110 lines
2.4 KiB
YAML
110 lines
2.4 KiB
YAML
Global:
|
|
use_gpu: True
|
|
epoch_num: 400
|
|
log_smooth_window: 20
|
|
print_batch_step: 10
|
|
save_model_dir: ./output/rec/seed
|
|
save_epoch_step: 3
|
|
# evaluation is run every 5000 iterations after the 4000th iteration
|
|
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: 100
|
|
infer_mode: False
|
|
use_space_char: False
|
|
save_res_path: ./output/rec/predicts_seed.txt
|
|
|
|
|
|
Optimizer:
|
|
name: Adadelta
|
|
weight_deacy: 0.0
|
|
momentum: 0.9
|
|
lr:
|
|
name: Piecewise
|
|
decay_epochs: [4,5,8]
|
|
values: [1.0, 0.1, 0.01]
|
|
regularizer:
|
|
name: 'L2'
|
|
factor: 2.0e-05
|
|
|
|
|
|
Architecture:
|
|
model_type: rec
|
|
algorithm: SEED
|
|
Transform:
|
|
name: STN_ON
|
|
tps_inputsize: [32, 64]
|
|
tps_outputsize: [32, 100]
|
|
num_control_points: 20
|
|
tps_margins: [0.05,0.05]
|
|
stn_activation: none
|
|
Backbone:
|
|
name: ResNet_ASTER
|
|
Head:
|
|
name: AsterHead # AttentionHead
|
|
sDim: 512
|
|
attDim: 512
|
|
max_len_labels: 100
|
|
|
|
Loss:
|
|
name: AsterLoss
|
|
|
|
PostProcess:
|
|
name: SEEDLabelDecode
|
|
|
|
Metric:
|
|
name: RecMetric
|
|
main_indicator: acc
|
|
is_filter: True
|
|
|
|
Train:
|
|
dataset:
|
|
name: LMDBDataSet
|
|
data_dir: ./train_data/data_lmdb_release/training/
|
|
transforms:
|
|
- Fasttext:
|
|
path: "./cc.en.300.bin"
|
|
- DecodeImage: # load image
|
|
img_mode: BGR
|
|
channel_first: False
|
|
- SEEDLabelEncode: # Class handling label
|
|
- RecResizeImg:
|
|
character_type: en
|
|
image_shape: [3, 64, 256]
|
|
padding: False
|
|
- KeepKeys:
|
|
keep_keys: ['image', 'label', 'length', 'fast_label'] # dataloader will return list in this order
|
|
loader:
|
|
shuffle: True
|
|
batch_size_per_card: 256
|
|
drop_last: True
|
|
num_workers: 6
|
|
|
|
Eval:
|
|
dataset:
|
|
name: LMDBDataSet
|
|
data_dir: ./train_data/data_lmdb_release/evaluation/
|
|
transforms:
|
|
- DecodeImage: # load image
|
|
img_mode: BGR
|
|
channel_first: False
|
|
- SEEDLabelEncode: # Class handling label
|
|
- RecResizeImg:
|
|
character_type: en
|
|
image_shape: [3, 64, 256]
|
|
padding: False
|
|
- KeepKeys:
|
|
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
|
loader:
|
|
shuffle: False
|
|
drop_last: True
|
|
batch_size_per_card: 256
|
|
num_workers: 4
|