# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/ 
  device: gpu
  save_interval: 50
  # train_epoch_iter_two_samples
  train_mode: iter_two_samples
  eval_during_train: False
  eval_interval: 1
  epochs: 200
  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


# model architecture
Arch:
  name: MoCo_V2
  backbone:
    name: ResNet50
    stop_layer_name: AvgPool2D
  neck:
    name: NonLinearNeck
    in_channels: 2048
    hid_channels: 2048
    out_channels: 128
  head:
    name: ContrastiveHead
    temperature: 0.2

# loss function config 
Loss:
  Train:
    - CELoss:
        weight: 1.0


Optimizer:
  name: Momentum
  momentum: 0.9
  weight_decay: 0.0001
  lr:
    name: Cosine
    learning_rate: 0.03
    T_max: 200

    

# data loader for train 
DataLoader:
  Train:
    dataset:
      name: MoCoImageNetDataset
      image_root: ./dataset/ILSVRC2012/
      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
      return_label: False
      return_two_sample: True
      transform_ops:
        - DecodeImage:
            to_rgb: True,
            channel_first: False
        - RandomResizedCrop:
            size: 224
            scale: [0.2, 1.]
      view_trans1:
        - RandomApply:
            transforms:
              - RawColorJitter:
                  brightness: 0.4
                  contrast: 0.4
                  saturation: 0.4
                  hue: 0.1
            p: 0.8
        - RandomGrayscale:
            p: 0.2
        - RandomApply:
            transforms:
              - GaussianBlur:
                  sigma: [0.1, 2.0]
            p: 0.5
        - RandomHorizontalFlip:
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - ToCHWImage:
      view_trans2:
        - RandomApply:
            transforms:
              - RawColorJitter:
                  brightness: 0.4
                  contrast: 0.4
                  saturation: 0.4
                  hue: 0.1
            p: 0.8
        - RandomGrayscale:
            p: 0.2
        - RandomApply:
            transforms:
              - GaussianBlur:
                  sigma: [0.1, 2.0]
            p: 0.5
        - RandomHorizontalFlip:
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - ToCHWImage:
    sampler:
      name: DistributedBatchSampler
      batch_size: 64
      drop_last: True
      shuffle: True
    loader:
      num_workers: 4
      use_shared_memory: True

Metric:
  Train:
    - TopkAcc:
        topk: [1, 5]