delete vit_huge config

ppcls/configs/ImageNet/VisionTransformer/ViT_huge_patch16_224.yaml

-# global configs
-Global:
-  checkpoints: null
-  pretrained_model: null
-  output_dir: ./output/
-  device: gpu
-  save_interval: 1
-  eval_during_train: True
-  eval_interval: 1
-  epochs: 120
-  print_batch_step: 10
-  use_visualdl: False
-  # used for static mode and model export
-  image_shape: [3, 224, 224]
-  save_inference_dir: ./inference
-
-# model architecture
-Arch:
-  name:  ViT_huge_patch16_224
-  class_num: 1000
- 
-# 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: Piecewise
-    learning_rate: 0.1
-    decay_epochs: [30, 60, 90]
-    values: [0.1, 0.01, 0.001, 0.0001]
-  regularizer:
-    name: 'L2'
-    coeff: 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: [0.5, 0.5, 0.5]
-            std: [0.5, 0.5, 0.5]
-            order: ''
-
-    sampler:
-      name: DistributedBatchSampler
-      batch_size: 64
-      drop_last: False
-      shuffle: True
-    loader:
-      num_workers: 4
-      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: [0.5, 0.5, 0.5]
-            std: [0.5, 0.5, 0.5]
-            order: ''
-    sampler:
-      name: DistributedBatchSampler
-      batch_size: 64
-      drop_last: False
-      shuffle: False
-    loader:
-      num_workers: 4
-      use_shared_memory: True
-
-Infer:
-  infer_imgs: docs/images/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]

ppcls/configs/ImageNet/VisionTransformer/ViT_huge_patch32_384.yaml

-# global configs
-Global:
-  checkpoints: null
-  pretrained_model: null
-  output_dir: ./output/
-  device: gpu
-  save_interval: 1
-  eval_during_train: True
-  eval_interval: 1
-  epochs: 120
-  print_batch_step: 10
-  use_visualdl: False
-  # used for static mode and model export
-  image_shape: [3, 384, 384]
-  save_inference_dir: ./inference
-
-# model architecture
-Arch:
-  name: ViT_huge_patch32_384
-  class_num: 1000
- 
-# 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: Piecewise
-    learning_rate: 0.1
-    decay_epochs: [30, 60, 90]
-    values: [0.1, 0.01, 0.001, 0.0001]
-  regularizer:
-    name: 'L2'
-    coeff: 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: 384
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.5, 0.5, 0.5]
-            std: [0.5, 0.5, 0.5]
-            order: ''
-
-    sampler:
-      name: DistributedBatchSampler
-      batch_size: 64
-      drop_last: False
-      shuffle: True
-    loader:
-      num_workers: 4
-      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: 384
-        - CropImage:
-            size: 384
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.5, 0.5, 0.5]
-            std: [0.5, 0.5, 0.5]
-            order: ''
-    sampler:
-      name: DistributedBatchSampler
-      batch_size: 64
-      drop_last: False
-      shuffle: False
-    loader:
-      num_workers: 4
-      use_shared_memory: True
-
-Infer:
-  infer_imgs: docs/images/whl/demo.jpg
-  batch_size: 10
-  transforms:
-    - DecodeImage:
-        to_rgb: True
-        channel_first: False
-    - ResizeImage:
-        resize_short: 384
-    - CropImage:
-        size: 384
-    - 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]