| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110 |
- Global:
- device: gpu
- epoch_num: 20
- log_smooth_window: 20
- print_batch_step: 10
- output_dir: ./output/rec/u14m_filter/vit_base_mgpstr_only_char/
- eval_epoch_step: [0, 1]
- eval_batch_step: [0, 500]
- cal_metric_during_train: False
- 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
- use_amp: True
- save_res_path: ./output/rec/u14m_filter/predicts_vit_mgpstr_only_char.txt
- grad_clip_val: 5
- Optimizer:
- name: Adam
- lr: 0.000325 # 4gpus 128bs/gpu
- weight_decay: 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: MGPSTR
- Transform:
- Encoder:
- name: ViT
- img_size: [32,128]
- patch_size: [4, 4]
- embed_dim: 1024
- depth: 24
- num_heads: 16
- mlp_ratio: 4
- qkv_bias: True
- Decoder:
- name: MGPDecoder
- only_char: &only_char True
- Loss:
- name: MGPLoss
- only_char: *only_char
- PostProcess:
- name: MPGLabelDecode
- character_dict_path: *character_dict_path
- use_space_char: *use_space_char
- only_char: *only_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:
- - MGPLabelEncode: # Class handling label
- character_dict_path: *character_dict_path
- use_space_char: *use_space_char
- max_text_length: *max_text_length
- only_char: *only_char
- - RecTVResize:
- image_shape: [32, 128]
- padding: False
- - KeepKeys:
- keep_keys: ['image', 'char_label', 'length'] # dataloader will return list in this order
- loader:
- shuffle: True
- batch_size_per_card: 128
- drop_last: True
- num_workers: 4
- Eval:
- dataset:
- name: LMDBDataSet
- data_dir: ../evaluation/
- transforms:
- - DecodeImagePIL: # load image
- img_mode: RGB
- - MGPLabelEncode: # Class handling label
- character_dict_path: *character_dict_path
- use_space_char: *use_space_char
- max_text_length: *max_text_length
- only_char: *only_char
- - RecTVResize:
- image_shape: [32, 128]
- padding: False
- - KeepKeys:
- keep_keys: ['image', 'char_label', 'length'] # dataloader will return list in this order
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 256
- num_workers: 2
|
