resnet34_distill_resnet18_dkd.yaml 3.6 KB
Newer Older
wc晨曦's avatar
wc晨曦 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: "./output/"
  device: "gpu"
  save_interval: 1
  eval_during_train: True
  eval_interval: 1
  epochs: 100
  print_batch_step: 10
  use_visualdl: False
  # used for static mode and model export
  image_shape: [3, 224, 224]
  save_inference_dir: "./inference"

G
gaotingquan 已提交
17 18 19 20 21 22 23 24 25 26 27 28

# mixed precision
AMP:
  use_amp: False
  use_fp16_test: False
  scale_loss: 128.0
  use_dynamic_loss_scaling: True
  use_promote: False
  # O1: mixed fp16, O2: pure fp16
  level: O1


wc晨曦's avatar
wc晨曦 已提交
29 30 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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
# model architecture
Arch:
  name: "DistillationModel"
  # 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
  models:
    - Teacher:
        name: ResNet34
        pretrained: True

    - Student:
        name: ResNet18
        pretrained: False

  infer_model_name: "Student"


# loss function config for traing/eval process
Loss:
  Train:
    - DistillationGTCELoss:
        weight: 1.0
        model_names: ["Student"]
    - DistillationDKDLoss:
        weight: 1.0
        model_name_pairs: [["Student", "Teacher"]]
        temperature: 1
        alpha: 1.0
        beta: 1.0
  Eval:
    - CELoss:
        weight: 1.0
        

Optimizer:
  name: Momentum
  momentum: 0.9
  weight_decay: 1e-4
  lr:
    name: MultiStepDecay
    learning_rate: 0.2
    milestones: [30, 60, 90]
    step_each_epoch: 1
    gamma: 0.1


# data loader for train and eval
DataLoader:
  Train:
    dataset:
        name: ImageNetDataset
        image_root: "./dataset/ILSVRC2012/"
        cls_label_path: "./dataset/ILSVRC2012/train_list.txt"
        transform_ops:
          - DecodeImage:
              to_rgb: True
              channel_first: False
          - RandCropImage:
              size: 224
          - RandFlipImage:
              flip_code: 1
          - NormalizeImage:
              scale: 0.00392157
              mean: [0.485, 0.456, 0.406]
              std: [0.229, 0.224, 0.225]
              order: ''

    sampler:
        name: DistributedBatchSampler
        batch_size: 128
        drop_last: False
        shuffle: True
    loader:
        num_workers: 8
        use_shared_memory: True

  Eval:
    dataset: 
        name: ImageNetDataset
        image_root: "./dataset/ILSVRC2012/"
        cls_label_path: "./dataset/ILSVRC2012/val_list.txt"
        transform_ops:
          - DecodeImage:
              to_rgb: True
              channel_first: False
          - ResizeImage:
              resize_short: 256
          - CropImage:
              size: 224
          - NormalizeImage:
              scale: 0.00392157
              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:
  infer_imgs: "docs/images/inference_deployment/whl_demo.jpg"
  batch_size: 10
  transforms:
      - DecodeImage:
          to_rgb: True
          channel_first: False
      - ResizeImage:
          resize_short: 256
      - CropImage:
          size: 224
      - NormalizeImage:
          scale: 1.0/255.0
          mean: [0.485, 0.456, 0.406]
          std: [0.229, 0.224, 0.225]
          order: ''
      - ToCHWImage:
  PostProcess:
littletomatodonkey's avatar
littletomatodonkey 已提交
154
    name: Topk
wc晨曦's avatar
wc晨曦 已提交
155 156 157 158 159 160 161 162 163 164 165 166
    topk: 5
    class_id_map_file: "ppcls/utils/imagenet1k_label_list.txt"

Metric:
    Train:
    - DistillationTopkAcc:
        model_key: "Student"
        topk: [1, 5]
    Eval:
    - DistillationTopkAcc:
        model_key: "Student"
        topk: [1, 5]