| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102 |
- Global:
- device: gpu
- epoch_num: 20
- log_smooth_window: 20
- print_batch_step: 10
- output_dir: ./output/rec/u14m_filter/resnet31_robustscanner
- 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: &max_text_length 25
- use_space_char: False
- save_res_path: ./output/rec/u14m_filter/predicts_resnet31_robustscanner.txt
- use_amp: True
- Optimizer:
- name: Adam
- lr: 0.00065 # for 4gpus bs256/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: RobustScanner
- in_channels: 3
- Transform:
- Encoder:
- name: ResNet31
- # init_type: KaimingNormal
- Decoder:
- name: RobustScannerDecoder
- enc_outchannles: 128
- hybrid_dec_rnn_layers: 2
- hybrid_dec_dropout: 0
- position_dec_rnn_layers: 2
- mask: True
- encode_value: False
- max_text_length: *max_text_length
- Loss:
- name: ARLoss
- PostProcess:
- name: ARLabelDecode
- Metric:
- name: RecMetric
- main_indicator: acc
- is_filter: True
- Train:
- dataset:
- name: LMDBDataSet
- data_dir: ../Union14M-L-LMDB-Filtered
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - PARSeqAug:
- - ARLabelEncode: # Class handling label
- - RobustScannerRecResizeImg:
- image_shape: [3, 48, 48, 160]
- width_downsample_ratio: 0.25
- max_text_length: *max_text_length
- - KeepKeys:
- keep_keys: ['image', 'label', 'length', 'valid_ratio'] # dataloader will return list in this order
- loader:
- shuffle: True
- batch_size_per_card: 256
- drop_last: True
- num_workers: 4
- Eval:
- dataset:
- name: LMDBDataSet
- data_dir: ../evaluation
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - ARLabelEncode: # Class handling label
- - RobustScannerRecResizeImg:
- image_shape: [3, 48, 48, 160]
- width_downsample_ratio: 0.25
- max_text_length: *max_text_length
- - KeepKeys:
- keep_keys: ['image', 'label', 'length', 'valid_ratio'] # dataloader will return list in this order
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 128
- num_workers: 2
|
