| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117 |
- Global:
- use_gpu: True
- epoch_num: 20
- log_smooth_window: 20
- print_batch_step: 10
- save_model_dir: ./output/rec/svtr/
- save_epoch_step: 1
- # evaluation is run every 2000 iterations after the 0th iteration
- eval_batch_step: [0, 2000]
- cal_metric_during_train: True
- pretrained_model:
- checkpoints:
- save_inference_dir:
- use_visualdl: False
- infer_img: doc/imgs_words_en/word_10.png
- # for data or label process
- character_dict_path:
- character_type: en
- max_text_length: 25
- infer_mode: False
- use_space_char: False
- save_res_path: ./output/rec/predicts_svtr_tiny.txt
- Optimizer:
- name: AdamW
- beta1: 0.9
- beta2: 0.99
- epsilon: 1.e-8
- weight_decay: 0.05
- no_weight_decay_name: norm pos_embed
- one_dim_param_no_weight_decay: True
- lr:
- name: Cosine
- learning_rate: 0.0005
- warmup_epoch: 2
- Architecture:
- model_type: rec
- algorithm: SVTR
- Transform:
- name: STN_ON
- tps_inputsize: [32, 64]
- tps_outputsize: [32, 100]
- num_control_points: 20
- tps_margins: [0.05,0.05]
- stn_activation: none
- Backbone:
- name: SVTRNet
- img_size: [32, 100]
- out_char_num: 25 # W//4 or W//8 or W/12
- out_channels: 192
- patch_merging: 'Conv'
- embed_dim: [64, 128, 256]
- depth: [3, 6, 3]
- num_heads: [2, 4, 8]
- mixer: ['Local','Local','Local','Local','Local','Local','Global','Global','Global','Global','Global','Global']
- local_mixer: [[7, 11], [7, 11], [7, 11]]
- last_stage: True
- prenorm: False
- Neck:
- name: SequenceEncoder
- encoder_type: reshape
- Head:
- name: CTCHead
- Loss:
- name: CTCLoss
- PostProcess:
- name: CTCLabelDecode
- 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
- - SVTRRecAug:
- aug_type: 0 # or 1
- - CTCLabelEncode: # Class handling label
- - SVTRRecResizeImg:
- image_shape: [3, 64, 256]
- padding: False
- - KeepKeys:
- keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
- loader:
- shuffle: True
- batch_size_per_card: 512
- drop_last: True
- num_workers: 8
- Eval:
- dataset:
- name: LMDBDataSet
- data_dir: ./train_data/data_lmdb_release/evaluation/
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - CTCLabelEncode: # Class handling label
- - SVTRRecResizeImg:
- image_shape: [3, 64, 256]
- 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
|
