GeneralRecognition_PPLCNet_x2_5_binary.yaml 3.3 KB
Newer Older
S
stephon 已提交
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
# 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
  eval_mode: retrieval
  use_dali: False
  to_static: False

  #feature postprocess
  feature_normalize: False
  feature_binarize: "sign"

# model architecture
Arch:
  name: RecModel
  infer_output_key: features
  infer_add_softmax: False

  Backbone:
S
stephon 已提交
31
    name: PPLCNet_x2_5_Tanh
S
stephon 已提交
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
    pretrained: True
    use_ssld: True
    class_num: 512
  Head:
    name: FC
    embedding_size: &embedding_size 512
    class_num: &n_class 185341

# loss function config for traing/eval process
Loss:
  Train:
    - DSHSDLoss:
        weight: 1.0
        n_class: *n_class
        bit: *embedding_size
        alpha: 0.1
  Eval:
    - DSHSDLoss:
        weight: 1.0
        n_class: *n_class
        bit: *embedding_size
        alpha: 0.1

Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Cosine
    learning_rate: 0.04
    warmup_epoch: 5
  regularizer:
    name: 'L2'
    coeff: 0.00001


# data loader for train and eval
DataLoader:
  Train:
    dataset:
      name: ImageNetDataset
      image_root: ./dataset/all_data
      cls_label_path: ./dataset/all_data/train_reg_all_data.txt
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - RandCropImage:
            size: 224
        - 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: ''

    sampler:
      name: DistributedBatchSampler
      batch_size: 256
      drop_last: False
      shuffle: True
    loader:
      num_workers: 4
      use_shared_memory: True

  Eval:
    Query:
      dataset: 
        name: VeriWild
        image_root: ./dataset/Aliproduct/
        cls_label_path: ./dataset/Aliproduct/val_list.txt
        transform_ops:
          - DecodeImage:
              to_rgb: True
              channel_first: False
          - ResizeImage:
              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

    Gallery:
      dataset: 
        name: VeriWild
        image_root: ./dataset/Aliproduct/
        cls_label_path: ./dataset/Aliproduct/val_list.txt
        transform_ops:
          - DecodeImage:
              to_rgb: True
              channel_first: False
          - ResizeImage:
              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

Metric:
  Eval:
    - Recallk:
        topk: [1, 5]