first commit

configs/rec/rec_svtrnet_ch.yml

@@ -0,0 +1,156 @@
+Global:
+  use_gpu: true
+  epoch_num: 100
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/svtr_ch_all/
+  save_epoch_step: 10
+  eval_batch_step:
+  - 0
+  - 2000
+  cal_metric_during_train: true
+  pretrained_model: null
+  checkpoints: null
+  save_inference_dir: null
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: false
+  use_space_char: true
+  save_res_path: ./output/rec/predicts_svtr_tiny_ch_all.txt
+  d2s_train_image_shape: [3, 32, 320]
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.99
+  epsilon: 1.0e-08
+  weight_decay: 0.05
+  no_weight_decay_name: norm pos_embed
+  one_dim_param_no_weight_decay: true
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 2
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform: null
+  Backbone:
+    name: SVTRNet
+    img_size:
+    - 32
+    - 320
+    out_char_num: 40 # W//4 or W//8 or W/12
+    out_channels: 96
+    patch_merging: Conv
+    embed_dim:
+    - 64
+    - 128
+    - 256
+    depth:
+    - 3
+    - 6
+    - 3
+    num_heads:
+    - 2
+    - 4
+    - 8
+    mixer:
+    - Local
+    - Local
+    - Local
+    - Local
+    - Local
+    - Local
+    - Global
+    - Global
+    - Global
+    - Global
+    - Global
+    - Global
+    local_mixer:
+    - - 7
+      - 11
+    - - 7
+      - 11
+    - - 7
+      - 11
+    last_stage: true
+    prenorm: false
+  Neck:
+    name: SequenceEncoder
+    encoder_type: reshape
+  Head:
+    name: CTCHead
+Loss:
+  name: CTCLoss
+PostProcess:
+  name: CTCLabelDecode
+Metric:
+  name: RecMetric
+  main_indicator: acc
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/train_list.txt
+    ext_op_transform_idx: 1
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape:
+        - 32
+        - 320
+        - 3
+    - RecAug: null
+    - CTCLabelEncode: null
+    - SVTRRecResizeImg:
+        image_shape:
+        - 3
+        - 32
+        - 320
+        padding: true
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: true
+    batch_size_per_card: 256
+    drop_last: true
+    num_workers: 8
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - CTCLabelEncode: null
+    - SVTRRecResizeImg:
+        image_shape:
+        - 3
+        - 32
+        - 320
+        padding: true
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label
+        - length
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 256
+    num_workers: 2
+profiler_options: null