mirror of
https://github.com/PaddlePaddle/PaddleOCR.git
synced 2026-09-24 23:33:08 +08:00
Merge pull request #4761 from WenmuZhou/tipc
add PSE and rec PACT to tipc
This commit is contained in:
MissPenguin
@@ -247,3 +247,7 @@ Q1: 训练模型转inference 模型之后预测效果不一致？
|
||||
**A**：此类问题出现较多，问题多是trained model预测时候的预处理、后处理参数和inference model预测的时候的预处理、后处理参数不一致导致的。以det_mv3_db.yml配置文件训练的模型为例，训练模型、inference模型预测结果不一致问题解决方式如下：
|
||||
- 检查[trained model预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L116)，和[inference model的预测预处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/predict_det.py#L42)函数是否一致。算法在评估的时候，输入图像大小会影响精度，为了和论文保持一致，训练icdar15配置文件中将图像resize到[736, 1280]，但是在inference model预测的时候只有一套默认参数，会考虑到预测速度问题，默认限制图像最长边为960做resize的。训练模型预处理和inference模型的预处理函数位于[ppocr/data/imaug/operators.py](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/ppocr/data/imaug/operators.py#L147)
|
||||
- 检查[trained model后处理](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/configs/det/det_mv3_db.yml#L51)，和[inference 后处理参数](https://github.com/PaddlePaddle/PaddleOCR/blob/c1ed243fb68d5d466258243092e56cbae32e2c14/tools/infer/utility.py#L50)是否一致。
|
||||
|
||||
Q1: 训练EAST模型提示找不到lanms库？
|
||||
|
||||
**A**：执行pip3 install lanms-nova 即可。
|
||||
|
||||
@@ -20,7 +20,6 @@ import numpy as np
|
||||
from .locality_aware_nms import nms_locality
|
||||
import cv2
|
||||
import paddle
|
||||
import lanms
|
||||
|
||||
import os
|
||||
import sys
|
||||
@@ -61,6 +60,7 @@ class EASTPostProcess(object):
|
||||
"""
|
||||
restore text boxes from score map and geo map
|
||||
"""
|
||||
|
||||
score_map = score_map[0]
|
||||
geo_map = np.swapaxes(geo_map, 1, 0)
|
||||
geo_map = np.swapaxes(geo_map, 1, 2)
|
||||
@@ -76,8 +76,15 @@ class EASTPostProcess(object):
|
||||
boxes = np.zeros((text_box_restored.shape[0], 9), dtype=np.float32)
|
||||
boxes[:, :8] = text_box_restored.reshape((-1, 8))
|
||||
boxes[:, 8] = score_map[xy_text[:, 0], xy_text[:, 1]]
|
||||
boxes = lanms.merge_quadrangle_n9(boxes, nms_thresh)
|
||||
# boxes = nms_locality(boxes.astype(np.float64), nms_thresh)
|
||||
|
||||
try:
|
||||
import lanms
|
||||
boxes = lanms.merge_quadrangle_n9(boxes, nms_thresh)
|
||||
except:
|
||||
print(
|
||||
'you should install lanms by pip3 install lanms-nova to speed up nms_locality'
|
||||
)
|
||||
boxes = nms_locality(boxes.astype(np.float64), nms_thresh)
|
||||
if boxes.shape[0] == 0:
|
||||
return []
|
||||
# Here we filter some low score boxes by the average score map,
|
||||
|
||||
@@ -67,6 +67,7 @@ def load_model(config, model, optimizer=None):
|
||||
if key not in params:
|
||||
logger.warning("{} not in loaded params {} !".format(
|
||||
key, params.keys()))
|
||||
continue
|
||||
pre_value = params[key]
|
||||
if list(value.shape) == list(pre_value.shape):
|
||||
new_state_dict[key] = pre_value
|
||||
@@ -76,9 +77,14 @@ def load_model(config, model, optimizer=None):
|
||||
format(key, value.shape, pre_value.shape))
|
||||
model.set_state_dict(new_state_dict)
|
||||
|
||||
optim_dict = paddle.load(checkpoints + '.pdopt')
|
||||
if optimizer is not None:
|
||||
optimizer.set_state_dict(optim_dict)
|
||||
if os.path.exists(checkpoints + '.pdopt'):
|
||||
optim_dict = paddle.load(checkpoints + '.pdopt')
|
||||
optimizer.set_state_dict(optim_dict)
|
||||
else:
|
||||
logger.warning(
|
||||
"{}.pdopt is not exists, params of optimizer is not loaded".
|
||||
format(checkpoints))
|
||||
|
||||
if os.path.exists(checkpoints + '.states'):
|
||||
with open(checkpoints + '.states', 'rb') as f:
|
||||
|
||||
+1
-2
@@ -12,5 +12,4 @@ cython
|
||||
lxml
|
||||
premailer
|
||||
openpyxl
|
||||
fasttext==0.9.1
|
||||
lanms-nova
|
||||
fasttext==0.9.1
|
||||
+21
@@ -0,0 +1,21 @@
|
||||
===========================kl_quant_params===========================
|
||||
model_name:ch_ppocr_mobile_v2.0_rec_KL
|
||||
python:python3.7
|
||||
Global.pretrained_model:null
|
||||
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
|
||||
--use_gpu:False|True
|
||||
--enable_mkldnn:True
|
||||
--cpu_threads:1|6
|
||||
--rec_batch_num:1
|
||||
--use_tensorrt:False|True
|
||||
--precision:int8
|
||||
--det_model_dir:
|
||||
--image_dir:./inference/rec_inference
|
||||
null:null
|
||||
--benchmark:True
|
||||
null:null
|
||||
null:null
|
||||
@@ -0,0 +1,101 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 500
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/rec_chinese_lite_v2.0
|
||||
save_epoch_step: 3
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: [0, 2000]
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
|
||||
max_text_length: 25
|
||||
infer_mode: False
|
||||
use_space_char: True
|
||||
save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.001
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00001
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: CRNN
|
||||
Transform:
|
||||
Backbone:
|
||||
name: MobileNetV3
|
||||
scale: 0.5
|
||||
model_name: small
|
||||
small_stride: [1, 2, 2, 2]
|
||||
Neck:
|
||||
name: SequenceEncoder
|
||||
encoder_type: rnn
|
||||
hidden_size: 48
|
||||
Head:
|
||||
name: CTCHead
|
||||
fc_decay: 0.00001
|
||||
|
||||
Loss:
|
||||
name: CTCLoss
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: train_data/ic15_data
|
||||
label_file_list: ["train_data/ic15_data/rec_gt_train.txt"]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- RecAug:
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 320]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: True
|
||||
batch_size_per_card: 256
|
||||
drop_last: True
|
||||
num_workers: 8
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: train_data/ic15_data
|
||||
label_file_list: ["train_data/ic15_data/rec_gt_test.txt"]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 320]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size_per_card: 256
|
||||
num_workers: 8
|
||||
@@ -0,0 +1,101 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 500
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/rec_chinese_lite_v2.0
|
||||
save_epoch_step: 3
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: [0, 2000]
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
|
||||
max_text_length: 25
|
||||
infer_mode: False
|
||||
use_space_char: True
|
||||
save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Cosine
|
||||
learning_rate: 0.001
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00001
|
||||
|
||||
Architecture:
|
||||
model_type: rec
|
||||
algorithm: CRNN
|
||||
Transform:
|
||||
Backbone:
|
||||
name: MobileNetV3
|
||||
scale: 0.5
|
||||
model_name: small
|
||||
small_stride: [1, 2, 2, 2]
|
||||
Neck:
|
||||
name: SequenceEncoder
|
||||
encoder_type: rnn
|
||||
hidden_size: 48
|
||||
Head:
|
||||
name: CTCHead
|
||||
fc_decay: 0.00001
|
||||
|
||||
Loss:
|
||||
name: CTCLoss
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: train_data/ic15_data
|
||||
label_file_list: ["train_data/ic15_data/rec_gt_train.txt"]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- RecAug:
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 320]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: True
|
||||
batch_size_per_card: 256
|
||||
drop_last: True
|
||||
num_workers: 8
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: train_data/ic15_data
|
||||
label_file_list: ["train_data/ic15_data/rec_gt_test.txt"]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [3, 32, 320]
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size_per_card: 256
|
||||
num_workers: 8
|
||||
@@ -0,0 +1,51 @@
|
||||
===========================train_params===========================
|
||||
model_name:ch_ppocr_mobile_v2.0_rec_PACT
|
||||
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.save_model_dir:./output/
|
||||
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
|
||||
Global.checkpoints:null
|
||||
train_model_name:latest
|
||||
train_infer_img_dir:./train_data/ic15_data/test/word_1.png
|
||||
null:null
|
||||
##
|
||||
trainer:pact_train
|
||||
norm_train:null
|
||||
pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/rec_chinese_lite_train_v2.0.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 -ctest_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/rec_chinese_lite_train_v2.0.yml -o
|
||||
fpgm_export:null
|
||||
distill_export:null
|
||||
export1:null
|
||||
export2:null
|
||||
inference_dir:null
|
||||
train_model:null
|
||||
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
|
||||
--rec_batch_num:1|6
|
||||
--use_tensorrt:False|True
|
||||
--precision:fp32|fp16|int8
|
||||
--rec_model_dir:
|
||||
--image_dir:./inference/rec_inference
|
||||
--save_log_path:./test/output/
|
||||
--benchmark:True
|
||||
null:null
|
||||
@@ -0,0 +1,135 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 600
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/det_mv3_pse/
|
||||
save_epoch_step: 600
|
||||
# evaluation is run every 63 iterations
|
||||
eval_batch_step: [ 0,1000 ]
|
||||
cal_metric_during_train: False
|
||||
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
|
||||
checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_en/img_10.jpg
|
||||
save_res_path: ./output/det_pse/predicts_pse.txt
|
||||
|
||||
Architecture:
|
||||
model_type: det
|
||||
algorithm: PSE
|
||||
Transform: null
|
||||
Backbone:
|
||||
name: MobileNetV3
|
||||
scale: 0.5
|
||||
model_name: large
|
||||
Neck:
|
||||
name: FPN
|
||||
out_channels: 96
|
||||
Head:
|
||||
name: PSEHead
|
||||
hidden_dim: 96
|
||||
out_channels: 7
|
||||
|
||||
Loss:
|
||||
name: PSELoss
|
||||
alpha: 0.7
|
||||
ohem_ratio: 3
|
||||
kernel_sample_mask: pred
|
||||
reduction: none
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Step
|
||||
learning_rate: 0.001
|
||||
step_size: 200
|
||||
gamma: 0.1
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.0005
|
||||
|
||||
PostProcess:
|
||||
name: PSEPostProcess
|
||||
thresh: 0
|
||||
box_thresh: 0.85
|
||||
min_area: 16
|
||||
box_type: box # 'box' or 'poly'
|
||||
scale: 1
|
||||
|
||||
Metric:
|
||||
name: DetMetric
|
||||
main_indicator: hmean
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./train_data/icdar2015/text_localization/
|
||||
label_file_list:
|
||||
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
|
||||
ratio_list: [ 1.0 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- DetLabelEncode: # Class handling label
|
||||
- ColorJitter:
|
||||
brightness: 0.12549019607843137
|
||||
saturation: 0.5
|
||||
- IaaAugment:
|
||||
augmenter_args:
|
||||
- { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
|
||||
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
|
||||
- { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
|
||||
- MakePseGt:
|
||||
kernel_num: 7
|
||||
min_shrink_ratio: 0.4
|
||||
size: 640
|
||||
- RandomCropImgMask:
|
||||
size: [ 640,640 ]
|
||||
main_key: gt_text
|
||||
crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [ 0.485, 0.456, 0.406 ]
|
||||
std: [ 0.229, 0.224, 0.225 ]
|
||||
order: 'hwc'
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
|
||||
loader:
|
||||
shuffle: True
|
||||
drop_last: False
|
||||
batch_size_per_card: 16
|
||||
num_workers: 8
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./train_data/icdar2015/text_localization/
|
||||
label_file_list:
|
||||
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
|
||||
ratio_list: [ 1.0 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- DetLabelEncode: # Class handling label
|
||||
- DetResizeForTest:
|
||||
limit_side_len: 736
|
||||
limit_type: min
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [ 0.485, 0.456, 0.406 ]
|
||||
std: [ 0.229, 0.224, 0.225 ]
|
||||
order: 'hwc'
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size_per_card: 1 # must be 1
|
||||
num_workers: 8
|
||||
@@ -0,0 +1,51 @@
|
||||
===========================train_params===========================
|
||||
model_name:det_mv3_pse_v2.0
|
||||
python:python3.7
|
||||
gpu_list:0
|
||||
Global.use_gpu:True|True
|
||||
Global.auto_cast:fp32
|
||||
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
|
||||
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_mv3_pse_v2.0/det_mv3_pse.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.pretrained_model:
|
||||
norm_export:tools/export_model.py -c test_tipc/configs/det_mv3_pse_v2.0/det_mv3_pse.yml -o
|
||||
quant_export:null
|
||||
fpgm_export:null
|
||||
distill_export:null
|
||||
export1:null
|
||||
export2:null
|
||||
##
|
||||
train_model:./inference/det_mv3_pse/best_accuracy
|
||||
infer_export:tools/export_model.py -c test_tipc/cconfigs/det_mv3_pse_v2.0/det_mv3_pse.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/
|
||||
--save_log_path:null
|
||||
--benchmark:True
|
||||
--det_algorithm:PSE
|
||||
@@ -34,7 +34,7 @@ distill_export:null
|
||||
export1:null
|
||||
export2:null
|
||||
##
|
||||
train_model:./inference/det_mv3_east/best_accuracy
|
||||
train_model:./inference/det_r50_vd_east/best_accuracy
|
||||
infer_export:tools/export_model.py -c test_tipc/cconfigs/det_r50_vd_east_v2.0/det_r50_vd_east.yml -o
|
||||
infer_quant:False
|
||||
inference:tools/infer/predict_det.py
|
||||
|
||||
@@ -0,0 +1,134 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 600
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/det_r50_vd_pse/
|
||||
save_epoch_step: 600
|
||||
# evaluation is run every 125 iterations
|
||||
eval_batch_step: [ 0,1000 ]
|
||||
cal_metric_during_train: False
|
||||
pretrained_model:
|
||||
checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_en/img_10.jpg
|
||||
save_res_path: ./output/det_pse/predicts_pse.txt
|
||||
|
||||
Architecture:
|
||||
model_type: det
|
||||
algorithm: PSE
|
||||
Transform:
|
||||
Backbone:
|
||||
name: ResNet
|
||||
layers: 50
|
||||
Neck:
|
||||
name: FPN
|
||||
out_channels: 256
|
||||
Head:
|
||||
name: PSEHead
|
||||
hidden_dim: 256
|
||||
out_channels: 7
|
||||
|
||||
Loss:
|
||||
name: PSELoss
|
||||
alpha: 0.7
|
||||
ohem_ratio: 3
|
||||
kernel_sample_mask: pred
|
||||
reduction: none
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Step
|
||||
learning_rate: 0.0001
|
||||
step_size: 200
|
||||
gamma: 0.1
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.0005
|
||||
|
||||
PostProcess:
|
||||
name: PSEPostProcess
|
||||
thresh: 0
|
||||
box_thresh: 0.85
|
||||
min_area: 16
|
||||
box_type: box # 'box' or 'poly'
|
||||
scale: 1
|
||||
|
||||
Metric:
|
||||
name: DetMetric
|
||||
main_indicator: hmean
|
||||
|
||||
Train:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./train_data/icdar2015/text_localization/
|
||||
label_file_list:
|
||||
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
|
||||
ratio_list: [ 1.0 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- DetLabelEncode: # Class handling label
|
||||
- ColorJitter:
|
||||
brightness: 0.12549019607843137
|
||||
saturation: 0.5
|
||||
- IaaAugment:
|
||||
augmenter_args:
|
||||
- { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
|
||||
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
|
||||
- { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
|
||||
- MakePseGt:
|
||||
kernel_num: 7
|
||||
min_shrink_ratio: 0.4
|
||||
size: 640
|
||||
- RandomCropImgMask:
|
||||
size: [ 640,640 ]
|
||||
main_key: gt_text
|
||||
crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [ 0.485, 0.456, 0.406 ]
|
||||
std: [ 0.229, 0.224, 0.225 ]
|
||||
order: 'hwc'
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
|
||||
loader:
|
||||
shuffle: True
|
||||
drop_last: False
|
||||
batch_size_per_card: 8
|
||||
num_workers: 8
|
||||
|
||||
Eval:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./train_data/icdar2015/text_localization/
|
||||
label_file_list:
|
||||
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
|
||||
ratio_list: [ 1.0 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- DetLabelEncode: # Class handling label
|
||||
- DetResizeForTest:
|
||||
limit_side_len: 736
|
||||
limit_type: min
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [ 0.485, 0.456, 0.406 ]
|
||||
std: [ 0.229, 0.224, 0.225 ]
|
||||
order: 'hwc'
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size_per_card: 1 # must be 1
|
||||
num_workers: 8
|
||||
@@ -0,0 +1,51 @@
|
||||
===========================train_params===========================
|
||||
model_name:det_r50_vd_pse_v2.0
|
||||
python:python3.7
|
||||
gpu_list:0
|
||||
Global.use_gpu:True|True
|
||||
Global.auto_cast:fp32
|
||||
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
|
||||
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_pse_v2.0/det_r50_vd_pse.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.pretrained_model:
|
||||
norm_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_pse_v2.0/det_r50_vd_pse.yml -o
|
||||
quant_export:null
|
||||
fpgm_export:null
|
||||
distill_export:null
|
||||
export1:null
|
||||
export2:null
|
||||
##
|
||||
train_model:./inference/det_r50_vd_pse/best_accuracy
|
||||
infer_export:tools/export_model.py -c test_tipc/cconfigs/det_r50_vd_pse_v2.0/det_r50_vd_pse.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/
|
||||
--save_log_path:null
|
||||
--benchmark:True
|
||||
--det_algorithm:PSE
|
||||
@@ -174,6 +174,13 @@ if [ ${MODE} = "klquant_whole_infer" ]; then
|
||||
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_ppocr_mobile_v2.0_rec_KL" ]; then
|
||||
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_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 ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf rec_inference.tar && cd ../
|
||||
fi
|
||||
fi
|
||||
|
||||
if [ ${MODE} = "cpp_infer" ];then
|
||||
|
||||
Reference in New Issue
Block a user