| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112 |
- Global:
- use_gpu: True
- epoch_num: 20
- log_smooth_window: 20
- print_batch_step: 10
- save_model_dir: ./output/rec/svtr_cppd_base/
- 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_cppd_base.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 char_node_embed pos_node_embed char_pos_embed vis_pos_embed
- one_dim_param_no_weight_decay: True
- lr:
- name: Cosine
- learning_rate: 0.0005 # 4gpus 256bs
- warmup_epoch: 2
- Architecture:
- model_type: rec
- algorithm: CPPD
- Transform:
- Backbone:
- name: SVTRNet
- img_size: [32, 100]
- patch_merging: 'Conv'
- embed_dim: [128, 256, 384]
- depth: [6, 6, 4]
- 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: False
- prenorm: True
- Head:
- name: CPPDHead
- dim: 384
- vis_seq: 50
- num_layer: 3
- Loss:
- name: CPPDLoss
- ignore_index: &ignore_index 100 # must be greater than the number of character classes
- smoothing: True
- sideloss_weight: 1.0
- PostProcess:
- name: CPPDLabelDecode
- 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
- - CPPDLabelEncode: # Class handling label
- ignore_index: *ignore_index
- - SVTRRecResizeImg:
- image_shape: [3, 32, 100]
- padding: False
- - KeepKeys:
- keep_keys: ['image', 'label', 'label_node', 'length'] # dataloader will return list in this order
- loader:
- shuffle: True
- batch_size_per_card: 256
- 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
- - CPPDLabelEncode: # Class handling label
- ignore_index: *ignore_index
- - SVTRRecResizeImg:
- image_shape: [3, 32, 100]
- padding: False
- - KeepKeys:
- keep_keys: ['image', 'label', 'label_node','length'] # dataloader will return list in this order
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 256
- num_workers: 2
|
