Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "e7667f6fcc6e7dd9dd50be206389b20cc9585799"
Commit 19eb7eb8 authored by Leif's avatar Leif
Browse files

Merge remote-tracking branch 'origin/dygraph' into dy1

parents 0afe6c32 03b7daa5
Hide whitespace changes
Inline Side-by-side
Showing with 1301 additions and 84 deletions
configs/det/ch_ppocr_v2.1/ch_det_lite_train_distill_v2.1.yml 0 → 100644
View file @ 19eb7eb8
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]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_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:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Teacher:
pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
freeze_params: true
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 18
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDilaDBLoss:
weight: 1.0
model_name_pairs:
- ["Student", "Teacher"]
key: maps
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Teacher"]
# key: maps
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: DistillationDBPostProcess
model_name: ["Student", "Student2"]
key: head_out
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
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
configs/det/ch_ppocr_v2.1/ch_det_lite_train_dml_v2.1.yml 0 → 100644
View file @ 19eb7eb8
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]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_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:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Student2:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
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: CombinedLoss
loss_config_list:
- DistillationDMLLoss:
model_name_pairs:
- ["Student", "Student2"]
maps_name: "thrink_maps"
weight: 1.0
act: "softmax"
model_name_pairs: ["Student", "Student2"]
key: maps
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Student2"]
# key: maps
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: DistillationDBPostProcess
model_name: ["Student", "Student2"]
key: head_out
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
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
configs/det/det_mv3_db.yml
View file @ 19eb7eb8
......@@ -7,11 +7,6 @@ Global:
save_epoch_step: 1200
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
......
configs/det/det_mv3_east.yml
View file @ 19eb7eb8
......@@ -7,11 +7,6 @@ Global:
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
......
configs/det/det_r50_vd_db.yml
View file @ 19eb7eb8
......@@ -7,11 +7,6 @@ Global:
save_epoch_step: 1200
# evaluation is run every 2000 iterations
eval_batch_step: [0,2000]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
checkpoints:
......
configs/det/det_r50_vd_east.yml
View file @ 19eb7eb8
......@@ -7,11 +7,6 @@ Global:
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_pretrained/
checkpoints:
......
configs/det/det_r50_vd_sast_icdar15.yml
View file @ 19eb7eb8
......@@ -7,19 +7,15 @@ Global:
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
checkpoints:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
infer_img:
save_res_path: ./output/sast_r50_vd_ic15/predicts_sast.txt
Architecture:
model_type: det
algorithm: SAST
......
configs/det/det_r50_vd_sast_totaltext.yml
View file @ 19eb7eb8
......@@ -7,11 +7,6 @@ Global:
save_epoch_step: 1000
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [4000, 5000]
# 1. If pretrained_model is saved in static mode, such as classification pretrained model
# from static branch, load_static_weights must be set as True.
# 2. If you want to finetune the pretrained models we provide in the docs,
# you should set load_static_weights as False.
load_static_weights: True
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
checkpoints:
......
configs/e2e/e2e_r50_vd_pg.yml 0 → 100644
View file @ 19eb7eb8
Global:
use_gpu: True
epoch_num: 600
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/pgnet_r50_vd_totaltext/
save_epoch_step: 10
# evaluation is run every 0 iterationss after the 1000th iteration
eval_batch_step: [ 0, 1000 ]
cal_metric_during_train: False
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
valid_set: totaltext # two mode: totaltext valid curved words, partvgg valid non-curved words
save_res_path: ./output/pgnet_r50_vd_totaltext/predicts_pgnet.txt
character_dict_path: ppocr/utils/ic15_dict.txt
character_type: EN
max_text_length: 50 # the max length in seq
max_text_nums: 30 # the max seq nums in a pic
tcl_len: 64
Architecture:
model_type: e2e
algorithm: PGNet
Transform:
Backbone:
name: ResNet
layers: 50
Neck:
name: PGFPN
Head:
name: PGHead
Loss:
name: PGLoss
tcl_bs: 64
max_text_length: 50 # the same as Global: max_text_length
max_text_nums: 30 # the same as Global：max_text_nums
pad_num: 36 # the length of dict for pad
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.001
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: PGPostProcess
score_thresh: 0.5
mode: fast # fast or slow two ways
Metric:
name: E2EMetric
mode: A # two ways for eval, A: label from txt, B: label from gt_mat
gt_mat_dir: ./train_data/total_text/gt # the dir of gt_mat
character_dict_path: ppocr/utils/ic15_dict.txt
main_indicator: f_score_e2e
Train:
dataset:
name: PGDataSet
data_dir: ./train_data/total_text/train
label_file_list: [./train_data/total_text/train/train.txt]
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- E2ELabelEncodeTrain:
- PGProcessTrain:
batch_size: 14 # same as loader: batch_size_per_card
min_crop_size: 24
min_text_size: 4
max_text_size: 512
- KeepKeys:
keep_keys: [ 'images', 'tcl_maps', 'tcl_label_maps', 'border_maps','direction_maps', 'training_masks', 'label_list', 'pos_list', 'pos_mask' ] # dataloader will return list in this order
loader:
shuffle: True
drop_last: True
batch_size_per_card: 14
num_workers: 16
Eval:
dataset:
name: PGDataSet
data_dir: ./train_data/total_text/test
label_file_list: [./train_data/total_text/test/test.txt]
transforms:
- DecodeImage: # load image
img_mode: RGB
channel_first: False
- E2ELabelEncodeTest:
- E2EResizeForTest:
max_side_len: 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', 'texts', 'ignore_tags', 'img_id']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
\ No newline at end of file
configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml
View file @ 19eb7eb8
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_chinese_common_v2.0.txt
Optimizer:
......
configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml
View file @ 19eb7eb8
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
Optimizer:
......
configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml 0 → 100644
View file @ 19eb7eb8
Global:
debug: false
use_gpu: true
epoch_num: 800
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_chinese_lite_distillation_v2.1
save_epoch_step: 3
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
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
character_type: ch
max_text_length: 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_chinese_lite_distillation_v2.1.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Piecewise
decay_epochs : [700, 800]
values : [0.001, 0.0001]
warmup_epoch: 5
regularizer:
name: L2
factor: 2.0e-05
Architecture:
model_type: &model_type "rec"
name: DistillationModel
algorithm: Distillation
Models:
Teacher:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: CRNN
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 64
Head:
name: CTCHead
mid_channels: 96
fc_decay: 0.00002
Student:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: CRNN
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 64
Head:
name: CTCHead
mid_channels: 96
fc_decay: 0.00002
Loss:
name: CombinedLoss
loss_config_list:
- DistillationCTCLoss:
weight: 1.0
model_name_list: ["Student", "Teacher"]
key: head_out
- DistillationDMLLoss:
weight: 1.0
act: "softmax"
model_name_pairs:
- ["Student", "Teacher"]
key: head_out
- DistillationDistanceLoss:
weight: 1.0
mode: "l2"
model_name_pairs:
- ["Student", "Teacher"]
key: backbone_out
PostProcess:
name: DistillationCTCLabelDecode
model_name: ["Student", "Teacher"]
key: head_out
Metric:
name: DistillationMetric
base_metric_name: RecMetric
main_indicator: acc
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list:
- ./train_data/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug:
- CTCLabelEncode:
- RecResizeImg:
image_shape: [3, 32, 320]
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: true
batch_size_per_card: 128
drop_last: true
num_sections: 1
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- CTCLabelEncode:
- RecResizeImg:
image_shape: [3, 32, 320]
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 8
configs/rec/multi_language/generate_multi_language_configs.py
View file @ 19eb7eb8
......@@ -19,21 +19,56 @@ import logging
logging.basicConfig(level=logging.INFO)
support_list = {
'it':'italian', 'xi':'spanish', 'pu':'portuguese', 'ru':'russian', 'ar':'arabic',
'ta':'tamil', 'ug':'uyghur', 'fa':'persian', 'ur':'urdu', 'rs':'serbian latin',
'oc':'occitan', 'rsc':'serbian cyrillic', 'bg':'bulgarian', 'uk':'ukranian', 'be':'belarusian',
'te':'telugu', 'ka':'kannada', 'chinese_cht':'chinese tradition','hi':'hindi','mr':'marathi',
'ne':'nepali',
'it': 'italian',
'xi': 'spanish',
'pu': 'portuguese',
'ru': 'russian',
'ar': 'arabic',
'ta': 'tamil',
'ug': 'uyghur',
'fa': 'persian',
'ur': 'urdu',
'rs': 'serbian latin',
'oc': 'occitan',
'rsc': 'serbian cyrillic',
'bg': 'bulgarian',
'uk': 'ukranian',
'be': 'belarusian',
'te': 'telugu',
'ka': 'kannada',
'chinese_cht': 'chinese tradition',
'hi': 'hindi',
'mr': 'marathi',
'ne': 'nepali',
}
assert(
os.path.isfile("./rec_multi_language_lite_train.yml")
),"Loss basic configuration file rec_multi_language_lite_train.yml.\
latin_lang = [
'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',
'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
'sw', 'tl', 'tr', 'uz', 'vi', 'latin'
]
arabic_lang = ['ar', 'fa', 'ug', 'ur']
cyrillic_lang = [
'ru', 'rs_cyrillic', 'be', 'bg', 'uk', 'mn', 'abq', 'ady', 'kbd', 'ava',
'dar', 'inh', 'che', 'lbe', 'lez', 'tab', 'cyrillic'
]
devanagari_lang = [
'hi', 'mr', 'ne', 'bh', 'mai', 'ang', 'bho', 'mah', 'sck', 'new', 'gom',
'sa', 'bgc', 'devanagari'
]
multi_lang = latin_lang + arabic_lang + cyrillic_lang + devanagari_lang
assert (os.path.isfile("./rec_multi_language_lite_train.yml")
), "Loss basic configuration file rec_multi_language_lite_train.yml.\
You can download it from \
https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/configs/rec/multi_language/"
global_config = yaml.load(open("./rec_multi_language_lite_train.yml", 'rb'), Loader=yaml.Loader)
global_config = yaml.load(
open("./rec_multi_language_lite_train.yml", 'rb'), Loader=yaml.Loader)
project_path = os.path.abspath(os.path.join(os.getcwd(), "../../../"))
class ArgsParser(ArgumentParser):
def __init__(self):
super(ArgsParser, self).__init__(
......@@ -41,15 +76,30 @@ class ArgsParser(ArgumentParser):
self.add_argument(
"-o", "--opt", nargs='+', help="set configuration options")
self.add_argument(
"-l", "--language", nargs='+', help="set language type, support {}".format(support_list))
"-l",
"--language",
nargs='+',
help="set language type, support {}".format(support_list))
self.add_argument(
"--train",type=str,help="you can use this command to change the train dataset default path")
"--train",
type=str,
help="you can use this command to change the train dataset default path"
)
self.add_argument(
"--val",type=str,help="you can use this command to change the eval dataset default path")
"--val",
type=str,
help="you can use this command to change the eval dataset default path"
)
self.add_argument(
"--dict",type=str,help="you can use this command to change the dictionary default path")
"--dict",
type=str,
help="you can use this command to change the dictionary default path"
)
self.add_argument(
"--data_dir",type=str,help="you can use this command to change the dataset default root path")
"--data_dir",
type=str,
help="you can use this command to change the dataset default root path"
)
def parse_args(self, argv=None):
args = super(ArgsParser, self).parse_args(argv)
......@@ -68,21 +118,37 @@ class ArgsParser(ArgumentParser):
return config
def _set_language(self, type):
assert(type),"please use -l or --language to choose language type"
lang = type[0]
assert (type), "please use -l or --language to choose language type"
assert(
type[0] in support_list.keys()
lang in support_list.keys() or lang in multi_lang
),"the sub_keys(-l or --language) can only be one of support list: \n{},\nbut get: {}, " \
"please check your running command".format(support_list, type)
global_config['Global']['character_dict_path'] = 'ppocr/utils/dict/{}_dict.txt'.format(type[0])
global_config['Global']['save_model_dir'] = './output/rec_{}_lite'.format(type[0])
global_config['Train']['dataset']['label_file_list'] = ["train_data/{}_train.txt".format(type[0])]
global_config['Eval']['dataset']['label_file_list'] = ["train_data/{}_val.txt".format(type[0])]
global_config['Global']['character_type'] = type[0]
assert(
os.path.isfile(os.path.join(project_path,global_config['Global']['character_dict_path']))
),"Loss default dictionary file {}_dict.txt.You can download it from \
https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/ppocr/utils/dict/".format(type[0])
return type[0]
"please check your running command".format(multi_lang, type)
if lang in latin_lang:
lang = "latin"
elif lang in arabic_lang:
lang = "arabic"
elif lang in cyrillic_lang:
lang = "cyrillic"
elif lang in devanagari_lang:
lang = "devanagari"
global_config['Global'][
'character_dict_path'] = 'ppocr/utils/dict/{}_dict.txt'.format(lang)
global_config['Global'][
'save_model_dir'] = './output/rec_{}_lite'.format(lang)
global_config['Train']['dataset'][
'label_file_list'] = ["train_data/{}_train.txt".format(lang)]
global_config['Eval']['dataset'][
'label_file_list'] = ["train_data/{}_val.txt".format(lang)]
global_config['Global']['character_type'] = lang
assert (
os.path.isfile(
os.path.join(project_path, global_config['Global'][
'character_dict_path']))
), "Loss default dictionary file {}_dict.txt.You can download it from \
https://github.com/PaddlePaddle/PaddleOCR/tree/dygraph/ppocr/utils/dict/".format(
lang)
return lang
def merge_config(config):
......@@ -110,43 +176,51 @@ def merge_config(config):
cur[sub_key] = value
else:
cur = cur[sub_key]
def loss_file(path):
assert(
os.path.exists(path)
),"There is no such file:{},Please do not forget to put in the specified file".format(path)
assert (
os.path.exists(path)
), "There is no such file:{},Please do not forget to put in the specified file".format(
path)
if __name__ == '__main__':
FLAGS = ArgsParser().parse_args()
merge_config(FLAGS.opt)
save_file_path = 'rec_{}_lite_train.yml'.format(FLAGS.language)
if os.path.isfile(save_file_path):
os.remove(save_file_path)
if FLAGS.train:
global_config['Train']['dataset']['label_file_list'] = [FLAGS.train]
train_label_path = os.path.join(project_path,FLAGS.train)
train_label_path = os.path.join(project_path, FLAGS.train)
loss_file(train_label_path)
if FLAGS.val:
global_config['Eval']['dataset']['label_file_list'] = [FLAGS.val]
eval_label_path = os.path.join(project_path,FLAGS.val)
eval_label_path = os.path.join(project_path, FLAGS.val)
loss_file(eval_label_path)
if FLAGS.dict:
global_config['Global']['character_dict_path'] = FLAGS.dict
dict_path = os.path.join(project_path,FLAGS.dict)
dict_path = os.path.join(project_path, FLAGS.dict)
loss_file(dict_path)
if FLAGS.data_dir:
global_config['Eval']['dataset']['data_dir'] = FLAGS.data_dir
global_config['Train']['dataset']['data_dir'] = FLAGS.data_dir
data_dir = os.path.join(project_path,FLAGS.data_dir)
data_dir = os.path.join(project_path, FLAGS.data_dir)
loss_file(data_dir)
with open(save_file_path, 'w') as f:
yaml.dump(dict(global_config), f, default_flow_style=False, sort_keys=False)
yaml.dump(
dict(global_config), f, default_flow_style=False, sort_keys=False)
logging.info("Project path is :{}".format(project_path))
logging.info("Train list path set to :{}".format(global_config['Train']['dataset']['label_file_list'][0]))
logging.info("Eval list path set to :{}".format(global_config['Eval']['dataset']['label_file_list'][0]))
logging.info("Dataset root path set to :{}".format(global_config['Eval']['dataset']['data_dir']))
logging.info("Dict path set to :{}".format(global_config['Global']['character_dict_path']))
logging.info("Config file set to :configs/rec/multi_language/{}".format(save_file_path))
logging.info("Train list path set to :{}".format(global_config['Train'][
'dataset']['label_file_list'][0]))
logging.info("Eval list path set to :{}".format(global_config['Eval'][
'dataset']['label_file_list'][0]))
logging.info("Dataset root path set to :{}".format(global_config['Eval'][
'dataset']['data_dir']))
logging.info("Dict path set to :{}".format(global_config['Global'][
'character_dict_path']))
logging.info("Config file set to :configs/rec/multi_language/{}".
format(save_file_path))
configs/rec/multi_language/rec_arabic_lite_train.yml 0 → 100644
View file @ 19eb7eb8
Global:
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_arabic_lite
save_epoch_step: 3
eval_batch_step:
- 0
- 2000
cal_metric_during_train: true
pretrained_model: null
checkpoints: null
save_inference_dir: null
use_visualdl: false
infer_img: null
character_dict_path: ppocr/utils/dict/arabic_dict.txt
character_type: arabic
max_text_length: 25
infer_mode: false
use_space_char: true
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
regularizer:
name: L2
factor: 1.0e-05
Architecture:
model_type: rec
algorithm: CRNN
Transform: null
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: 1.0e-05
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/arabic_train.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug: null
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
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/arabic_val.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: false
drop_last: false
batch_size_per_card: 256
num_workers: 8
configs/rec/multi_language/rec_cyrillic_lite_train.yml 0 → 100644
View file @ 19eb7eb8
Global:
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_cyrillic_lite
save_epoch_step: 3
eval_batch_step:
- 0
- 2000
cal_metric_during_train: true
pretrained_model: null
checkpoints: null
save_inference_dir: null
use_visualdl: false
infer_img: null
character_dict_path: ppocr/utils/dict/cyrillic_dict.txt
character_type: cyrillic
max_text_length: 25
infer_mode: false
use_space_char: true
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
regularizer:
name: L2
factor: 1.0e-05
Architecture:
model_type: rec
algorithm: CRNN
Transform: null
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: 1.0e-05
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/cyrillic_train.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug: null
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
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/cyrillic_val.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: false
drop_last: false
batch_size_per_card: 256
num_workers: 8
configs/rec/multi_language/rec_devanagari_lite_train.yml 0 → 100644
View file @ 19eb7eb8
Global:
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_devanagari_lite
save_epoch_step: 3
eval_batch_step:
- 0
- 2000
cal_metric_during_train: true
pretrained_model: null
checkpoints: null
save_inference_dir: null
use_visualdl: false
infer_img: null
character_dict_path: ppocr/utils/dict/devanagari_dict.txt
character_type: devanagari
max_text_length: 25
infer_mode: false
use_space_char: true
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
regularizer:
name: L2
factor: 1.0e-05
Architecture:
model_type: rec
algorithm: CRNN
Transform: null
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: 1.0e-05
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/devanagari_train.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug: null
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
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/devanagari_val.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: false
drop_last: false
batch_size_per_card: 256
num_workers: 8
configs/rec/multi_language/rec_en_number_lite_train.yml
View file @ 19eb7eb8
......@@ -15,11 +15,11 @@ Global:
use_visualdl: False
infer_img:
# for data or label process
character_dict_path: ppocr/utils/dict/en_dict.txt
character_dict_path: ppocr/utils/en_dict.txt
character_type: EN
max_text_length: 25
infer_mode: False
use_space_char: False
use_space_char: True
Optimizer:
......
configs/rec/multi_language/rec_latin_lite_train.yml 0 → 100644
View file @ 19eb7eb8
Global:
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_latin_lite
save_epoch_step: 3
eval_batch_step:
- 0
- 2000
cal_metric_during_train: true
pretrained_model: null
checkpoints: null
save_inference_dir: null
use_visualdl: false
infer_img: null
character_dict_path: ppocr/utils/dict/latin_dict.txt
character_type: latin
max_text_length: 25
infer_mode: false
use_space_char: true
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
regularizer:
name: L2
factor: 1.0e-05
Architecture:
model_type: rec
algorithm: CRNN
Transform: null
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: 1.0e-05
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/latin_train.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug: null
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
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/latin_val.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- CTCLabelEncode: null
- RecResizeImg:
image_shape:
- 3
- 32
- 320
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: false
drop_last: false
batch_size_per_card: 256
num_workers: 8
configs/rec/rec_icdar15_train.yml
View file @ 19eb7eb8
......@@ -10,7 +10,7 @@ Global:
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
save_inference_dir: ./
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_ic15.txt
Optimizer:
name: Adam
......@@ -59,8 +60,8 @@ Metric:
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list: ["./train_data/train_list.txt"]
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
......@@ -80,8 +81,8 @@ Train:
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list: ["./train_data/train_list.txt"]
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
......
configs/rec/rec_mtb_nrtr.yml 0 → 100644
View file @ 19eb7eb8
Global:
use_gpu: True
epoch_num: 21
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/nrtr/
save_epoch_step: 1
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
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_symbol
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_nrtr.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.99
clip_norm: 5.0
lr:
name: Cosine
learning_rate: 0.0005
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0.
Architecture:
model_type: rec
algorithm: NRTR
in_channels: 1
Transform:
Backbone:
name: MTB
cnn_num: 2
Head:
name: Transformer
d_model: 512
num_encoder_layers: 6
beam_size: 10 # When Beam size is greater than 0, it means to use beam search when evaluation.
Loss:
name: NRTRLoss
smoothing: True
PostProcess:
name: NRTRLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- NRTRDecodeImage: # load image
img_mode: BGR
channel_first: False
- NRTRLabelEncode: # Class handling label
- NRTRRecResizeImg:
image_shape: [100, 32]
resize_type: PIL # PIL or OpenCV
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 512
drop_last: True
num_workers: 8
Eval:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/evaluation/
transforms:
- NRTRDecodeImage: # load image
img_mode: BGR
channel_first: False
- NRTRLabelEncode: # Class handling label
- NRTRRecResizeImg:
image_shape: [100, 32]
resize_type: PIL # PIL or OpenCV
- 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: 1
use_shared_memory: False
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment