| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101 |
- Global:
- use_gpu: False
- epoch_num: 10
- log_smooth_window: 20
- print_batch_step: 1
- save_model_dir: output/rec/my_rec_chinese_lite/
- save_epoch_step: 5
- # evaluation is run every 2000 iterations
- eval_batch_step: [0, 150000]
- # if pretrained_model is saved in static mode, load_static_weights must set to True
- cal_metric_during_train: True
- pretrained_model: output/rec/my_rec_chinese_lite/best_accuracy
- checkpoints:
- save_inference_dir:
- use_visualdl: False
- infer_img: doc/imgs_words_en/word_10.png
- # for data or label process
- character_dict_path: ppocr/utils/ppocr_keys_v1.txt
- character_type: ch
- max_text_length: 128
- infer_mode: False
- use_space_char: True
- distributed: True
- Optimizer:
- name: Adam
- beta1: 0.9
- beta2: 0.999
- lr:
- name: Cosine
- learning_rate: 0.0000001
- regularizer:
- name: 'L2'
- factor: 0.00001
- Architecture:
- model_type: rec
- algorithm: CRNN
- Transform:
- Backbone:
- name: MobileNetV3
- scale: 0.5
- model_name: small
- small_stride: [1, 2, 2, 2]
- Neck:
- name: SequenceEncoder
- encoder_type: rnn
- hidden_size: 48
- Head:
- name: CTCHead
- fc_decay: 0.00001
- Loss:
- name: CTCLoss
- PostProcess:
- name: CTCLabelDecode
- Metric:
- name: RecMetric
- main_indicator: acc
- Train:
- dataset:
- name: SimpleDataSet
- data_dir: train_data/bidi_data/orgs_data/
- label_file_list: ["./train_data/bidi_data/orgs_data/rec_gt_train.txt"]
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - CTCLabelEncode: # Class handling label
- - RecResizeImg:
- image_shape: [3, 32, 1000]
- - KeepKeys:
- keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
- loader:
- shuffle: True
- batch_size_per_card: 100
- drop_last: True
- num_workers: 16
- Eval:
- dataset:
- name: SimpleDataSet
- data_dir: train_data/bidi_data/orgs_data/
- label_file_list: ["./train_data/bidi_data/orgs_data/rec_gt_test.txt"]
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - CTCLabelEncode: # Class handling label
- - RecResizeImg:
- image_shape: [3, 32, 1000]
- - KeepKeys:
- keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
- loader:
- shuffle: False
- drop_last: False
- batch_size_per_card: 100
- num_workers: 16
|
