Spaces:
Running
Running
| Global: | |
| device: gpu | |
| epoch_num: 20 | |
| log_smooth_window: 20 | |
| print_batch_step: 10 | |
| output_dir: ./output/rec/u14m_filter/svtr_base_ctc/ | |
| 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: &character_dict_path ./tools/utils/EN_symbol_dict.txt | |
| max_text_length: &max_text_length 25 | |
| use_space_char: &use_space_char False | |
| save_res_path: ./output/rec/u14m_filter/predicts_svtr_tiny.txt | |
| use_amp: True | |
| Optimizer: | |
| name: AdamW | |
| lr: 0.00065 # for 4gpus bs256/gpu | |
| weight_decay: 0.05 | |
| filter_bias_and_bn: True | |
| LRScheduler: | |
| name: OneCycleLR | |
| warmup_epoch: 1.5 # pct_start 0.075*20 = 1.5ep | |
| cycle_momentum: False | |
| Architecture: | |
| model_type: rec | |
| algorithm: SVTR | |
| Transform: | |
| Encoder: | |
| name: SVTRNet | |
| img_size: [32, 128] | |
| out_char_num: 32 | |
| out_channels: 256 | |
| patch_merging: 'Conv' | |
| embed_dim: [128, 256, 384] | |
| depth: [6, 6, 6] | |
| num_heads: [4, 8, 12] | |
| mixer: ['Conv','Conv','Conv','Conv','Conv','Conv', 'Conv','Conv', 'Global','Global','Global','Global','Global','Global','Global','Global','Global','Global'] | |
| local_mixer: [[5, 5], [5, 5], [5, 5]] | |
| last_stage: True | |
| prenorm: True | |
| Decoder: | |
| name: CTCDecoder | |
| Loss: | |
| name: CTCLoss | |
| zero_infinity: True | |
| PostProcess: | |
| name: CTCLabelDecode | |
| character_dict_path: | |
| use_space_char: | |
| Metric: | |
| name: RecMetric | |
| main_indicator: acc | |
| is_filter: True | |
| Train: | |
| dataset: | |
| name: LMDBDataSet | |
| data_dir: ../Union14M-L-LMDB-Filtered | |
| transforms: | |
| - DecodeImagePIL: # load image | |
| img_mode: RGB | |
| - PARSeqAugPIL: | |
| - CTCLabelEncode: # Class handling label | |
| character_dict_path: | |
| use_space_char: | |
| max_text_length: | |
| - RecTVResize: | |
| image_shape: [32, 128] | |
| padding: False | |
| - KeepKeys: | |
| keep_keys: ['image', 'label', 'length'] # 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: | |
| - DecodeImagePIL: # load image | |
| img_mode: RGB | |
| - CTCLabelEncode: # Class handling label | |
| character_dict_path: | |
| use_space_char: | |
| max_text_length: | |
| - RecTVResize: | |
| image_shape: [32, 128] | |
| 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 | |