# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/r34_r18_mgd
  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
  to_static: False


# 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


# model architecture
Arch:
  name: "DistillationModel"
  class_num: &class_num 1000
  # 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
  infer_model_name: "Student"
  models:
    - Teacher:
        name: ResNet34
        class_num: *class_num
        pretrained: True
        return_patterns: &t_stages ["blocks[2]", "blocks[6]", "blocks[12]", "blocks[15]"]
    - Student:
        name: ResNet18
        class_num: *class_num
        pretrained: False
        return_patterns: &s_stages ["blocks[1]", "blocks[3]", "blocks[5]", "blocks[7]"]
 
# loss function config for traing/eval process
Loss:
  Train:
    - DistillationGTCELoss:
        weight: 1.0
        model_names: ["Student"]
    - DistillationPairLoss:
        weight: 1.0
        base_loss_name: MGDLoss
        model_name_pairs: [["Student", "Teacher"]]
        s_key: "blocks[7]"
        t_key: "blocks[15]"
        name: "loss_mgd"
        student_channels: 512
        teacher_channels: 512
  Eval:
    - CELoss:
        weight: 1.0

Optimizer:
  name: Momentum
  momentum: 0.9
  weight_decay: 1e-4
  lr:
    name: Piecewise
    learning_rate: 0.1
    decay_epochs: [30, 60, 90]
    values: [0.1, 0.01, 0.001, 0.0001]


# 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: 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: 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: 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: False
    loader:
      num_workers: 8
      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:
    name: Topk
    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]