Spaces:
Running
Running
| Global: | |
| device: gpu | |
| epoch_num: 20 | |
| log_smooth_window: 20 | |
| print_batch_step: 10 | |
| output_dir: ./output/rec/repsvtr_ch/ | |
| save_epoch_step: 1 | |
| # evaluation is run every 2000 iterations | |
| eval_epoch_step: [0, 1] | |
| eval_batch_step: [0, 500] | |
| cal_metric_during_train: True | |
| pretrained_model: ./openocr_repsvtr_ch.pth | |
| checkpoints: | |
| use_tensorboard: false | |
| infer_img: | |
| # for data or label process | |
| character_dict_path: &character_dict_path ./tools/utils/ppocr_keys_v1.txt | |
| max_text_length: &max_text_length 25 | |
| use_space_char: &use_space_char True | |
| save_res_path: ./output/rec/u14m_filter/predicts_svtrv2_ctc.txt | |
| use_amp: True | |
| project_name: resvtr_ctc_nosgm_ds | |
| 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: SVTRv2_mobile | |
| Transform: | |
| Encoder: | |
| name: RepSVTREncoder | |
| Decoder: | |
| name: CTCDecoder | |
| svtr_encoder: | |
| dims: 256 | |
| depth: 2 | |
| hidden_dims: 256 | |
| kernel_size: [1, 3] | |
| use_guide: True | |
| Loss: | |
| name: CTCLoss | |
| zero_infinity: True | |
| PostProcess: | |
| name: CTCLabelDecode | |
| character_dict_path: | |
| Metric: | |
| name: RecMetric | |
| main_indicator: acc | |
| ignore_space: False | |
| # is_filter: True | |
| Train: | |
| dataset: | |
| name: RatioDataSetTVResize | |
| ds_width: True | |
| padding: False | |
| base_shape: [[32, 32], [64, 32], [96, 32], [128, 32]] | |
| data_dir_list: ['../Union14M-L-LMDB-Filtered/filter_train_challenging', | |
| '../Union14M-L-LMDB-Filtered/filter_train_hard', | |
| '../Union14M-L-LMDB-Filtered/filter_train_medium', | |
| '../Union14M-L-LMDB-Filtered/filter_train_normal', | |
| '../Union14M-L-LMDB-Filtered/filter_train_easy', | |
| ] | |
| transforms: | |
| - DecodeImagePIL: # load image | |
| img_mode: RGB | |
| - PARSeqAugPIL: | |
| - CTCLabelEncode: # Class handling label | |
| character_dict_path: | |
| use_space_char: | |
| max_text_length: | |
| - KeepKeys: | |
| keep_keys: ['image', 'label', 'length'] | |
| sampler: | |
| name: RatioSampler | |
| scales: [[128, 32]] # w, h | |
| # divide_factor: to ensure the width and height dimensions can be devided by downsampling multiple | |
| first_bs: &bs 256 | |
| fix_bs: false | |
| divided_factor: [4, 16] # w, h | |
| is_training: True | |
| loader: | |
| shuffle: True | |
| batch_size_per_card: | |
| drop_last: True | |
| max_ratio: 4 | |
| num_workers: 4 | |
| Eval: | |
| dataset: | |
| name: LMDBDataSet | |
| data_dir: ../evaluation | |
| transforms: | |
| - DecodeImage: # load image | |
| img_mode: BGR | |
| - CTCLabelEncode: # Class handling label | |
| character_dict_path: | |
| use_space_char: | |
| max_text_length: | |
| - RecDynamicResize: | |
| image_shape: [48, 320] | |
| padding: False | |
| - KeepKeys: | |
| keep_keys: ['image', 'label', 'length'] | |
| loader: | |
| shuffle: False | |
| drop_last: False | |
| batch_size_per_card: 1 | |
| num_workers: 4 | |