m53297601
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'dygraph' into dygraph_doc

Browse Source
release/2.0-rc1-0
xiaoting 4 years ago committed by GitHub
parent 8520dd1e8c 90b968d596
commit 631fd9fdec
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
98 changed files with 6850 additions and 1183 deletions
Show Stats Download Patch File Download Diff File

7
MANIFEST.in
Unescape View File

@ -1,8 +1,7 @@
include LICENSE.txt
include README.md
recursive-include ppocr/utils *.txt utility.py character.py check.py
recursive-include ppocr/data/det *.py
recursive-include ppocr/utils *.txt utility.py logging.py
recursive-include ppocr/data/ *.py
recursive-include ppocr/postprocess *.py
recursive-include ppocr/postprocess/lanms *.*
recursive-include tools/infer *.py
recursive-include tools/infer *.py

1
configs/cls/cls_mv3.yml
Unescape View File

@ -8,7 +8,6 @@ Global:
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [0, 1000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: True
pretrained_model:
checkpoints:

134
configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml
Unescape View File

@ -0,0 +1,134 @@
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints: #./output/det_db_0.001_DiceLoss_256_pp_config_2.0b_4gpu/best_accuracy
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
model_type: det
algorithm: DB
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Loss:
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DBPostProcess
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
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
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- 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: 2

133
configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml
Unescape View File

@ -0,0 +1,133 @@
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_res18/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet18_vd_pretrained
checkpoints: #./output/det_db_0.001_DiceLoss_256_pp_config_2.0b_4gpu/best_accuracy
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 18
disable_se: True
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DBPostProcess
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
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
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- 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: 2

2
configs/det/det_mv3_db.yml
Unescape View File

@ -45,9 +45,7 @@ Optimizer:
beta1: 0.9
beta2: 0.999
lr:
# name: Cosine
learning_rate: 0.001
# warmup_epoch: 0
regularizer:
name: 'L2'
factor: 0

111
configs/det/det_mv3_east.yml
Unescape View File

@ -0,0 +1,111 @@
Global:
use_gpu: true
epoch_num: 10000
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/east_mv3/
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
save_res_path: ./output/det_east/predicts_east.txt
Architecture:
model_type: det
algorithm: EAST
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
Neck:
name: EASTFPN
model_name: small
Head:
name: EASTHead
model_name: small
Loss:
name: EASTLoss
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
# name: Cosine
learning_rate: 0.001
# warmup_epoch: 0
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: EASTPostProcess
score_thresh: 0.8
cover_thresh: 0.1
nms_thresh: 0.2
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
- EASTProcessTrain:
image_shape: [512, 512]
background_ratio: 0.125
min_crop_side_ratio: 0.1
min_text_size: 10
- KeepKeys:
keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order
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
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
limit_side_len: 2400
limit_type: max
- 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: 2

130
configs/det/det_r50_vd_db.yml
Unescape View File

@ -0,0 +1,130 @@
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/det_rc/det_r50_vd/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [5000,4000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 50
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.001
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DBPostProcess
thresh: 0.3
box_thresh: 0.7
max_candidates: 1000
unclip_ratio: 1.5
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: [0.5]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [640, 640]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_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
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
image_shape: [736, 1280]
- 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

110
configs/det/det_r50_vd_east.yml
Unescape View File

@ -0,0 +1,110 @@
Global:
use_gpu: true
epoch_num: 10000
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/east_r50_vd/
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_pretrained/
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
save_res_path: ./output/det_east/predicts_east.txt
Architecture:
model_type: det
algorithm: EAST
Transform:
Backbone:
name: ResNet
layers: 50
Neck:
name: EASTFPN
model_name: large
Head:
name: EASTHead
model_name: large
Loss:
name: EASTLoss
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
# name: Cosine
learning_rate: 0.001
# warmup_epoch: 0
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: EASTPostProcess
score_thresh: 0.8
cover_thresh: 0.1
nms_thresh: 0.2
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
- EASTProcessTrain:
image_shape: [512, 512]
background_ratio: 0.125
min_crop_side_ratio: 0.1
min_text_size: 10
- KeepKeys:
keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order
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
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
limit_side_len: 2400
limit_type: max
- 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: 2

110
configs/det/det_r50_vd_sast_icdar15.yml
Unescape View File

@ -0,0 +1,110 @@
Global:
use_gpu: true
epoch_num: 5000
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/sast_r50_vd_ic15/
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
save_res_path: ./output/sast_r50_vd_ic15/predicts_sast.txt
Architecture:
model_type: det
algorithm: SAST
Transform:
Backbone:
name: ResNet_SAST
layers: 50
Neck:
name: SASTFPN
with_cab: True
Head:
name: SASTHead
Loss:
name: SASTLoss
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
# name: Cosine
learning_rate: 0.001
# warmup_epoch: 0
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: SASTPostProcess
score_thresh: 0.5
sample_pts_num: 2
nms_thresh: 0.2
expand_scale: 1.0
shrink_ratio_of_width: 0.3
Metric:
name: DetMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_path: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt]
data_ratio_list: [0.5, 0.5]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- SASTProcessTrain:
image_shape: [512, 512]
min_crop_side_ratio: 0.3
min_crop_size: 24
min_text_size: 4
max_text_size: 512
- KeepKeys:
keep_keys: ['image', 'score_map', 'border_map', 'training_mask', 'tvo_map', 'tco_map'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 4
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
resize_long: 1536
- 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: 2

109
configs/det/det_r50_vd_sast_totaltext.yml
Unescape View File

@ -0,0 +1,109 @@
Global:
use_gpu: true
epoch_num: 5000
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/sast_r50_vd_tt/
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
save_res_path: ./output/sast_r50_vd_tt/predicts_sast.txt
Architecture:
model_type: det
algorithm: SAST
Transform:
Backbone:
name: ResNet_SAST
layers: 50
Neck:
name: SASTFPN
with_cab: True
Head:
name: SASTHead
Loss:
name: SASTLoss
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
# name: Cosine
learning_rate: 0.001
# warmup_epoch: 0
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: SASTPostProcess
score_thresh: 0.5
sample_pts_num: 6
nms_thresh: 0.2
expand_scale: 1.2
shrink_ratio_of_width: 0.2
Metric:
name: DetMetric
main_indicator: hmean
Train:
dataset:
name: SimpleDataSet
label_file_list: [./train_data/icdar2013/train_label_json.txt, ./train_data/icdar2015/train_label_json.txt, ./train_data/icdar17_mlt_latin/train_label_json.txt, ./train_data/coco_text_icdar_4pts/train_label_json.txt]
ratio_list: [0.1, 0.45, 0.3, 0.15]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- SASTProcessTrain:
image_shape: [512, 512]
min_crop_side_ratio: 0.3
min_crop_size: 24
min_text_size: 4
max_text_size: 512
- KeepKeys:
keep_keys: ['image', 'score_map', 'border_map', 'training_mask', 'tvo_map', 'tco_map'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 4
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list:
- ./train_data/total_text_icdar_14pt/test_label_json.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
resize_long: 768
- 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: 2

2
configs/rec/ch_ppocr_v1.1/rec_chinese_common_train_v1.1.yaml → configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yaml
Unescape View File

@ -3,7 +3,7 @@ Global:
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_chinese_common_v1.1
save_model_dir: ./output/rec_chinese_common_v2.0
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [0, 2000]

4
configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yaml → configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yaml
Unescape View File

@ -3,7 +3,7 @@ Global:
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_chinese_lite_v1.1
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]
@ -19,7 +19,7 @@ Global:
character_type: ch
max_text_length: 25
infer_mode: False
use_space_char: False
use_space_char: True
Optimizer:

4
configs/rec/multi_language/rec_en_number_lite_train.yml
Unescape View File

@ -1,5 +1,5 @@
Global:
use_gpu: true
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
@ -15,7 +15,7 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/dict/ic15_dict.txt
character_dict_path: ppocr/utils/dict/en_dict.txt
character_type: ch
max_text_length: 25
infer_mode: False

8
configs/rec/multi_language/rec_french_lite_train.yml
Unescape View File

@ -1,5 +1,5 @@
Global:
use_gpu: true
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
@ -9,9 +9,9 @@ Global:
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
pretrained_model:
pretrained_model:
checkpoints:
save_inference_dir:
save_inference_dir:
use_visualdl: False
infer_img:
# for data or label process
@ -19,7 +19,7 @@ Global:
character_type: french
max_text_length: 25
infer_mode: False
use_space_char: True
use_space_char: False
Optimizer:

4
configs/rec/multi_language/rec_german_lite_train.yml
Unescape View File

@ -1,5 +1,5 @@
Global:
use_gpu: true
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
@ -19,7 +19,7 @@ Global:
character_type: german
max_text_length: 25
infer_mode: False
use_space_char: True
use_space_char: False
Optimizer:

4
configs/rec/multi_language/rec_japan_lite_train.yml
Unescape View File

@ -1,5 +1,5 @@
Global:
use_gpu: true
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
@ -19,7 +19,7 @@ Global:
character_type: japan
max_text_length: 25
infer_mode: False
use_space_char: True
use_space_char: False
Optimizer:

4
configs/rec/multi_language/rec_korean_lite_train.yml
Unescape View File

@ -1,5 +1,5 @@
Global:
use_gpu: true
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
@ -19,7 +19,7 @@ Global:
character_type: korean
max_text_length: 25
infer_mode: False
use_space_char: True
use_space_char: False
Optimizer:

5
configs/rec/rec_mv3_none_bilstm_ctc.yml
Unescape View File

@ -5,7 +5,7 @@ Global:
print_batch_step: 10
save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
@ -13,7 +13,7 @@ Global:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words/ch/word_1.jpg
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: en
@ -21,7 +21,6 @@ Global:
infer_mode: False
use_space_char: False
Optimizer:
name: Adam
beta1: 0.9

95
configs/rec/rec_mv3_none_none_ctc.yml
Unescape View File

@ -0,0 +1,95 @@
Global:
use_gpu: True
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/mv3_none_none_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: en
max_text_length: 25
infer_mode: False
use_space_char: False
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: Rosetta
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
Neck:
name: SequenceEncoder
encoder_type: reshape
Head:
name: CTCHead
fc_decay: 0.0004
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: LMDBDateSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: LMDBDateSet
data_dir: ./train_data/data_lmdb_release/validation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- 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

100
configs/rec/rec_mv3_tps_bilstm_ctc.yml
Unescape View File

@ -0,0 +1,100 @@
Global:
use_gpu: true
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/mv3_tps_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: en
max_text_length: 25
infer_mode: False
use_space_char: False
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: STARNet
Transform:
name: TPS
num_fiducial: 20
loc_lr: 0.1
model_name: small
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 96
Head:
name: CTCHead
fc_decay: 0.0004
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: LMDBDateSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: LMDBDateSet
data_dir: ./train_data/data_lmdb_release/validation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- 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: 4

7
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
Unescape View File

@ -5,7 +5,7 @@ Global:
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
@ -13,7 +13,7 @@ Global:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words/ch/word_1.jpg
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: en
@ -21,7 +21,6 @@ Global:
infer_mode: False
use_space_char: False
Optimizer:
name: Adam
beta1: 0.9
@ -71,7 +70,7 @@ Train:
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
shuffle: True
batch_size_per_card: 256
drop_last: True
num_workers: 8

93
configs/rec/rec_r34_vd_none_none_ctc.yml
Unescape View File

@ -0,0 +1,93 @@
Global:
use_gpu: true
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_none_none_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: en
max_text_length: 25
infer_mode: False
use_space_char: False
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: Rosetta
Backbone:
name: ResNet
layers: 34
Neck:
name: SequenceEncoder
encoder_type: reshape
Head:
name: CTCHead
fc_decay: 0.0004
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: LMDBDateSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- 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: LMDBDateSet
data_dir: ./train_data/data_lmdb_release/validation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- 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: 4

7
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
Unescape View File

@ -5,7 +5,7 @@ Global:
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_tps_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True
@ -13,7 +13,7 @@ Global:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words/ch/word_1.jpg
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: en
@ -21,7 +21,6 @@ Global:
infer_mode: False
use_space_char: False
Optimizer:
name: Adam
beta1: 0.9
@ -34,7 +33,7 @@ Optimizer:
Architecture:
model_type: rec
algorithm: CRNN
algorithm: STARNet
Transform:
name: TPS
num_fiducial: 20

3
deploy/cpp_infer/src/ocr_cls.cpp
Unescape View File

@ -81,7 +81,8 @@ cv::Mat Classifier::Run(cv::Mat &img) {
void Classifier::LoadModel(const std::string &model_dir) {
AnalysisConfig config;
config.SetModel(model_dir + "/model", model_dir + "/params");
config.SetModel(model_dir + "/inference.pdmodel",
model_dir + "/inference.pdiparams");
if (this->use_gpu_) {
config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);

3
deploy/cpp_infer/src/ocr_det.cpp
Unescape View File

@ -18,7 +18,8 @@ namespace PaddleOCR {
void DBDetector::LoadModel(const std::string &model_dir) {
AnalysisConfig config;
config.SetModel(model_dir + "/model", model_dir + "/params");
config.SetModel(model_dir + "/inference.pdmodel",
model_dir + "/inference.pdiparams");
if (this->use_gpu_) {
config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);

Some files were not shown because too many files have changed in this diff Show More

Write Preview
Loading…
Cancel
Save