| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103 |
- Global:
- use_gpu: True
- epoch_num: 21
- log_smooth_window: 20
- print_batch_step: 10
- save_model_dir: ./output/rec/nrtr/
- save_epoch_step: 1
- # evaluation is run every 2000 iterations
- 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: ppocr/utils/EN_symbol_dict.txt
- max_text_length: 25
- infer_mode: False
- use_space_char: False
- save_res_path: ./output/rec/predicts_nrtr.txt
- Optimizer:
- name: Adam
- beta1: 0.9
- beta2: 0.99
- clip_norm: 5.0
- lr:
- name: Cosine
- learning_rate: 0.0005
- warmup_epoch: 2
- regularizer:
- name: 'L2'
- factor: 0.
- Architecture:
- model_type: rec
- algorithm: NRTR
- in_channels: 1
- Transform:
- Backbone:
- name: MTB
- cnn_num: 2
- Head:
- name: Transformer
- d_model: 512
- num_encoder_layers: 6
- beam_size: -1 # When Beam size is greater than 0, it means to use beam search when evaluation.
-
- Loss:
- name: CELoss
- smoothing: True
- PostProcess:
- name: NRTRLabelDecode
- Metric:
- name: RecMetric
- main_indicator: acc
- Train:
- dataset:
- name: SimpleDataSet
- data_dir: ./train_data/ic15_data/
- label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - NRTRLabelEncode: # Class handling label
- - GrayRecResizeImg:
- image_shape: [100, 32]
- resize_type: PIL # PIL or OpenCV
- - 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: SimpleDataSet
- data_dir: ./train_data/ic15_data
- label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
- transforms:
- - DecodeImage: # load image
- img_mode: BGR
- channel_first: False
- - NRTRLabelEncode: # Class handling label
- - GrayRecResizeImg:
- image_shape: [100, 32]
- resize_type: PIL # PIL or OpenCV
- - 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: 4
- use_shared_memory: False
|
