111 lines
2.4 KiB
YAML
111 lines
2.4 KiB
YAML
Global:
|
|
use_gpu: True
|
|
epoch_num: 6
|
|
log_smooth_window: 20
|
|
print_batch_step: 50
|
|
save_model_dir: ./output/rec/rec_resnet_rfl_visual/
|
|
save_epoch_step: 1
|
|
# evaluation is run every 5000 iterations after the 4000th iteration
|
|
eval_batch_step: [0, 5000]
|
|
cal_metric_during_train: False
|
|
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:
|
|
max_text_length: 25
|
|
infer_mode: False
|
|
use_space_char: False
|
|
save_res_path: ./output/rec/rec_resnet_rfl_visual.txt
|
|
|
|
|
|
Optimizer:
|
|
name: AdamW
|
|
beta1: 0.9
|
|
beta2: 0.999
|
|
weight_decay: 0.0
|
|
clip_norm_global: 5.0
|
|
lr:
|
|
name: Piecewise
|
|
decay_epochs : [3, 4, 5]
|
|
values : [0.001, 0.0003, 0.00009, 0.000027]
|
|
|
|
Architecture:
|
|
model_type: rec
|
|
algorithm: RFL
|
|
in_channels: 1
|
|
Transform:
|
|
name: TPS
|
|
num_fiducial: 20
|
|
loc_lr: 1.0
|
|
model_name: large
|
|
Backbone:
|
|
name: ResNetRFL
|
|
use_cnt: True
|
|
use_seq: False
|
|
Neck:
|
|
name: RFAdaptor
|
|
use_v2s: False
|
|
use_s2v: False
|
|
Head:
|
|
name: RFLHead
|
|
in_channels: 512
|
|
hidden_size: 256
|
|
batch_max_legnth: 25
|
|
out_channels: 38
|
|
use_cnt: True
|
|
use_seq: False
|
|
Loss:
|
|
name: RFLLoss
|
|
|
|
PostProcess:
|
|
name: RFLLabelDecode
|
|
|
|
Metric:
|
|
name: CNTMetric
|
|
main_indicator: acc
|
|
|
|
Train:
|
|
dataset:
|
|
name: LMDBDataSet
|
|
data_dir: ./train_data/data_lmdb_release/training
|
|
transforms:
|
|
- DecodeImage: # load image
|
|
img_mode: BGR
|
|
channel_first: False
|
|
- RFLLabelEncode: # Class handling label
|
|
- RFLRecResizeImg:
|
|
image_shape: [1, 32, 100]
|
|
padding: false
|
|
interpolation: 2
|
|
- KeepKeys:
|
|
keep_keys: ['image', 'label', 'length', 'cnt_label'] # dataloader will return list in this order
|
|
loader:
|
|
shuffle: True
|
|
batch_size_per_card: 64
|
|
drop_last: True
|
|
num_workers: 8
|
|
|
|
Eval:
|
|
dataset:
|
|
name: LMDBDataSet
|
|
data_dir: ./train_data/data_lmdb_release/evaluation
|
|
transforms:
|
|
- DecodeImage: # load image
|
|
img_mode: BGR
|
|
channel_first: False
|
|
- RFLLabelEncode: # Class handling label
|
|
- RFLRecResizeImg:
|
|
image_shape: [1, 32, 100]
|
|
padding: false
|
|
interpolation: 2
|
|
- KeepKeys:
|
|
keep_keys: ['image', 'label', 'length', 'cnt_label'] # dataloader will return list in this order
|
|
loader:
|
|
shuffle: False
|
|
drop_last: False
|
|
batch_size_per_card: 256
|
|
num_workers: 8
|