fix distillation and augment yaml (#851)

ppcls/configs/DataAugment/ResNet50_AutoAugment.yaml

@@ -1,73 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - AutoAugment:
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_Baseline.yaml

@@ -1,72 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_Cutmix.yaml

@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-    mix:
-        - CutmixOperator:
-            alpha: 0.2
-    
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_Cutout.yaml

@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - Cutout:
-            n_holes: 1
-            length: 112
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_GridMask.yaml

@@ -1,78 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - GridMask:
-            d1: 96
-            d2: 224
-            rotate: 1
-            ratio: 0.5
-            mode: 0
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_HideAndSeek.yaml

@@ -1,73 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - HideAndSeek:
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_Mixup.yaml

@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-    mix:
-        - MixupOperator:
-            alpha: 0.2
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_RandAugment.yaml

@@ -1,75 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - RandAugment:
-            num_layers: 2 
-            magnitude: 5
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/DataAugment/ResNet50_RandomErasing.yaml

@@ -1,78 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 300
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.000100
-
-TRAIN:
-    batch_size: 256
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-        - RandomErasing:
-              EPSILON: 0.5
-              sl: 0.02
-              sh: 0.4
-              r1: 0.3
-              mean: [0., 0., 0.]
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/Distillation/R50_vd_distill_MV3_large_x1_0.yaml

@@ -1,71 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNet50_vd_distill_MobileNetV3_large_x1_0'
-
-pretrained_model: "./pretrained/ResNet50_vd_ssld_pretrained"
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_distillation: True
-
-LEARNING_RATE:
-    function: 'CosineWarmup'
-    params:                   
-        lr: 1.3   
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00001
-
-TRAIN:
-    batch_size: 2048
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/Distillation/ResX101_32x16d_wsl_distill_R50_vd.yaml

@@ -1,71 +0,0 @@
-mode: 'train'
-ARCHITECTURE:
-    name: 'ResNeXt101_32x16d_wsl_distill_ResNet50_vd'
-
-pretrained_model: "./pretrained/ResNeXt101_32x16d_wsl_pretrained"
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 120
-topk: 5
-image_shape: [3, 224, 224]
-
-use_distillation: True
-
-LEARNING_RATE:
-    function: 'CosineWarmup'
-    params:                   
-        lr: 0.4
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00007
-
-TRAIN:
-    batch_size: 1024
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/train_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    transforms:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1./255.
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-
-VALID:
-    batch_size: 64
-    num_workers: 4
-    file_list: "./dataset/ILSVRC2012/val_list.txt"
-    data_dir: "./dataset/ILSVRC2012/"
-    shuffle_seed: 0
-    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:

ppcls/configs/ImageNet/DataAugment/ResNet50_AutoAugment.yaml

@@ -0,0 +1,130 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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
+        - AutoAugment:
+        - 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: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_Baseline.yaml

@@ -0,0 +1,129 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 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: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_Cutmix.yaml

@@ -0,0 +1,129 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+      batch_transform_ops:
+        - CutmixOperator:
+            alpha: 0.2
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_Cutout.yaml

@@ -0,0 +1,132 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - Cutout:
+            n_holes: 1
+            length: 112
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_GridMask.yaml

@@ -0,0 +1,135 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - GridMask:
+            d1: 96
+            d2: 224
+            rotate: 1
+            ratio: 0.5
+            mode: 0
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_HideAndSeek.yaml

@@ -0,0 +1,130 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - HideAndSeek:
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_Mixup.yaml

@@ -0,0 +1,129 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+      batch_transform_ops:
+        - MixupOperator:
+            alpha: 0.2
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_RandAugment.yaml

@@ -0,0 +1,132 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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
+        - RandAugment:
+            num_layers: 2 
+            magnitude: 5
+        - 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: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/configs/ImageNet/DataAugment/ResNet50_RandomErasing.yaml

@@ -0,0 +1,135 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  class_num: 1000
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  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: ResNet50
+ 
+# 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: 0.1
+  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: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.5
+            sl: 0.02
+            sh: 0.4
+            r1: 0.3
+            mean: [0., 0., 0.]
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    # TOTO: modify to the latest trainer
+    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: 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: [0.485, 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:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

ppcls/data/preprocess/ops/random_erasing.py

@@ -21,11 +21,7 @@ import numpy as np
 
 
 class RandomErasing(object):
-    def __init__(self,
-                 EPSILON=0.5,
-                 sl=0.02,
-                 sh=0.4,
-                 r1=0.3,
+    def __init__(self, EPSILON=0.5, sl=0.02, sh=0.4, r1=0.3,
                  mean=[0., 0., 0.]):
         self.EPSILON = EPSILON
         self.mean = mean
@@ -37,8 +33,8 @@ class RandomErasing(object):
         if random.uniform(0, 1) > self.EPSILON:
             return img
 
-        for attempt in range(100):
-            area = img.shape[1] * img.shape[2]
+        for _ in range(100):
+            area = img.shape[0] * img.shape[1]
 
             target_area = random.uniform(self.sl, self.sh) * area
             aspect_ratio = random.uniform(self.r1, 1 / self.r1)
@@ -50,9 +46,9 @@ class RandomErasing(object):
                 x1 = random.randint(0, img.shape[1] - h)
                 y1 = random.randint(0, img.shape[2] - w)
                 if img.shape[0] == 3:
-                    img[0, x1:x1 + h, y1:y1 + w] = self.mean[0]
-                    img[1, x1:x1 + h, y1:y1 + w] = self.mean[1]
-                    img[2, x1:x1 + h, y1:y1 + w] = self.mean[2]
+                    img[x1:x1 + h, y1:y1 + w, 0] = self.mean[0]
+                    img[x1:x1 + h, y1:y1 + w, 1] = self.mean[1]
+                    img[x1:x1 + h, y1:y1 + w, 2] = self.mean[2]
                 else:
                     img[0, x1:x1 + h, y1:y1 + w] = self.mean[1]
                 return img