first commit

configs/rec/PP-OCRv4/PP-OCRv4_mobile_rec_distillation.yml

@@ -0,0 +1,231 @@
+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_dkd_400w_svtr_ctc_lcnet_blank_dkd0.1/
+  save_epoch_step: 40
+  eval_batch_step:
+  - 0
+  - 2000
+  cal_metric_during_train: true
+  pretrained_model: null
+  checkpoints: ./output/rec_dkd_400w_svtr_ctc_lcnet_blank_dkd0.1/latest
+  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: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+Architecture:
+  model_type: rec
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained: 
+      freeze_params: true
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR
+      Transform: null
+      Backbone:
+        name: SVTRNet
+        img_size:
+        - 48
+        - 320
+        out_char_num: 40
+        out_channels: 192
+        patch_merging: Conv
+        embed_dim:
+        - 64
+        - 128
+        - 256
+        depth:
+        - 3
+        - 6
+        - 3
+        num_heads:
+        - 2
+        - 4
+        - 8
+        mixer:
+        - Conv
+        - Conv
+        - Conv
+        - Conv
+        - Conv
+        - Conv
+        - Global
+        - Global
+        - Global
+        - Global
+        - Global
+        - Global
+        local_mixer:
+        - - 5
+          - 5
+        - - 5
+          - 5
+        - - 5
+          - 5
+        last_stage: false
+        prenorm: true
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 120
+                depth: 2
+                hidden_dims: 120
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              max_text_length: *max_text_length
+    Student:
+      pretrained: 
+      freeze_params: false
+      return_all_feats: true
+      model_type: rec
+      algorithm: SVTR
+      Transform: null
+      Backbone:
+        name: PPLCNetV3
+        scale: 0.95
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 120
+                depth: 2
+                hidden_dims: 120
+                kernel_size: [1, 3]
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - NRTRHead:
+              nrtr_dim: 384
+              max_text_length: *max_text_length
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDKDLoss:
+      weight: 0.1
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+      multi_head: true
+      alpha: 1.0
+      beta: 2.0
+      dis_head: gtc
+      name: dkd
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillationNRTRLoss:
+      weight: 1.0
+      smoothing: false
+      model_name_list:
+      - Student
+      key: head_out
+      multi_head: true
+  - DistillCTCLogits:
+      weight: 1.0
+      reduction: mean
+      model_name_pairs:
+      - - Student
+        - Teacher
+      key: head_out
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name:
+  - Student
+  key: head_out
+  multi_head: true
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: Student
+  ignore_space: false
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list:
+    - ./train_data/train_list.txt
+    ratio_list:
+    - 1.0
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecAug:
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 8
+    use_shared_memory: true
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+        gtc_encode: NRTRLabelEncode
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_gtc
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4
+profiler_options: null