OpenOCR-Demo / configs /rec /aster /resnet31_lstm_aster_tps_on.yml
topdu's picture
openocr demo
29f689c
raw
history blame
2.08 kB
Global:
device: gpu
epoch_num: 20
log_smooth_window: 20
print_batch_step: 10
output_dir: ./output/rec/u14m_filter/resnet31_lstm_aster_tps_on
eval_epoch_step: [0, 1]
eval_batch_step: [0, 500]
cal_metric_during_train: True
pretrained_model:
checkpoints:
use_tensorboard: false
infer_img:
# for data or label process
character_dict_path: ./tools/utils/EN_symbol_dict.txt
max_text_length: 25
use_space_char: False
save_res_path: ./output/rec/predicts_aster_tps.txt
use_amp: True
grad_clip_val: 1.0
Optimizer:
name: Adam
lr: 0.002 # for 1gpus bs1024/gpu
weight_decay: 0.0
filter_bias_and_bn: False
LRScheduler:
name: OneCycleLR
warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep
cycle_momentum: False
Architecture:
model_type: rec
algorithm: aster
Transform:
name: Aster_TPS
tps_inputsize: [32, 64]
tps_outputsize: [32, 128]
Encoder:
name: ResNet_ASTER
Decoder:
name: ASTERDecoder
Loss:
name: ARLoss
Metric:
name: RecMetric
main_indicator: acc
is_filter: True
PostProcess:
name: ARLabelDecode
Train:
dataset:
name: LMDBDataSet
data_dir: ../Union14M-L-LMDB-Filtered
transforms:
- DecodeImagePIL: # load image
img_mode: RGB
- PARSeqAugPIL:
- ARLabelEncode: # Class handling label
- RecTVResize:
image_shape: [64, 256]
padding: False
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 1024
drop_last: True
num_workers: 4
Eval:
dataset:
name: LMDBDataSet
data_dir: ../evaluation
transforms:
- DecodeImagePIL: # load image
img_mode: RGB
- ARLabelEncode: # Class handling label
- RecTVResize:
image_shape: [64, 256]
padding: False
- 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: 2