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

Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into py_inference_doc

Browse Source
release/2.0-rc1-0
zhoujun 4 years ago
parent 204ab814f1 055f207fcf
commit 19d66e6209
79 changed files with 15038 additions and 1008 deletions
Show Stats Download Patch File Download Diff File

7
MANIFEST.in
Unescape View File

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

2
configs/det/det_mv3_db.yml
Unescape View File

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

102
configs/rec/multi_language/rec_en_number_lite_train.yml
Unescape View File

@ -0,0 +1,102 @@
Global:
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_en_number_lite
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
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:
# for data or label process
character_dict_path: ppocr/utils/dict/en_dict.txt
character_type: ch
max_text_length: 25
infer_mode: False
use_space_char: False
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/
label_file_list: ["./train_data/train_list.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/
label_file_list: ["./train_data/eval_list.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

102
configs/rec/multi_language/rec_french_lite_train.yml
Unescape View File

@ -0,0 +1,102 @@
Global:
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_french_lite
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
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:
# for data or label process
character_dict_path: ppocr/utils/dict/french_dict.txt
character_type: french
max_text_length: 25
infer_mode: False
use_space_char: False
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/
label_file_list: ["./train_data/train_list.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/
label_file_list: ["./train_data/eval_list.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

102
configs/rec/multi_language/rec_german_lite_train.yml
Unescape View File

@ -0,0 +1,102 @@
Global:
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_german_lite
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
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:
# for data or label process
character_dict_path: ppocr/utils/dict/german_dict.txt
character_type: german
max_text_length: 25
infer_mode: False
use_space_char: False
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/
label_file_list: ["./train_data/train_list.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/
label_file_list: ["./train_data/eval_list.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

102
configs/rec/multi_language/rec_japan_lite_train.yml
Unescape View File

@ -0,0 +1,102 @@
Global:
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_japan_lite
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
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:
# for data or label process
character_dict_path: ppocr/utils/dict/japan_dict.txt
character_type: japan
max_text_length: 25
infer_mode: False
use_space_char: False
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/
label_file_list: ["./train_data/train_list.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/
label_file_list: ["./train_data/eval_list.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

102
configs/rec/multi_language/rec_korean_lite_train.yml
Unescape View File

@ -0,0 +1,102 @@
Global:
use_gpu: True
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_korean_lite
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
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:
# for data or label process
character_dict_path: ppocr/utils/dict/korean_dict.txt
character_type: korean
max_text_length: 25
infer_mode: False
use_space_char: False
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/
label_file_list: ["./train_data/train_list.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/
label_file_list: ["./train_data/eval_list.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

5
configs/rec/rec_mv3_none_bilstm_ctc.yml
Unescape View File

@ -5,7 +5,7 @@ Global:
print_batch_step: 10 print_batch_step: 10
save_model_dir: ./output/rec/mv3_none_bilstm_ctc/ save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
save_epoch_step: 3 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] eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True # if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True cal_metric_during_train: True
@ -13,7 +13,7 @@ Global:
checkpoints: checkpoints:
save_inference_dir: save_inference_dir:
use_visualdl: False 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 # for data or label process
character_dict_path: character_dict_path:
character_type: en character_type: en
@ -21,7 +21,6 @@ Global:
infer_mode: False infer_mode: False
use_space_char: False use_space_char: False
Optimizer: Optimizer:
name: Adam name: Adam
beta1: 0.9 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 print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc/ save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc/
save_epoch_step: 3 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] eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True # if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True cal_metric_during_train: True
@ -13,7 +13,7 @@ Global:
checkpoints: checkpoints:
save_inference_dir: save_inference_dir:
use_visualdl: False 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 # for data or label process
character_dict_path: character_dict_path:
character_type: en character_type: en
@ -21,7 +21,6 @@ Global:
infer_mode: False infer_mode: False
use_space_char: False use_space_char: False
Optimizer: Optimizer:
name: Adam name: Adam
beta1: 0.9 beta1: 0.9
@ -71,7 +70,7 @@ Train:
- KeepKeys: - KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader: loader:
shuffle: False shuffle: True
batch_size_per_card: 256 batch_size_per_card: 256
drop_last: True drop_last: True
num_workers: 8 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 print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_tps_bilstm_ctc/ save_model_dir: ./output/rec/r34_vd_tps_bilstm_ctc/
save_epoch_step: 3 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] eval_batch_step: [0, 2000]
# if pretrained_model is saved in static mode, load_static_weights must set to True # if pretrained_model is saved in static mode, load_static_weights must set to True
cal_metric_during_train: True cal_metric_during_train: True
@ -13,7 +13,7 @@ Global:
checkpoints: checkpoints:
save_inference_dir: save_inference_dir:
use_visualdl: False 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 # for data or label process
character_dict_path: character_dict_path:
character_type: en character_type: en
@ -21,7 +21,6 @@ Global:
infer_mode: False infer_mode: False
use_space_char: False use_space_char: False
Optimizer: Optimizer:
name: Adam name: Adam
beta1: 0.9 beta1: 0.9
@ -34,7 +33,7 @@ Optimizer:
Architecture: Architecture:
model_type: rec model_type: rec
algorithm: CRNN algorithm: STARNet
Transform: Transform:
name: TPS name: TPS
num_fiducial: 20 num_fiducial: 20

0
deploy/hubserving/ocr_cls/__init__.py
Unescape View File

15
deploy/hubserving/ocr_cls/config.json
Unescape View File

@ -0,0 +1,15 @@
{
"modules_info": {
"ocr_cls": {
"init_args": {
"version": "1.0.0",
"use_gpu": true
},
"predict_args": {
}
}
},
"port": 8866,
"use_multiprocess": false,
"workers": 2
}

121
deploy/hubserving/ocr_cls/module.py
Unescape View File

@ -0,0 +1,121 @@
# -*- coding:utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import sys
sys.path.insert(0, ".")
from paddlehub.common.logger import logger
from paddlehub.module.module import moduleinfo, runnable, serving
import cv2
import paddlehub as hub
from tools.infer.utility import base64_to_cv2
from tools.infer.predict_cls import TextClassifier
@moduleinfo(
name="ocr_cls",
version="1.0.0",
summary="ocr recognition service",
author="paddle-dev",
author_email="paddle-dev@baidu.com",
type="cv/text_recognition")
class OCRCls(hub.Module):
def _initialize(self, use_gpu=False, enable_mkldnn=False):
"""
initialize with the necessary elements
"""
from ocr_cls.params import read_params
cfg = read_params()
cfg.use_gpu = use_gpu
if use_gpu:
try:
_places = os.environ["CUDA_VISIBLE_DEVICES"]
int(_places[0])
print("use gpu: ", use_gpu)
print("CUDA_VISIBLE_DEVICES: ", _places)
cfg.gpu_mem = 8000
except:
raise RuntimeError(
"Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
)
cfg.ir_optim = True
cfg.enable_mkldnn = enable_mkldnn
self.text_classifier = TextClassifier(cfg)
def read_images(self, paths=[]):
images = []
for img_path in paths:
assert os.path.isfile(
img_path), "The {} isn't a valid file.".format(img_path)
img = cv2.imread(img_path)
if img is None:
logger.info("error in loading image:{}".format(img_path))
continue
images.append(img)
return images
def predict(self, images=[], paths=[]):
"""
Get the text angle in the predicted images.
Args:
images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
paths (list[str]): The paths of images. If paths not images
Returns:
res (list): The result of text detection box and save path of images.
"""
if images != [] and isinstance(images, list) and paths == []:
predicted_data = images
elif images == [] and isinstance(paths, list) and paths != []:
predicted_data = self.read_images(paths)
else:
raise TypeError("The input data is inconsistent with expectations.")
assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
img_list = []
for img in predicted_data:
if img is None:
continue
img_list.append(img)
rec_res_final = []
try:
img_list, cls_res, predict_time = self.text_classifier(img_list)
for dno in range(len(cls_res)):
angle, score = cls_res[dno]
rec_res_final.append({
'angle': angle,
'confidence': float(score),
})
except Exception as e:
print(e)
return [[]]
return [rec_res_final]
@serving
def serving_method(self, images, **kwargs):
"""
Run as a service.
"""
images_decode = [base64_to_cv2(image) for image in images]
results = self.predict(images_decode, **kwargs)
return results
if __name__ == '__main__':
ocr = OCRCls()
image_path = [
'./doc/imgs_words/ch/word_1.jpg',
'./doc/imgs_words/ch/word_2.jpg',
'./doc/imgs_words/ch/word_3.jpg',
]
res = ocr.predict(paths=image_path)
print(res)

24
deploy/hubserving/ocr_cls/params.py
Unescape View File

@ -0,0 +1,24 @@
# -*- coding:utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
class Config(object):
pass
def read_params():
cfg = Config()
#params for text classifier
cfg.cls_model_dir = "./inference/ch_ppocr_mobile_v1.1_cls_infer/"
cfg.cls_image_shape = "3, 48, 192"
cfg.label_list = ['0', '180']
cfg.cls_batch_num = 30
cfg.cls_thresh = 0.9
cfg.use_zero_copy_run = False
cfg.use_pdserving = False
return cfg

2
deploy/hubserving/ocr_det/config.json
Unescape View File

@ -9,7 +9,7 @@
} }
} }
}, },
"port": 8866, "port": 8865,
"use_multiprocess": false, "use_multiprocess": false,
"workers": 2 "workers": 2
} }

28
deploy/hubserving/ocr_det/module.py
Unescape View File

@ -3,20 +3,14 @@ from __future__ import absolute_import
from __future__ import division from __future__ import division
from __future__ import print_function from __future__ import print_function
import argparse
import ast
import copy
import math
import os import os
import time import sys
sys.path.insert(0, ".")
from paddle.fluid.core import AnalysisConfig, create_paddle_predictor, PaddleTensor
from paddlehub.common.logger import logger from paddlehub.common.logger import logger
from paddlehub.module.module import moduleinfo, runnable, serving from paddlehub.module.module import moduleinfo, runnable, serving
from PIL import Image
import cv2 import cv2
import numpy as np import numpy as np
import paddle.fluid as fluid
import paddlehub as hub import paddlehub as hub
from tools.infer.utility import base64_to_cv2 from tools.infer.utility import base64_to_cv2
@ -67,9 +61,7 @@ class OCRDet(hub.Module):
images.append(img) images.append(img)
return images return images
def predict(self, def predict(self, images=[], paths=[]):
images=[],
paths=[]):
""" """
Get the text box in the predicted images. Get the text box in the predicted images.
Args: Args:
@ -87,7 +79,7 @@ class OCRDet(hub.Module):
raise TypeError("The input data is inconsistent with expectations.") raise TypeError("The input data is inconsistent with expectations.")
assert predicted_data != [], "There is not any image to be predicted. Please check the input data." assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
all_results = [] all_results = []
for img in predicted_data: for img in predicted_data:
if img is None: if img is None:
@ -99,11 +91,9 @@ class OCRDet(hub.Module):
rec_res_final = [] rec_res_final = []
for dno in range(len(dt_boxes)): for dno in range(len(dt_boxes)):
rec_res_final.append( rec_res_final.append({
{ 'text_region': dt_boxes[dno].astype(np.int).tolist()
'text_region': dt_boxes[dno].astype(np.int).tolist() })
}
)
all_results.append(rec_res_final) all_results.append(rec_res_final)
return all_results return all_results
@ -116,7 +106,7 @@ class OCRDet(hub.Module):
results = self.predict(images_decode, **kwargs) results = self.predict(images_decode, **kwargs)
return results return results
if __name__ == '__main__': if __name__ == '__main__':
ocr = OCRDet() ocr = OCRDet()
image_path = [ image_path = [
@ -124,4 +114,4 @@ if __name__ == '__main__':
'./doc/imgs/12.jpg', './doc/imgs/12.jpg',
] ]
res = ocr.predict(paths=image_path) res = ocr.predict(paths=image_path)
print(res) print(res)

14
deploy/hubserving/ocr_det/params.py
Unescape View File

@ -10,16 +10,17 @@ class Config(object):
def read_params(): def read_params():
cfg = Config() cfg = Config()
#params for text detector #params for text detector
cfg.det_algorithm = "DB" cfg.det_algorithm = "DB"
cfg.det_model_dir = "./inference/ch_det_mv3_db/" cfg.det_model_dir = "./inference/ch_ppocr_mobile_v1.1_det_infer/"
cfg.det_max_side_len = 960 cfg.det_limit_side_len = 960
cfg.det_limit_type = 'max'
#DB parmas #DB parmas
cfg.det_db_thresh =0.3 cfg.det_db_thresh = 0.3
cfg.det_db_box_thresh =0.5 cfg.det_db_box_thresh = 0.5
cfg.det_db_unclip_ratio =2.0 cfg.det_db_unclip_ratio = 2.0
# #EAST parmas # #EAST parmas
# cfg.det_east_score_thresh = 0.8 # cfg.det_east_score_thresh = 0.8
@ -37,5 +38,6 @@ def read_params():
# cfg.use_space_char = True # cfg.use_space_char = True
cfg.use_zero_copy_run = False cfg.use_zero_copy_run = False
cfg.use_pdserving = False
return cfg return cfg

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

Write Preview
Loading…
Cancel
Save