PPLCNet_x1_0_distillation.yaml 3.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29
# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/
  device: gpu
  save_interval: 1
  eval_during_train: True
  eval_interval: 1
  epochs: 30
  print_batch_step: 10
  use_visualdl: False
  # used for static mode and model export
  image_shape: [3, 224, 224]
  save_inference_dir: ./inference
  # training model under @to_static
  to_static: False
  use_dali: False

# model architecture
Arch:
  name: "DistillationModel"
  class_num: &class_num 10
  # if not null, its lengths should be same as models
  pretrained_list:
  # if not null, its lengths should be same as models
  freeze_params_list:
  - True
  - False
30
  use_sync_bn: True
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74
  models:
    - Teacher:
        name: ResNet101_vd
        class_num: *class_num
    - Student:
        name: PPLCNet_x1_0
        class_num: *class_num
        pretrained: True
        use_ssld: True
        stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
        lr_mult_list : [0.0, 0.4, 0.4, 0.8, 0.8, 1.0]
        

  infer_model_name: "Student"
 
# loss function config for traing/eval process
Loss:
  Train:
    - DistillationDMLLoss:
        weight: 1.0
        model_name_pairs:
        - ["Student", "Teacher"]
  Eval:
    - CELoss:
        weight: 1.0


Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Cosine
    learning_rate: 0.8
    warmup_epoch: 5
  regularizer:
    name: 'L2'
    coeff: 0.00003


# data loader for train and eval
DataLoader:
  Train:
    dataset:
      name: ImageNetDataset
75 76
      image_root: ./dataset/language_classification/
      cls_label_path: ./dataset/language_classification/train_list_for_distill.txt
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [160, 80]
        - RandFlipImage:
            flip_code: 1
        - TimmAutoAugment:
            prob: 1.0
            config_str: rand-m9-mstd0.5-inc1
            interpolation: bicubic
            img_size: [160, 80]
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - RandomErasing:
            EPSILON: 1.0
            sl: 0.02
            sh: 1.0/3.0
            r1: 0.3
            attempt: 10
            use_log_aspect: True
            mode: pixel
    sampler:
      name: DistributedBatchSampler
      batch_size: 256
      drop_last: False
      shuffle: True
    loader:
      num_workers: 4
      use_shared_memory: True

  Eval:
    dataset: 
      name: ImageNetDataset
115 116
      image_root: ./dataset/language_classification/
      cls_label_path: ./dataset/language_classification/test_list.txt
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [160, 80]
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
    sampler:
      name: DistributedBatchSampler
      batch_size: 64
      drop_last: False
      shuffle: False
    loader:
      num_workers: 4
      use_shared_memory: True

Infer:
138
  infer_imgs: deploy/images/PULC/language_classification/word_35404.png
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
  batch_size: 10
  transforms:
    - DecodeImage:
        to_rgb: True
        channel_first: False
    - ResizeImage:
        size: [160, 80]
    - NormalizeImage:
        scale: 1.0/255.0
        mean: [0.485, 0.456, 0.406]
        std: [0.229, 0.224, 0.225]
        order: ''
    - ToCHWImage:
  PostProcess:
    name: Topk
    topk: 2
155
    class_id_map_file: ppcls/utils/PULC/language_classification_label_list.txt
156 157 158 159 160 161 162 163 164

Metric:
    Train:
    - DistillationTopkAcc:
        model_key: "Student"
        topk: [1, 2]
    Eval:
    - TopkAcc:
        topk: [1, 2]