CLIP_vit_base_patch16_224_finetune.yaml

# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/
  device: gpu
  save_interval: 10
  eval_during_train: True
  eval_interval: 1
  epochs: 50
  print_batch_step: 10
  use_visualdl: False
  # used for static mode and model export
  image_shape: [3, 224, 224]
  save_inference_dir: ./inference

# mixed precision training
AMP:
  scale_loss: 128.0
  use_dynamic_loss_scaling: True
  # O1: mixed fp16
  level: O1

# model ema
EMA:
  decay: 0.9999

# model architecture
Arch:
  name: CLIP_vit_base_patch16_224
  class_num: 1000
  return_embed: False
  pretrained: True
  head_init_scale: 0.001

# loss function config for traing/eval process
Loss:
  Train:
    - CELoss:
        weight: 1.0
        epsilon: 0.1
  Eval:
    - CELoss:
        weight: 1.0

Optimizer:
  name: AdamWDL
  beta1: 0.9
  beta2: 0.999
  epsilon: 1e-8
  weight_decay: 0.05
  layerwise_decay: 0.6
  filter_bias_and_bn: True
  lr:
    name: Cosine
    learning_rate: 0.0003
    eta_min: 1e-6
    warmup_epoch: 10
    warmup_start_lr: 1e-6

# 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
            interpolation: bicubic
            backend: pil
        - RandFlipImage:
            flip_code: 1
        - TimmAutoAugment:
            config_str: rand-m9-mstd0.5-inc1
            interpolation: bicubic
            img_size: 224
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.48145466, 0.4578275, 0.40821073]
            std: [0.26862954, 0.26130258, 0.27577711] 
            order: ''
        - RandomErasing:
            EPSILON: 0.25
            sl: 0.02
            sh: 1.0/3.0
            r1: 0.3
            attempt: 10
            use_log_aspect: True
            mode: pixel
    sampler:
      name: DistributedBatchSampler
      batch_size: 128
      drop_last: True
      shuffle: True
    loader:
      num_workers: 16
      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: 224
            interpolation: bicubic
            backend: pil
        - CropImage:
            size: 224
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.48145466, 0.4578275, 0.40821073]
            std: [0.26862954, 0.26130258, 0.27577711] 
            order: ''
    sampler:
      name: DistributedBatchSampler
      batch_size: 128
      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: [0.5, 0.5, 0.5]
        std: [0.5, 0.5, 0.5]
        order: ''
    - ToCHWImage:
  PostProcess:
    name: Topk
    topk: 5
    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt

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