TableRec-RARE在PubTabNet数据集上训练的英文表格识别模型|6.8M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) | |en_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的英文表格识别模型|9.2M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar) | -|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | +|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | diff --git a/ppstructure/docs/models_list_en.md b/ppstructure/docs/models_list_en.md index cb6857f62f..27b444d5a7 100644 --- a/ppstructure/docs/models_list_en.md +++ b/ppstructure/docs/models_list_en.md @@ -36,7 +36,7 @@ If you need to use other OCR models, you can download the model in [PP-OCR model | --- |-----------------------------------------------------------------------------| --- | --- | |en_ppocr_mobile_v2.0_table_structure| English table recognition model trained on PubTabNet dataset based on TableRec-RARE |6.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) | |en_ppstructure_mobile_v2.0_SLANet|English table recognition model trained on PubTabNet dataset based on SLANet|9.2M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar) | -|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model trained on PubTabNet dataset based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | +|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | ## 3. KIE From f7b35bbbc418d4e4dcfedd3313eb514e11a60859 Mon Sep 17 00:00:00 2001 From: WenmuZhou <572459439@qq.com> Date: Mon, 22 Aug 2022 08:00:49 +0000 Subject: [PATCH 4/5] do not print table result --- paddleocr.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/paddleocr.py b/paddleocr.py index d78046802e..f6fb095af3 100644 --- a/paddleocr.py +++ b/paddleocr.py @@ -636,4 +636,6 @@ def main(): for item in result: item.pop('img') + item.pop('res') logger.info(item) + logger.info('result save to {}'.format(args.output)) From 6eca179e966b20eeb6633b539f93b639ad50d86e Mon Sep 17 00:00:00 2001 From: WenmuZhou <572459439@qq.com> Date: Mon, 22 Aug 2022 08:20:20 +0000 Subject: [PATCH 5/5] update rec det model to fp32 --- ppstructure/README.md | 4 ++-- ppstructure/README_ch.md | 4 ++-- ppstructure/docs/inference.md | 12 ++++++------ ppstructure/docs/inference_en.md | 12 ++++++------ ppstructure/table/README.md | 8 ++++---- ppstructure/table/README_ch.md | 8 ++++---- 6 files changed, 24 insertions(+), 24 deletions(-) diff --git a/ppstructure/README.md b/ppstructure/README.md index 079db53fd1..66df10b2ec 100644 --- a/ppstructure/README.md +++ b/ppstructure/README.md @@ -106,8 +106,8 @@ PP-Structure Series Model List (Updating) |model name|description|model size|download| | --- | --- | --- | --- | -|ch_PP-OCRv3_det_slim|[New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection| 1.1M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_distill_train.tar)| -|ch_PP-OCRv3_rec_slim |[New] Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition| 4.9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) | +|ch_PP-OCRv3_det| [New] Lightweight model, supporting Chinese, English, multilingual text detection | 3.8M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar)| +|ch_PP-OCRv3_rec| [New] Lightweight model, supporting Chinese, English, multilingual text recognition | 12.4M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) | |ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | ### 7.3 KIE model diff --git a/ppstructure/README_ch.md b/ppstructure/README_ch.md index f30a7345fe..597cceafdf 100644 --- a/ppstructure/README_ch.md +++ b/ppstructure/README_ch.md @@ -120,8 +120,8 @@ PP-Structure系列模型列表（更新中） |模型名称|模型简介|模型大小|下载地址| | --- | --- | --- | --- | -|ch_PP-OCRv3_det_slim|【最新】slim量化+蒸馏版超轻量模型，支持中英文、多语种文本检测| 1.1M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_distill_train.tar)| -|ch_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型，支持中英文、数字识别| 4.9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) | +|ch_PP-OCRv3_det| 【最新】超轻量模型，支持中英文、多语种文本检测 | 3.8M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar)| +|ch_PP-OCRv3_rec|【最新】超轻量模型，支持中英文、数字识别|12.4M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) | |ch_ppstructure_mobile_v2.0_SLANet|基于SLANet的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) | diff --git a/ppstructure/docs/inference.md b/ppstructure/docs/inference.md index 150471795a..cf11960c1c 100644 --- a/ppstructure/docs/inference.md +++ b/ppstructure/docs/inference.md @@ -19,9 +19,9 @@ mkdir inference && cd inference # 下载PP-Structurev2版面分析模型并解压 wget https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar && tar xf picodet_lcnet_x1_0_layout_infer.tar # 下载PP-OCRv3文本检测模型并解压 -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar # 下载PP-OCRv3文本识别模型并解压 -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar # 下载PP-Structurev2表格识别模型并解压 wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. @@ -29,8 +29,8 @@ cd .. ### 1.1 版面分析+表格识别 ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ - --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \ --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \ --image_dir=./docs/table/1.png \ @@ -55,8 +55,8 @@ python3 predict_system.py --layout_model_dir=inference/picodet_lcnet_x1_0_layout ### 1.3 表格识别 ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ - --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \ --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --image_dir=./docs/table/table.jpg \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ diff --git a/ppstructure/docs/inference_en.md b/ppstructure/docs/inference_en.md index 1e35e62f8e..357e26a11f 100644 --- a/ppstructure/docs/inference_en.md +++ b/ppstructure/docs/inference_en.md @@ -21,9 +21,9 @@ mkdir inference && cd inference # Download the PP-Structurev2 layout analysis model and unzip it wget https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar && tar xf picodet_lcnet_x1_0_layout_infer.tar # Download the PP-OCRv3 text detection model and unzip it -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar # Download the PP-OCRv3 text recognition model and unzip it -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar # Download the PP-Structurev2 form recognition model and unzip it wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. @@ -31,8 +31,8 @@ cd .. ### 1.1 layout analysis + table recognition ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ - --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \ --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \ --image_dir=./docs/table/1.png \ @@ -57,8 +57,8 @@ After the operation is completed, each image will have a directory with the same ### 1.3 table recognition ```bash -python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ - --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ +python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \ --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --image_dir=./docs/table/table.jpg \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ diff --git a/ppstructure/table/README.md b/ppstructure/table/README.md index a5d0da3ccd..e5c85eb961 100644 --- a/ppstructure/table/README.md +++ b/ppstructure/table/README.md @@ -59,16 +59,16 @@ cd PaddleOCR/ppstructure # download model mkdir inference && cd inference # Download the PP-OCRv3 text detection model and unzip it -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar # Download the PP-OCRv3 text recognition model and unzip it -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar # Download the PP-Structurev2 form recognition model and unzip it wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. # run python3.7 table/predict_table.py \ - --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ - --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --det_model_dir=inference/ch_PP-OCRv3_det_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \ --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \ diff --git a/ppstructure/table/README_ch.md b/ppstructure/table/README_ch.md index e83c81befb..086e39348e 100644 --- a/ppstructure/table/README_ch.md +++ b/ppstructure/table/README_ch.md @@ -64,16 +64,16 @@ cd PaddleOCR/ppstructure # 下载模型 mkdir inference && cd inference # 下载PP-OCRv3文本检测模型并解压 -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar # 下载PP-OCRv3文本识别模型并解压 -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar # 下载PP-Structurev2表格识别模型并解压 wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar cd .. # 执行表格识别 python table/predict_table.py \ - --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \ - --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer \ + --det_model_dir=inference/ch_PP-OCRv3_det_infer \ + --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \ --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \ --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \ --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \