diff --git a/configs/DataAugment/ResNet50_AutoAugment.yaml b/configs/DataAugment/ResNet50_AutoAugment.yaml
new file mode 100644
index 000000000..44bbe631a
--- /dev/null
+++ b/configs/DataAugment/ResNet50_AutoAugment.yaml
@@ -0,0 +1,75 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_Baseline.yaml b/configs/DataAugment/ResNet50_Baseline.yaml
new file mode 100644
index 000000000..1d03ae37c
--- /dev/null
+++ b/configs/DataAugment/ResNet50_Baseline.yaml
@@ -0,0 +1,74 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_Cutmix.yaml b/configs/DataAugment/ResNet50_Cutmix.yaml
new file mode 100644
index 000000000..322fb35c4
--- /dev/null
+++ b/configs/DataAugment/ResNet50_Cutmix.yaml
@@ -0,0 +1,77 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_Cutout.yaml b/configs/DataAugment/ResNet50_Cutout.yaml
new file mode 100644
index 000000000..91cbe4c72
--- /dev/null
+++ b/configs/DataAugment/ResNet50_Cutout.yaml
@@ -0,0 +1,77 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_GridMask.yaml b/configs/DataAugment/ResNet50_GridMask.yaml
new file mode 100644
index 000000000..4d442a2e9
--- /dev/null
+++ b/configs/DataAugment/ResNet50_GridMask.yaml
@@ -0,0 +1,80 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_HideAndSeek.yaml b/configs/DataAugment/ResNet50_HideAndSeek.yaml
new file mode 100644
index 000000000..17f5f1eec
--- /dev/null
+++ b/configs/DataAugment/ResNet50_HideAndSeek.yaml
@@ -0,0 +1,75 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_Mixup.yaml b/configs/DataAugment/ResNet50_Mixup.yaml
new file mode 100644
index 000000000..3e4105f7b
--- /dev/null
+++ b/configs/DataAugment/ResNet50_Mixup.yaml
@@ -0,0 +1,77 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_RandAugment.yaml b/configs/DataAugment/ResNet50_RandAugment.yaml
new file mode 100644
index 000000000..a3a34eceb
--- /dev/null
+++ b/configs/DataAugment/ResNet50_RandAugment.yaml
@@ -0,0 +1,77 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/DataAugment/ResNet50_RandomErasing.yaml b/configs/DataAugment/ResNet50_RandomErasing.yaml
new file mode 100644
index 000000000..682cf95d6
--- /dev/null
+++ b/configs/DataAugment/ResNet50_RandomErasing.yaml
@@ -0,0 +1,80 @@
+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
+            to_np: False
+            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: ''
+        - RandomErasing:
+              EPSILON: 0.5
+              sl: 0.02
+              sh: 0.4
+              r1: 0.3                                     
+              mean: [0., 0., 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
+            to_np: False
+            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:
diff --git a/configs/Distillation/R50_vd_distill_MV3_large_x1_0.yaml b/configs/Distillation/R50_vd_distill_MV3_large_x1_0.yaml
new file mode 100644
index 000000000..39c186e82
--- /dev/null
+++ b/configs/Distillation/R50_vd_distill_MV3_large_x1_0.yaml
@@ -0,0 +1,74 @@
+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
+ls_epsilon: 0.1
+
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/configs/Distillation/ResX101_32x16d_wsl_distill_R50_vd.yaml b/configs/Distillation/ResX101_32x16d_wsl_distill_R50_vd.yaml
new file mode 100644
index 000000000..9e5b060f1
--- /dev/null
+++ b/configs/Distillation/ResX101_32x16d_wsl_distill_R50_vd.yaml
@@ -0,0 +1,73 @@
+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
+            to_np: False
+            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
+            to_np: False
+            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:
diff --git a/docs/zh_CN/advanced_tutorials/distillation/distillation.md b/docs/zh_CN/advanced_tutorials/distillation/distillation.md
index cf5c2c2a2..6e29702c9 100644
--- a/docs/zh_CN/advanced_tutorials/distillation/distillation.md
+++ b/docs/zh_CN/advanced_tutorials/distillation/distillation.md
@@ -185,9 +185,73 @@ for var in ./*_student; do cp "$var" "../student_model/${var%_student}"; done #
 
 # 五、SSLD实战
 
-* 该部分内容正在持续更新中，敬请期待。
+本节简要介绍了SSLD的实战内容，用户可以通过此处的配置启动SSLD蒸馏任务。如果用户对SSLD
 
+## 7.1 参数配置
 
+实战部分提供了SSLD蒸馏的示例，在`ppcls/modeling/architectures/distillation_models.py`中提供了`ResNeXt101_32x16d_wsl`蒸馏`ResNet50_vd`与`ResNet50_vd_ssld`蒸馏`MobileNetV3_large_x1_0`的示例，`configs/Distillation`里分别提供了二者的配置文件，用户可以在`tools/run.sh`里直接替换配置文件的路径即可使用。
+
+### ResNeXt101_32x16d_wsl蒸馏ResNet50_vd
+
+`ResNeXt101_32x16d_wsl`蒸馏`ResNet50_vd`的配置如下，其中`pretrained model`指定了`ResNeXt101_32x16d_wsl`（教师模型）的预训练模型的路径，该路径也可以同时指定教师模型与学生模型的预训练模型的路径，用户只需要同时传入二者预训练的路径即可（配置中的注释部分）。
+
+```yaml
+ARCHITECTURE:                                                                                    
+    name: 'ResNeXt101_32x16d_wsl_distill_ResNet50_vd'   
+pretrained_model: "./pretrained/ResNeXt101_32x16d_wsl_pretrained/"  
+# pretrained_model:
+#     - "./pretrained/ResNeXt101_32x16d_wsl_pretrained/"
+#     - "./pretrained/ResNet50_vd_pretrained/"
+use_distillation: True 
+```
+
+### ResNet50_vd_ssld蒸馏MobileNetV3_large_x1_0
+
+类似于`ResNeXt101_32x16d_wsl`蒸馏`ResNet50_vd`，`ResNet50_vd_ssld`蒸馏`MobileNetV3_large_x1_0`的配置如下:
+
+```yaml
+ARCHITECTURE:                                                                                    
+    name: 'ResNet50_vd_distill_MobileNetV3_large_x1_0'  
+pretrained_model: "./pretrained/ResNet50_vd_ssld_pretrained/"  
+# pretrained_model:
+#     - "./pretrained/ResNet50_vd_ssld_pretrained/"
+#     - "./pretrained/ResNet50_vd_pretrained/"
+use_distillation: True 
+```
+
+## 7.2 启动命令
+
+当用户配置完训练环境后，类似于训练其他分类任务，只需要将`tools/run.sh`中的配置文件替换成为相应的蒸馏配置文件即可。
+
+其中`run.sh`中的内容如下：
+
+```bash
+export PYTHONPATH=path_to_PaddleClas:$PYTHONPATH
+
+python -m paddle.distributed.launch \                                                            
+    --selected_gpus="0,1,2,3" \                                                                  
+    --log_dir=R50_vd_distill_MV3_large_x1_0 \                                                                  
+    tools/train.py \                                                                             
+        -c ./configs/Distillation/R50_vd_distill_MV3_large_x1_0.yaml
+```
+
+运行`run.sh`
+
+```bash
+sh tools/run.sh
+```
+
+## 7.3 注意事项
+
+* 用户在使用SSLD蒸馏之前，首先需要在目标数据集上训练一个教师模型，该教师模型用于指导学生模型在该数据集上的训练。
+
+* 在用户使用SSLD蒸馏的时候需要将配置文件中的`use_distillation`设置为`True`，另外由于学生模型学习带有知识信息的soft-label，所以需要关掉label_smoothing选项，即将`ls_epsilon`中的值设置在[0,1]之外。
+
+* 如果学生模型没有加载预训练模型，训练的其他超参数可以参考该学生模型在ImageNet-1k上训练的超参数，如果学生模型加载了预训练模型，学习率可以调整到原来的1/10或者1/100。
+
+* 在SSLD蒸馏的过程中，学生模型只学习soft-label导致训练目标变的更加复杂，建议可以适当的调小`l2_decay`的值来获得更高的验证集准确率。
+
+* 若用户准备添加无标签的训练数据，只需要将新的训练数据放置在原本训练数据的路径下，生成新的数据list即可，另外，新生成的数据list需要将无标签的数据添加伪标签（只是为了统一读数据）。
 
 **此处插播一条硬广~**
 > 如果您觉得此文档对您有帮助，欢迎star、watch、fork，三连我们的项目：[https://github.com/PaddlePaddle/PaddleClas](https://github.com/PaddlePaddle/PaddleClas)
diff --git a/docs/zh_CN/advanced_tutorials/image_augmentation/ImageAugment.md b/docs/zh_CN/advanced_tutorials/image_augmentation/ImageAugment.md
index 2fb872990..5e35dab34 100644
--- a/docs/zh_CN/advanced_tutorials/image_augmentation/ImageAugment.md
+++ b/docs/zh_CN/advanced_tutorials/image_augmentation/ImageAugment.md
@@ -438,9 +438,118 @@ new_batch = cutmix_op(batch)
 
 # 七、数据增广分类实战
 
-* 该部分内容正在持续更新中，敬请期待。
+本节列举了八类数据增广的参数配置、启动命令以及使用过程的注意事项等。如果用户在使用
 
+## 7.1 参数配置
 
+由于不同的数据增广方式含有不同的超参数，为了便于理解和使用，我们在`configs/DataAugment`里分别列举了8种训练ResNet50的数据增广方式的参数配置文件，用户可以在`tools/run.sh`里直接替换配置文件的路径即可使用。此处分别挑选了图像变换、图像裁剪、图像混叠中的一个示例展示，其他参数配置用户可以自查配置文件。
+
+### RandAugment
+
+`RandAugment`的图像增广方式的配置如下，其中用户需要指定其中的参数`num_layers`与`magnitude`，默认的数值分别是`2`和`5`。`RandAugment`是在uint8的数据格式上转换的，所以其处理过程应该放在归一化操作（`NormalizeImage`）之前。
+
+```yaml
+    transforms:                                                                                  
+        - DecodeImage:                                                                           
+            to_rgb: True                                                                         
+            to_np: False                                                                         
+            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: 
+```
+
+### Cutout
+
+`Cutout`的图像增广方式的配置如下，其中用户需要指定其中的参数`n_holes`与`length`，默认的数值分别是`1`和`112`。类似其他图像裁剪类的数据增广方式，`Cutout`既可以在uint8格式的数据上操作，也可以在归一化（`NormalizeImage`）后的数据上操作，此处给出的是在归一化后的操作。
+
+```yaml
+    transforms:                                                                                  
+        - DecodeImage:                                                                           
+            to_rgb: True                                                                         
+            to_np: False                                                                         
+            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: 
+```
+
+### Mixup
+
+`Mixup`的图像增广方式的配置如下，其中用户需要指定其中的参数`alpha`，默认的数值是`0.2`。类似其他图像混合类的数据增广方式，`Mixup`是在图像做完数据处理后将每个batch内的数据做图像混叠，将混叠后的图像和标签输入网络中训练，所以其是在图像数据处理（图像变换、图像裁剪）后操作。另外，在配置文件中，需要将`use_mix`参数设置为`True`。
+
+```yaml
+    transforms:                                                                                  
+        - DecodeImage:                                                                           
+            to_rgb: True                                                                         
+            to_np: False                                                                         
+            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  
+```
+
+## 7.2 启动命令
+
+当用户配置完训练环境后，类似于训练其他分类任务，只需要将`tools/run.sh`中的配置文件替换成为相应的数据增广方式的配置文件即可。
+
+其中`run.sh`中的内容如下：
+
+```bash
+export PYTHONPATH=path_to_PaddleClas:$PYTHONPATH
+
+python -m paddle.distributed.launch \                                                            
+    --selected_gpus="0,1,2,3" \                                                                  
+    --log_dir=ResNet50_Cutout \                                                                  
+    tools/train.py \                                                                             
+        -c ./configs/DataAugment/ResNet50_Cutout.yaml 
+```
+
+运行`run.sh`
+
+```bash
+sh tools/run.sh
+```
+
+## 7.3 注意事项
+
+* 在使用图像混叠类的数据处理时，需要将配置文件中的`use_mix`设置为`True`，另外由于图像混叠时需对label进行混叠，无法计算训练数据的准确率，所以在训练过程中没有打印训练准确率。
+
+* 在使用数据增广后，由于训练数据更难，所以训练损失函数可能较大，训练集的准确率相对较低，但其有拥更好的泛化能力，所以验证集的准确率相对较高。
+
+* 在使用数据增广后，模型可能会趋于欠拟合状态，建议可以适当的调小`l2_decay`的值来获得更高的验证集准确率。
+
+* 几乎每一类图像增广均含有超参数，我们只提供了基于ImageNet-1k的超参数，其他数据集需要用户自己调试超参数，具体超参数的含义用户可以阅读相关的论文，调试方法也可以参考训练技巧的章节。
 
 **此处插播一条硬广~**
 > 如果您觉得此文档对您有帮助，欢迎star、watch、fork，三连我们的项目：[https://github.com/PaddlePaddle/PaddleClas](https://github.com/PaddlePaddle/PaddleClas)
diff --git a/ppcls/data/imaug/__init__.py b/ppcls/data/imaug/__init__.py
index 55be7a373..6860382bc 100644
--- a/ppcls/data/imaug/__init__.py
+++ b/ppcls/data/imaug/__init__.py
@@ -44,12 +44,12 @@ def transform(data, ops=[]):
     return data
 
 
-class ImageNetPolicy(RawImageNetPolicy):
+class AutoAugment(RawImageNetPolicy):
     """ ImageNetPolicy wrapper to auto fit different img types """
 
     def __init__(self, *args, **kwargs):
         if six.PY2:
-            super(ImageNetPolicy, self).__init__(*args, **kwargs)
+            super(AutoAugment, self).__init__(*args, **kwargs)
         else:
             super().__init__(*args, **kwargs)
 
@@ -59,7 +59,7 @@ class ImageNetPolicy(RawImageNetPolicy):
             img = Image.fromarray(img)
 
         if six.PY2:
-            img = super(ImageNetPolicy, self).__call__(img)
+            img = super(AutoAugment, self).__call__(img)
         else:
             img = super().__call__(img)
 
diff --git a/ppcls/data/imaug/grid.py b/ppcls/data/imaug/grid.py
index 437dbc09d..93e0c58ac 100644
--- a/ppcls/data/imaug/grid.py
+++ b/ppcls/data/imaug/grid.py
@@ -25,7 +25,7 @@ NUM_EPOCHS = 240
 
 
 class GridMask(object):
-    def __init__(self, d1, d2, rotate=1, ratio=0.5, mode=0, prob=1.):
+    def __init__(self, d1=96, d2=224, rotate=1, ratio=0.5, mode=0, prob=1.):
         self.d1 = d1
         self.d2 = d2
         self.rotate = rotate
diff --git a/ppcls/data/imaug/randaugment.py b/ppcls/data/imaug/randaugment.py
index 959c7b185..3ccf75757 100644
--- a/ppcls/data/imaug/randaugment.py
+++ b/ppcls/data/imaug/randaugment.py
@@ -20,7 +20,7 @@ import random
 
 
 class RandAugment(object):
-    def __init__(self, num_layers, magnitude, fillcolor=(128, 128, 128)):
+    def __init__(self, num_layers=2, magnitude=5, fillcolor=(128, 128, 128)):
         self.num_layers = num_layers
         self.magnitude = magnitude
         self.max_level = 10