| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122 |
- Global:
- use_gpu: True
- epoch_num: 240
- log_smooth_window: 20
- print_batch_step: 10
- save_model_dir: ./output/rec/can/
- save_epoch_step: 1
- # evaluation is run every 1105 iterations (1 epoch)(batch_size = 8)
- eval_batch_step: [0, 1105]
- cal_metric_during_train: True
- pretrained_model:
- checkpoints:
- save_inference_dir:
- use_visualdl: False
- infer_img: doc/datasets/crohme_demo/hme_00.jpg
- # for data or label process
- character_dict_path: ppocr/utils/dict/latex_symbol_dict.txt
- max_text_length: 36
- infer_mode: False
- use_space_char: False
- save_res_path: ./output/rec/predicts_can.txt
- Optimizer:
- name: Momentum
- momentum: 0.9
- clip_norm_global: 100.0
- lr:
- name: TwoStepCosine
- learning_rate: 0.01
- warmup_epoch: 1
- weight_decay: 0.0001
- Architecture:
- model_type: rec
- algorithm: CAN
- in_channels: 1
- Transform:
- Backbone:
- name: DenseNet
- growthRate: 24
- reduction: 0.5
- bottleneck: True
- use_dropout: True
- input_channel: 1
- Head:
- name: CANHead
- in_channel: 684
- out_channel: 111
- max_text_length: 36
- ratio: 16
- attdecoder:
- is_train: True
- input_size: 256
- hidden_size: 256
- encoder_out_channel: 684
- dropout: True
- dropout_ratio: 0.5
- word_num: 111
- counting_decoder_out_channel: 111
- attention:
- attention_dim: 512
- word_conv_kernel: 1
-
- Loss:
- name: CANLoss
- PostProcess:
- name: CANLabelDecode
- Metric:
- name: CANMetric
- main_indicator: exp_rate
- Train:
- dataset:
- name: SimpleDataSet
- data_dir: ./train_data/CROHME/training/images/
- label_file_list: ["./train_data/CROHME/training/labels.txt"]
- transforms:
- - DecodeImage:
- channel_first: False
- - NormalizeImage:
- mean: [0,0,0]
- std: [1,1,1]
- order: 'hwc'
- - GrayImageChannelFormat:
- inverse: True
- - CANLabelEncode:
- lower: False
- - KeepKeys:
- keep_keys: ['image', 'label']
- loader:
- shuffle: True
- batch_size_per_card: 8
- drop_last: False
- num_workers: 4
- collate_fn: DyMaskCollator
- Eval:
- dataset:
- name: SimpleDataSet
- data_dir: ./train_data/CROHME/evaluation/images/
- label_file_list: ["./train_data/CROHME/evaluation/labels.txt"]
- transforms:
- - DecodeImage:
- channel_first: False
- - NormalizeImage:
- mean: [0,0,0]
- std: [1,1,1]
- order: 'hwc'
- - GrayImageChannelFormat:
- inverse: True
- - CANLabelEncode:
- lower: False
- - KeepKeys:
- keep_keys: ['image', 'label']
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 1
- num_workers: 4
- collate_fn: DyMaskCollator
|
