forked from PaddlePaddle/PaddleOCR
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'dygraph' into add_multi_doc
- Loading branch information
Showing
39 changed files
with
4,534 additions
and
97 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,114 @@ | ||
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 ] | ||
# 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: False | ||
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 | ||
Metric: | ||
name: E2EMetric | ||
character_dict_path: ppocr/utils/ic15_dict.txt | ||
main_indicator: f_score_e2e | ||
|
||
Train: | ||
dataset: | ||
name: PGDataSet | ||
label_file_list: [.././train_data/total_text/train/] | ||
ratio_list: [1.0] | ||
data_format: icdar #two data format: icdar/textnet | ||
transforms: | ||
- DecodeImage: # load image | ||
img_mode: BGR | ||
channel_first: False | ||
- 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/ | ||
label_file_list: [./train_data/total_text/test/] | ||
transforms: | ||
- DecodeImage: # load image | ||
img_mode: RGB | ||
channel_first: False | ||
- E2ELabelEncode: | ||
- 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', 'strs', 'tags' ] | ||
loader: | ||
shuffle: False | ||
drop_last: False | ||
batch_size_per_card: 1 # must be 1 | ||
num_workers: 2 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.