提交 0da2cdb4 编写于 作者: W WenmuZhou

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

Global:
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_chinese_common_v1.1
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: doc/imgs_words/ch/word_1.jpg
# for data or label process
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
character_type: ch
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: 0.00004
Architecture:
model_type: rec
algorithm: CRNN
Transform:
Backbone:
name: ResNet
layers: 34
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 256
Head:
name: CTCHead
fc_decay: 0.00004
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/val_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
...@@ -104,8 +104,8 @@ class SimpleDataSet(Dataset): ...@@ -104,8 +104,8 @@ class SimpleDataSet(Dataset):
try: try:
data_line = data_line.decode('utf-8') data_line = data_line.decode('utf-8')
substr = data_line.strip("\n").split(self.delimiter) substr = data_line.strip("\n").split(self.delimiter)
file_name = substr[1] file_name = substr[0]
label = substr[0] label = substr[1]
img_path = os.path.join(self.data_dir, file_name) img_path = os.path.join(self.data_dir, file_name)
data = {'img_path': img_path, 'label': label} data = {'img_path': img_path, 'label': label}
with open(data['img_path'], 'rb') as f: with open(data['img_path'], 'rb') as f:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册