# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/
  device: gpu
  save_interval: 1
  eval_during_train: True
  eval_interval: 1
  epochs: 30
  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_sync_bn: True

# model architecture
Arch:
  name: "DistillationModel"
  class_num: &class_num 10
  # 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: ResNet101_vd
        class_num: *class_num
    - Student:
        name: PPLCNet_x1_0
        class_num: *class_num
        pretrained: True
        use_ssld: True
        stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
        lr_mult_list : [0.0, 0.4, 0.4, 0.8, 0.8, 1.0]
        

  infer_model_name: "Student"
 
# loss function config for traing/eval process
Loss:
  Train:
    - DistillationDMLLoss:
        weight: 1.0
        model_name_pairs:
        - ["Student", "Teacher"]
  Eval:
    - CELoss:
        weight: 1.0


Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Cosine
    learning_rate: 0.8
    warmup_epoch: 5
  regularizer:
    name: 'L2'
    coeff: 0.00003


# data loader for train and eval
DataLoader:
  Train:
    dataset:
      name: ImageNetDataset
      image_root: ./dataset/language_classification/
      cls_label_path: ./dataset/language_classification/train_list_for_distill.txt
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [160, 80]
        - RandFlipImage:
            flip_code: 1
        - TimmAutoAugment:
            prob: 1.0
            config_str: rand-m9-mstd0.5-inc1
            interpolation: bicubic
            img_size: [160, 80]
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - RandomErasing:
            EPSILON: 1.0
            sl: 0.02
            sh: 1.0/3.0
            r1: 0.3
            attempt: 10
            use_log_aspect: True
            mode: pixel
    sampler:
      name: DistributedBatchSampler
      batch_size: 256
      drop_last: False
      shuffle: True
    loader:
      num_workers: 4
      use_shared_memory: True

  Eval:
    dataset: 
      name: ImageNetDataset
      image_root: ./dataset/language_classification/
      cls_label_path: ./dataset/language_classification/test_list.txt
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [160, 80]
        - 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

Infer:
  infer_imgs: deploy/images/PULC/language_classification/word_35404.png
  batch_size: 10
  transforms:
    - DecodeImage:
        to_rgb: True
        channel_first: False
    - ResizeImage:
        size: [160, 80]
    - 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: 2
    class_id_map_file: dataset/language_classification/label_list.txt

Metric:
    Train:
    - DistillationTopkAcc:
        model_key: "Student"
        topk: [1, 2]
    Eval:
    - TopkAcc:
        topk: [1, 2]