Add RepVGG models (#592)

* Add RepVGG models

* Update model code

* Rename code

* format code

* add README of RepVGG

configs/RepVGG/RepVGG_A0.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_A0'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_A1.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_A1'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_A2.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_A2'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B0.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B0'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B1.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B1'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B1g2.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B1g2'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B1g4.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B1g4'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B2.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B2'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B2g2.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B2g2'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B2g4.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B2g4'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B3.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B3'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B3g2.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B3g2'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

configs/RepVGG/RepVGG_B3g4.yaml

+mode: 'train'
+ARCHITECTURE:
+    name: 'RepVGG_B3g4'
+
+pretrained_model: ""
+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_mix: False
+ls_epsilon: -1
+
+LEARNING_RATE:
+    function: 'Cosine'          
+    params:                   
+        lr: 0.001             
+
+OPTIMIZER:
+    function: 'Momentum'
+    params:
+        momentum: 0.9
+    regularizer:
+        function: 'L2'
+        factor: 0.000100
+
+TRAIN:
+    batch_size: 64
+    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:

docs/en/models/RepVGG_en.md

+# RepVGG series
+
+## Overview
+
+RepVGG (Making VGG-style ConvNets Great Again) series model is a simple but powerful convolutional neural network architecture proposed by Tsinghua University (Guiguang Ding's team), MEGVII Technology (Jian Sun et al.), HKUST and Aberystwyth University in 2021. The architecture has an inference time agent similar to VGG. The main body is composed of 3x3 convolution and relu stack, while the training time model has multi branch topology. The decoupling of training time and inference time is realized by re-parameterization technology, so the model is called repvgg. [paper](https://arxiv.org/abs/2101.03697).
+
+## Accuracy, FLOPS and Parameters
+
+| Models | Top1 | Top5 | Reference<br>top1| FLOPS<br>(G) |
+|:--:|:--:|:--:|:--:|:--:|
+| RepVGG_A0 | 0.7131 | 0.9016 | 0.7241 |     |
+| RepVGG_A1 | 0.7380 | 0.9146 | 0.7446 |     |
+| RepVGG_A2 | 0.7571 | 0.9264 | 0.7648 |     |
+| RepVGG_B0 | 0.7450 | 0.9213 | 0.7514 |     |
+| RepVGG_B1 | 0.7773 | 0.9385 | 0.7837 |     |
+| RepVGG_B2 | 0.7813 | 0.9410 | 0.7878 |     |
+| RepVGG_B1g2 | 0.7732 | 0.9359 | 0.7778 |    |
+| RepVGG_B1g4 | 0.7675 | 0.9335 | 0.7758 |    |
+| RepVGG_B2g4 | 0.7782 | 0.9380 | 0.7850 |    |
+
+| Models | Top1 | Top5 | Reference<br>top1 | FLOPS<br>(G) |
+|:--:|:--:|:--:|:--:|:--:|
+| RepVGG_B3_200epochs | 0.7987 | 0.9502 | 0.8052 |      |
+| RepVGG_B2g4_200epochs | 0.7881 | 0.9448 | 0.7938 |     |
+| RepVGG_B3g4_200epochs | 0.7965 | 0.9485 | 0.8021 |     |
+
+Params, FLOPs, Inference speed and other information are coming soon.
\ No newline at end of file

docs/zh_CN/models/RepVGG.md

+# RepVGG系列
+
+## 概述
+
+RepVGG（Making VGG-style ConvNets Great Again）系列模型是由清华大学(丁贵广团队)、旷视科技(孙剑等人)、港科大和阿伯里斯特威斯大学在2021年提出的一个简单但强大的卷积神经网络架构，该架构具有类似于VGG的推理时间主体，该主体仅由3x3卷积和ReLU的堆栈组成，而训练时间模型具有多分支拓扑。训练时间和推理时间架构的这种解耦是通过结构重新参数化(re-parameterization)技术实现的，因此该模型称为RepVGG。[论文地址](https://arxiv.org/abs/2101.03697)。
+
+
+## 精度、FLOPS和参数量
+
+| Models | Top1 | Top5 | Reference<br>top1| FLOPS<br>(G) |
+|:--:|:--:|:--:|:--:|:--:|
+| RepVGG_A0 | 0.7131 | 0.9016 | 0.7241 |     |
+| RepVGG_A1 | 0.7380 | 0.9146 | 0.7446 |     |
+| RepVGG_A2 | 0.7571 | 0.9264 | 0.7648 |     |
+| RepVGG_B0 | 0.7450 | 0.9213 | 0.7514 |     |
+| RepVGG_B1 | 0.7773 | 0.9385 | 0.7837 |     |
+| RepVGG_B2 | 0.7813 | 0.9410 | 0.7878 |     |
+| RepVGG_B1g2 | 0.7732 | 0.9359 | 0.7778 |    |
+| RepVGG_B1g4 | 0.7675 | 0.9335 | 0.7758 |    |
+| RepVGG_B2g4 | 0.7782 | 0.9380 | 0.7850 |    |
+
+| Models | Top1 | Top5 | Reference<br>top1 | FLOPS<br>(G) |
+|:--:|:--:|:--:|:--:|:--:|
+| RepVGG_B3_200epochs | 0.7987 | 0.9502 | 0.8052 |      |
+| RepVGG_B2g4_200epochs | 0.7881 | 0.9448 | 0.7938 |     |
+| RepVGG_B3g4_200epochs | 0.7965 | 0.9485 | 0.8021 |     |
+
+关于Params、FLOPs、Inference speed等信息，敬请期待。
\ No newline at end of file

ppcls/modeling/architectures/__init__.py

@@ -46,3 +46,5 @@ from .regnet import RegNetX_200MF, RegNetX_4GF, RegNetX_32GF, RegNetY_200MF, Reg
 from .vision_transformer import ViT_small_patch16_224, ViT_base_patch16_224, ViT_base_patch16_384, ViT_base_patch32_384, ViT_large_patch16_224, ViT_large_patch16_384, ViT_large_patch32_384, ViT_huge_patch16_224, ViT_huge_patch32_384
 from .distilled_vision_transformer import DeiT_tiny_patch16_224, DeiT_small_patch16_224, DeiT_base_patch16_224, DeiT_tiny_distilled_patch16_224, DeiT_small_distilled_patch16_224, DeiT_base_distilled_patch16_224, DeiT_base_patch16_384, DeiT_base_distilled_patch16_384
 from .distillation_models import ResNet50_vd_distill_MobileNetV3_large_x1_0
+from .repvgg import RepVGG_A0, RepVGG_A1, RepVGG_A2, RepVGG_B0, RepVGG_B1, RepVGG_B2, RepVGG_B3, RepVGG_B1g2, RepVGG_B1g4, RepVGG_B2g2, RepVGG_B2g4, RepVGG_B3g2, RepVGG_B3g4
+

ppcls/modeling/architectures/repvgg.py

+import paddle.nn as nn
+import paddle
+import numpy as np
+
+__all__ = [
+    'RepVGG',
+    'RepVGG_A0', 'RepVGG_A1', 'RepVGG_A2',
+    'RepVGG_B0', 'RepVGG_B1', 'RepVGG_B2', 'RepVGG_B3',
+    'RepVGG_B1g2', 'RepVGG_B1g4',
+    'RepVGG_B2g2', 'RepVGG_B2g4',
+    'RepVGG_B3g2', 'RepVGG_B3g4',
+]
+
+
+class ConvBN(nn.Layer):
+    def __init__(self, in_channels, out_channels, kernel_size, stride, padding, groups=1):
+        super(ConvBN, self).__init__()
+        self.conv = nn.Conv2D(in_channels=in_channels, out_channels=out_channels,
+                              kernel_size=kernel_size, stride=stride, padding=padding, groups=groups, bias_attr=False)
+        self.bn = nn.BatchNorm2D(num_features=out_channels)
+
+    def forward(self, x):
+        y = self.conv(x)
+        y = self.bn(y)
+        return y
+
+
+class RepVGGBlock(nn.Layer):
+
+    def __init__(self, in_channels, out_channels, kernel_size,
+                 stride=1, padding=0, dilation=1, groups=1, padding_mode='zeros'):
+        super(RepVGGBlock, self).__init__()
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        self.kernel_size = kernel_size
+        self.stride = stride
+        self.padding = padding
+        self.dilation = dilation
+        self.groups = groups
+        self.padding_mode = padding_mode
+
+        assert kernel_size == 3
+        assert padding == 1
+
+        padding_11 = padding - kernel_size // 2
+
+        self.nonlinearity = nn.ReLU()
+
+        self.rbr_identity = nn.BatchNorm2D(
+            num_features=in_channels) if out_channels == in_channels and stride == 1 else None
+        self.rbr_dense = ConvBN(in_channels=in_channels, out_channels=out_channels,
+                                kernel_size=kernel_size, stride=stride, padding=padding, groups=groups)
+        self.rbr_1x1 = ConvBN(in_channels=in_channels, out_channels=out_channels,
+                              kernel_size=1, stride=stride, padding=padding_11, groups=groups)
+
+    def forward(self, inputs):
+        if not self.training:
+            return self.nonlinearity(self.rbr_reparam(inputs))
+
+        if self.rbr_identity is None:
+            id_out = 0
+        else:
+            id_out = self.rbr_identity(inputs)
+        return self.nonlinearity(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)
+
+    def eval(self):
+        if not hasattr(self, 'rbr_reparam'):
+            self.rbr_reparam = nn.Conv2D(in_channels=self.in_channels, out_channels=self.out_channels, kernel_size=self.kernel_size, stride=self.stride,
+                                         padding=self.padding, dilation=self.dilation, groups=self.groups, padding_mode=self.padding_mode)
+        self.training = False
+        kernel, bias = self.get_equivalent_kernel_bias()
+        self.rbr_reparam.weight.set_value(kernel)
+        self.rbr_reparam.bias.set_value(bias)
+        for layer in self.sublayers():
+            layer.eval()
+
+    def get_equivalent_kernel_bias(self):
+        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
+        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
+        kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
+        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
+
+    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
+        if kernel1x1 is None:
+            return 0
+        else:
+            return nn.functional.pad(kernel1x1, [1, 1, 1, 1])
+
+    def _fuse_bn_tensor(self, branch):
+        if branch is None:
+            return 0, 0
+        if isinstance(branch, ConvBN):
+            kernel = branch.conv.weight
+            running_mean = branch.bn._mean
+            running_var = branch.bn._variance
+            gamma = branch.bn.weight
+            beta = branch.bn.bias
+            eps = branch.bn._epsilon
+        else:
+            assert isinstance(branch, nn.BatchNorm2D)
+            if not hasattr(self, 'id_tensor'):
+                input_dim = self.in_channels // self.groups
+                kernel_value = np.zeros(
+                    (self.in_channels, input_dim, 3, 3), dtype=np.float32)
+                for i in range(self.in_channels):
+                    kernel_value[i, i % input_dim, 1, 1] = 1
+                self.id_tensor = paddle.to_tensor(kernel_value)
+            kernel = self.id_tensor
+            running_mean = branch._mean
+            running_var = branch._variance
+            gamma = branch.weight
+            beta = branch.bias
+            eps = branch._epsilon
+        std = (running_var + eps).sqrt()
+        t = (gamma / std).reshape((-1, 1, 1, 1))
+        return kernel * t, beta - running_mean * gamma / std
+
+
+class RepVGG(nn.Layer):
+
+    def __init__(self, num_blocks, width_multiplier=None, override_groups_map=None, class_dim=1000):
+        super(RepVGG, self).__init__()
+
+        assert len(width_multiplier) == 4
+        self.override_groups_map = override_groups_map or dict()
+
+        assert 0 not in self.override_groups_map
+
+        self.in_planes = min(64, int(64 * width_multiplier[0]))
+
+        self.stage0 = RepVGGBlock(
+            in_channels=3, out_channels=self.in_planes, kernel_size=3, stride=2, padding=1)
+        self.cur_layer_idx = 1
+        self.stage1 = self._make_stage(
+            int(64 * width_multiplier[0]), num_blocks[0], stride=2)
+        self.stage2 = self._make_stage(
+            int(128 * width_multiplier[1]), num_blocks[1], stride=2)
+        self.stage3 = self._make_stage(
+            int(256 * width_multiplier[2]), num_blocks[2], stride=2)
+        self.stage4 = self._make_stage(
+            int(512 * width_multiplier[3]), num_blocks[3], stride=2)
+        self.gap = nn.AdaptiveAvgPool2D(output_size=1)
+        self.linear = nn.Linear(int(512 * width_multiplier[3]), class_dim)
+
+    def _make_stage(self, planes, num_blocks, stride):
+        strides = [stride] + [1]*(num_blocks-1)
+        blocks = []
+        for stride in strides:
+            cur_groups = self.override_groups_map.get(self.cur_layer_idx, 1)
+            blocks.append(RepVGGBlock(in_channels=self.in_planes, out_channels=planes, kernel_size=3,
+                                      stride=stride, padding=1, groups=cur_groups))
+            self.in_planes = planes
+            self.cur_layer_idx += 1
+        return nn.Sequential(*blocks)
+
+    def forward(self, x):
+        out = self.stage0(x)
+        out = self.stage1(out)
+        out = self.stage2(out)
+        out = self.stage3(out)
+        out = self.stage4(out)
+        out = self.gap(out)
+        out = paddle.flatten(out, start_axis=1)
+        out = self.linear(out)
+        return out
+
+
+optional_groupwise_layers = [2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26]
+g2_map = {l: 2 for l in optional_groupwise_layers}
+g4_map = {l: 4 for l in optional_groupwise_layers}
+
+
+def RepVGG_A0(**kwargs):
+    return RepVGG(num_blocks=[2, 4, 14, 1],
+                  width_multiplier=[0.75, 0.75, 0.75, 2.5], override_groups_map=None, **kwargs)
+
+
+def RepVGG_A1(**kwargs):
+    return RepVGG(num_blocks=[2, 4, 14, 1],
+                  width_multiplier=[1, 1, 1, 2.5], override_groups_map=None, **kwargs)
+
+
+def RepVGG_A2(**kwargs):
+    return RepVGG(num_blocks=[2, 4, 14, 1],
+                  width_multiplier=[1.5, 1.5, 1.5, 2.75], override_groups_map=None, **kwargs)
+
+
+def RepVGG_B0(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[1, 1, 1, 2.5], override_groups_map=None, **kwargs)
+
+
+def RepVGG_B1(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[2, 2, 2, 4], override_groups_map=None, **kwargs)
+
+
+def RepVGG_B1g2(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[2, 2, 2, 4], override_groups_map=g2_map, **kwargs)
+
+
+def RepVGG_B1g4(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[2, 2, 2, 4], override_groups_map=g4_map, **kwargs)
+
+
+def RepVGG_B2(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[2.5, 2.5, 2.5, 5], override_groups_map=None, **kwargs)
+
+
+def RepVGG_B2g2(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[2.5, 2.5, 2.5, 5], override_groups_map=g2_map, **kwargs)
+
+
+def RepVGG_B2g4(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[2.5, 2.5, 2.5, 5], override_groups_map=g4_map, **kwargs)
+
+
+def RepVGG_B3(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[3, 3, 3, 5], override_groups_map=None, **kwargs)
+
+
+def RepVGG_B3g2(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[3, 3, 3, 5], override_groups_map=g2_map, **kwargs)
+
+
+def RepVGG_B3g4(**kwargs):
+    return RepVGG(num_blocks=[4, 6, 16, 1],
+                  width_multiplier=[3, 3, 3, 5], override_groups_map=g4_map, **kwargs)