| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153 |
- Global:
- device: gpu
- epoch_num: 100
- log_smooth_window: 20
- print_batch_step: 10
- output_dir: ./output/rec/ch/svtrv2_smtr_gtc_rctc_ch
- save_epoch_step: [15, 1]
- # evaluation is run every 2000 iterations
- eval_batch_step: [0, 2000]
- eval_epoch_step: [0, 1]
- cal_metric_during_train: False
- pretrained_model:
- # ./output/rec/u14m_filter/svtrv2_rctc/best.pth
- checkpoints:
- use_tensorboard: false
- infer_img:
- # for data or label process
- character_dict_path: &character_dict_path ./tools/utils/ppocr_keys_v1.txt # ch
- max_text_length: &max_text_length 25
- use_space_char: &use_space_char False
- save_res_path: ./output/rec/ch/predicts_svtrv2_smtr_gtc_rctc_ch.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: 5
- cycle_momentum: False
- Architecture:
- model_type: rec
- algorithm: SVTRv2
- in_channels: 3
- Transform:
- Encoder:
- name: SVTRv2LNConvTwo33
- use_pos_embed: False
- dims: [128, 256, 384]
- depths: [6, 6, 6]
- num_heads: [4, 8, 12]
- mixer: [['Conv','Conv','Conv','Conv','Conv','Conv'],['Conv','Conv','FGlobal','Global','Global','Global'],['Global','Global','Global','Global','Global','Global']]
- local_k: [[5, 5], [5, 5], [-1, -1]]
- sub_k: [[1, 1], [2, 1], [-1, -1]]
- last_stage: false
- feat2d: True
- Decoder:
- name: GTCDecoder
- infer_gtc: True
- detach: False
- gtc_decoder:
- name: SMTRDecoder
- num_layer: 1
- ds: True
- max_len: *max_text_length
- next_mode: &next True
- sub_str_len: &subsl 5
- ctc_decoder:
- name: RCTCDecoder
- Loss:
- name: GTCLoss
- ctc_weight: 0.1
- gtc_loss:
- name: SMTRLoss
- PostProcess:
- name: GTCLabelDecode
- gtc_label_decode:
- name: SMTRLabelDecode
- next_mode: *next
- character_dict_path: *character_dict_path
- use_space_char: *use_space_char
- Metric:
- name: RecGTCMetric
- main_indicator: acc
- # is_filter: True
- Train:
- dataset:
- name: RatioDataSetTVResize
- ds_width: True
- padding: false
- data_dir_list: ['../benchmark_bctr/benchmark_bctr_train/document_train',
- '../benchmark_bctr/benchmark_bctr_train/handwriting_train',
- '../benchmark_bctr/benchmark_bctr_train/scene_train',
- '../benchmark_bctr/benchmark_bctr_train/web_train'
- ]
- transforms:
- - DecodeImagePIL: # load image
- img_mode: RGB
- - PARSeqAugPIL:
- - GTCLabelEncode: # Class handling label
- gtc_label_encode:
- name: SMTRLabelEncode
- sub_str_len: *subsl
- character_dict_path: *character_dict_path
- use_space_char: *use_space_char
- max_text_length: *max_text_length
- - KeepKeys:
- keep_keys: ['image', 'label', 'label_subs', 'label_next', 'length_subs',
- 'label_subs_pre', 'label_next_pre', 'length_subs_pre', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
- 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: *bs
- drop_last: True
- max_ratio: &max_ratio 8
- num_workers: 4
- Eval:
- dataset:
- name: RatioDataSetTVResize
- ds_width: True
- padding: False
- data_dir_list: ['../benchmark_bctr/benchmark_bctr_test/scene_test']
- transforms:
- - DecodeImagePIL: # load image
- img_mode: RGB
- - GTCLabelEncode: # Class handling label
- gtc_label_encode:
- name: ARLabelEncode
- character_dict_path: *character_dict_path
- use_space_char: *use_space_char
- max_text_length: *max_text_length
- - KeepKeys:
- keep_keys: ['image', 'label', 'length', 'ctc_label', 'ctc_length'] # dataloader will return list in this order
- 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
- fix_bs: false
- divided_factor: [4, 16] # w, h
- is_training: False
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: *bs
- max_ratio: *max_ratio
- num_workers: 4
|
