PaddleOCR/configs/rec/rec_r50_fpn_srn.yml

108 lines
2.4 KiB
YAML

Global:
use_gpu: True
epoch_num: 72
log_smooth_window: 20
print_batch_step: 5
save_model_dir: ./output/rec/srn_new
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [0, 5000]
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:
character_type: en
max_text_length: 25
num_heads: 8
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_srn.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
clip_norm: 10.0
lr:
learning_rate: 0.0001
Architecture:
model_type: rec
algorithm: SRN
in_channels: 1
Transform:
Backbone:
name: ResNetFPN
Head:
name: SRNHead
max_text_length: 25
num_heads: 8
num_encoder_TUs: 2
num_decoder_TUs: 4
hidden_dims: 512
Loss:
name: SRNLoss
PostProcess:
name: SRNLabelDecode
Metric:
name: RecMetric
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
- SRNLabelEncode: # Class handling label
- SRNRecResizeImg:
image_shape: [1, 64, 256]
- KeepKeys:
keep_keys: ['image',
'label',
'length',
'encoder_word_pos',
'gsrm_word_pos',
'gsrm_slf_attn_bias1',
'gsrm_slf_attn_bias2'] # dataloader will return list in this order
loader:
shuffle: False
batch_size_per_card: 64
drop_last: False
num_workers: 4
Eval:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/validation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- SRNLabelEncode: # Class handling label
- SRNRecResizeImg:
image_shape: [1, 64, 256]
- KeepKeys:
keep_keys: ['image',
'label',
'length',
'encoder_word_pos',
'gsrm_word_pos',
'gsrm_slf_attn_bias1',
'gsrm_slf_attn_bias2']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 32
num_workers: 4