PPLCNet_x1_0_Distillation.yaml 3.4 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 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154
# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output
  device: gpu
  save_interval: 1
  eval_during_train: True
  start_eval_epoch: 1
  eval_interval: 1
  epochs: 20
  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
  use_multilabel: True

# model architecture
Arch:
  name: "DistillationModel"
  class_num: &class_num 26
  # 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
  use_sync_bn: True
  models:
    - Teacher:
        name: ResNet101_vd
        class_num: *class_num
    - Student:
        name: PPLCNet_x1_0
        class_num: *class_num
        pretrained: True
        use_ssld: True

  infer_model_name: "Student"
 
# loss function config for traing/eval process
Loss:
  Train:
    - DistillationDMLLoss:
        weight: 1.0
        model_name_pairs:
        - ["Student", "Teacher"]
    - DistillationMultiLabelLoss:
        weight: 1.0
        weight_ratio: True
        model_names: ["Student"]
        size_sum: True
  Eval:
    - MultiLabelLoss:
        weight: 1.0
        weight_ratio: True
        size_sum: True

Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Cosine
    learning_rate: 0.01
    warmup_epoch: 5
  regularizer:
    name: 'L2'
    coeff: 0.0005


# data loader for train and eval
# data loader for train and eval
DataLoader:
  Train:
    dataset:
      name: MultiLabelDataset
      image_root: "dataset/attribute/data/"
      cls_label_path: "dataset/attribute/train_list.txt"
      label_ratio: True
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [192, 256]
        - TimmAutoAugment:
            prob: 0.0
            config_str: rand-m9-mstd0.5-inc1
            interpolation: bicubic
            img_size: [192, 256]
        - Padv2:
            size: [212, 276]
            pad_mode: 1
            fill_value: 0
        - RandomCropImage:
            size: [192, 256]
        - RandFlipImage:
            flip_code: 1
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - RandomErasing:
            EPSILON: 0.0
            sl: 0.02
            sh: 1.0/3.0
            r1: 0.3
            attempt: 10
            use_log_aspect: True
            mode: pixel
    sampler:
      name: DistributedBatchSampler
      batch_size: 64
      drop_last: True
      shuffle: True
    loader:
      num_workers: 4
      use_shared_memory: True
  Eval:
    dataset:
      name: MultiLabelDataset
      image_root: "dataset/attribute/data/"
      cls_label_path: "dataset/attribute/pa100k_val_list.txt"
      label_ratio: True
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [192, 256]
        - 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



Metric:
  Eval:
    - ATTRMetric: