# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/
  device: gpu
  save_interval: 5
  eval_during_train: True
  eval_interval: 1
  epochs: 10
  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

# 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: RecModel
  infer_output_key: features
  infer_add_softmax: False

  Backbone:
    name: CLIP_vit_large_patch14_224
    pretrained: True
    return_embed: True
    return_mean_embed: True 
  BackboneStopLayer:
    name: "flatten"
  Neck:
    name: FC
    embedding_size: 512
    class_num: 512
  Head:
    name: ArcMargin
    embedding_size: 512
    class_num: 192613
    margin: 0.2
    scale: 30

# loss function config for traing/eval process
Loss:
  Train:
    - CELoss:
        weight: 1.0
  Eval:
    - CELoss:
        weight: 1.0

Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Cosine
    learning_rate: 0.0025
    warmup_epoch: 1
  regularizer:
    name: "L2"
    coeff: 0.00002

# data loader for train and eval
DataLoader:
  Train:
    dataset:
      name: ImageNetDataset
      image_root: ./dataset/
      cls_label_path: ./dataset/train_reg_all_data_v2.txt
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - RandCropImage:
            size: 224
        - RandFlipImage:
            flip_code: 1
        - TimmAutoAugment:
            config_str: rand-m7-mstd0.5-inc1
            interpolation: bicubic
            img_size: 224  
        - RandomRotation:
            prob: 0.3
            degrees: 90
            interpolation: bicubic
        - 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: 32
      drop_last: False
      shuffle: True
    loader:
      num_workers: 4
      use_shared_memory: True

  Eval:
    Query:
      dataset:
        name: VeriWild
        image_root: ./dataset/ppshitu_traindata/Aliproduct
        cls_label_path: ./dataset/ppshitu_traindata/Aliproduct/val_list.txt
        transform_ops:
          - DecodeImage:
              to_rgb: True
              channel_first: False
          - ResizeImage:
              size: 224
              interpolation: bicubic
          - 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: 32
        drop_last: False
        shuffle: False
      loader:
        num_workers: 12
        use_shared_memory: True

    Gallery:
      dataset:
        name: VeriWild
        image_root: ./dataset/ppshitu_traindata/Aliproduct/
        cls_label_path: ./dataset/ppshitu_traindata/Aliproduct/val_list.txt
        transform_ops:
          - DecodeImage:
              to_rgb: True
              channel_first: False
          - ResizeImage:
              size: 224
              interpolation: bicubic
          - 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: 32
        drop_last: False
        shuffle: False
      loader:
        num_workers: 12
        use_shared_memory: True

Metric:
  Eval:
    - Recallk:
        topk: [1, 5]
    - mAP: {}