PaddleOCR/configs/rec/rec_resnet_stn_bilstm_att.yml

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