Merge pull request #860 from PaddlePaddle/develop_reg

merge develop_reg into develop

.gitignore

@@ -2,7 +2,6 @@ __pycache__/
 *.pyc
 *.sw*
 */workerlog*
-dataset/
 checkpoints/
 output/
 pretrained/

README.md

@@ -8,13 +8,10 @@ PaddleClas is a toolset for image classification tasks prepared for the industry
 
 **Recent update**
 
-- 2021.05.14 Add `SwinTransformer` series pretrained models, whose Top-1 Acc on ImageNet-1k dataset reaches 87.19%.
-- 2021.04.15 Add `MixNet` and `ReXNet` pretrained models, `MixNet_L`'s Top-1 Acc on ImageNet-1k reaches 78.6% and `ReXNet_3_0` reaches 82.09%.
-- 2021.03.02 Add support for model quantization.
-- 2021.02.01 Add `RepVGG` pretrained models, whose Top-1 Acc on ImageNet-1k dataset reaches 79.65%.
-- 2021.01.27 Add `ViT` and `DeiT` pretrained models, `ViT`'s Top-1 Acc on ImageNet-1k dataset reaches 85.13%, and `DeiT` reaches 85.1%.
-- 2021.01.08 Add support for whl package and its usage, Model inference can be done by simply install paddleclas using pip.
-- 2020.12.16 Add support for TensorRT when using cpp inference to obain more obvious acceleration.
+- 2021.06.16 PaddleClas release/2.2.
+   - Add metric learning and vector search module.
+   - Add product recognition, cartoon character recognition, car recognition and logo recognition.
+   - Added 30 pretrained models of LeViT, Twins, TNT, DLA, HarDNet, and RedNet, and the accuracy is roughly the same as that of the paper.
 - [more](./docs/en/update_history_en.md)
 
 

configs/AlexNet/AlexNet.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "AlexNet"
-
-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]
-
-LEARNING_RATE:
-   function: 'Piecewise'
-   params:
-       lr: 0.01
-       decay_epochs: [30, 60, 90]
-       gamma: 0.1
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.0001
-
-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:
-

configs/DPN/DPN107.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DPN107'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DPN/DPN131.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DPN131'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DPN/DPN68.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DPN68'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DPN/DPN92.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DPN92'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DPN/DPN98.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DPN98'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.1               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DarkNet/DarkNet53.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "DarkNet53"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 256, 256]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-   function: 'Cosine'
-   params:
-       lr: 0.1
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.0001
-
-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: 256
-        - 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: 256
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:
-
-

configs/DataAugment/ResNet50_AutoAugment.yaml

-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:

configs/DataAugment/ResNet50_Baseline.yaml

-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:

configs/DataAugment/ResNet50_Cutmix.yaml

-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:

configs/DataAugment/ResNet50_Cutout.yaml

-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:

configs/DataAugment/ResNet50_GridMask.yaml

-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:

configs/DataAugment/ResNet50_HideAndSeek.yaml

-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:

configs/DataAugment/ResNet50_Mixup.yaml

-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:

configs/DataAugment/ResNet50_RandAugment.yaml

-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:

configs/DataAugment/ResNet50_RandomErasing.yaml

-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:

configs/DeiT/DeiT_base_distilled_patch16_224.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_base_distilled_patch16_224'
-
-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: 0.01               
-
-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
-            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: 248
-        - 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/DeiT/DeiT_base_distilled_patch16_384.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_base_distilled_patch16_384'
-
-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, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.01               
-
-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
-            channel_first: False
-        - RandCropImage:
-            size: 384
-        - 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: 426
-        - CropImage:
-            size: 384
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:

configs/DeiT/DeiT_base_patch16_224.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_base_patch16_224'
-
-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: 0.01               
-
-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
-            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: 248
-        - 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/DeiT/DeiT_base_patch16_384.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_base_patch16_384'
-
-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, 384, 384]
-
-use_mix: False
-ls_epsilon: -1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                   
-        lr: 0.01               
-
-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
-            channel_first: False
-        - RandCropImage:
-            size: 384
-        - 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: 426
-        - CropImage:
-            size: 384
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:

configs/DeiT/DeiT_small_distilled_patch16_224.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_small_distilled_patch16_224'
-
-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: 0.01               
-
-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
-            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: 248
-        - 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/DeiT/DeiT_small_patch16_224.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_small_patch16_224'
-
-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: 0.01               
-
-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
-            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: 248
-        - 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/DeiT/DeiT_tiny_distilled_patch16_224.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_tiny_distilled_patch16_224'
-
-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: 0.01               
-
-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
-            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: 248
-        - 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/DeiT/DeiT_tiny_patch16_224.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DeiT_tiny_patch16_224'
-
-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: 0.01               
-
-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
-            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: 248
-        - 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/DenseNet/DenseNet121.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DenseNet121'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DenseNet/DenseNet161.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DenseNet161'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DenseNet/DenseNet169.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DenseNet169'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DenseNet/DenseNet201.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DenseNet201'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/DenseNet/DenseNet264.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'DenseNet264'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/Distillation/R50_vd_distill_MV3_large_x1_0.yaml

-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:

configs/Distillation/ResX101_32x16d_wsl_distill_R50_vd.yaml

-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:

configs/EfficientNet/EfficientNetB0.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "EfficientNetB0"
-    params:
-        padding_type : "SAME"
-        override_params:
-            drop_connect_rate: 0.1
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-use_ema: True
-ema_decay: 0.9999
-use_aa: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'ExponentialWarmup'
-    params:
-        lr: 0.032
-
-OPTIMIZER:
-    function: 'RMSProp'
-    params:
-        momentum: 0.9
-        rho: 0.9
-        epsilon: 0.001
-    regularizer:
-        function: 'L2'
-        factor: 0.00001
-
-TRAIN:
-    batch_size: 512
-    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
-            interpolation: 2
-        - 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: 128
-    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:
-            interpolation: 2
-            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/GhostNet/GhostNet_x0_5.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'GhostNet_x0_5'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'CosineWarmup'          
-    params:                   
-        lr: 0.8               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.0000400
-
-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:

configs/GhostNet/GhostNet_x1_0.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'GhostNet_x1_0'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'CosineWarmup'          
-    params:                   
-        lr: 0.4               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.0000400
-
-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:

configs/GhostNet/GhostNet_x1_3.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'GhostNet_x1_3'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-use_mix: False
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'CosineWarmup'          
-    params:                   
-        lr: 0.4               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.0000400
-
-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
-        - 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:

configs/HRNet/HRNet_W18_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W18_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/HRNet/HRNet_W30_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W30_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/HRNet/HRNet_W32_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W32_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/HRNet/HRNet_W40_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W40_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/HRNet/HRNet_W44_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W44_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/HRNet/HRNet_W48_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W48_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/HRNet/HRNet_W64_C.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'HRNet_W64_C'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 0.1 
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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:

configs/Inception/GoogLeNet.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "GoogLeNet"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
-   function: 'CosineWarmup'
-   params:
-       lr: 0.01
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.0001
-
-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:

configs/Inception/InceptionV3.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'InceptionV3'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                  
-        lr: 0.045               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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: 299
-        - 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: 16
-    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: 320
-        - CropImage:
-            size: 299
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:

configs/Inception/InceptionV4.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: 'InceptionV4'
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 200
-topk: 5
-image_shape: [3, 299, 299]
-
-use_mix: True
-ls_epsilon: 0.1
-
-LEARNING_RATE:
-    function: 'Cosine'          
-    params:                  
-        lr: 0.045               
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00010
-
-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: 299
-        - 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: 16
-    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: 320
-        - CropImage:
-            size: 299
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-        - ToCHWImage:

configs/MixNet/MixNet_L.yaml

-# just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
-    name: 'MixNet_L'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 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:

configs/MixNet/MixNet_M.yaml

-#just for finetune, the config for training on ImageNet is coming soon
-mode: 'train'
-ARCHITECTURE:
-    name: 'MixNet_M'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 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:

configs/MixNet/MixNet_S.yaml

-# just for finetune, the config for training on ImageNet is coming soon.
-mode: 'train'
-ARCHITECTURE:
-    name: 'MixNet_S'
-
-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: 'Piecewise'          
-    params:                   
-        lr: 0.1               
-        decay_epochs: [30, 60, 90] 
-        gamma: 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:

configs/MobileNetV1/MobileNetV1.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV1"
-
-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]
-
-LEARNING_RATE:
-   function: 'Piecewise'
-   params:
-       lr: 0.1
-       decay_epochs: [30, 60, 90]
-       gamma: 0.1
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00003
-
-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:
-
-

configs/MobileNetV1/MobileNetV1_x0_25.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV1_x0_25"
-
-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]
-
-LEARNING_RATE:
-   function: 'Piecewise'
-   params:
-       lr: 0.1
-       decay_epochs: [30, 60, 90]
-       gamma: 0.1
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00003
-
-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:
-
-

configs/MobileNetV1/MobileNetV1_x0_5.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV1_x0_5"
-
-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]
-
-LEARNING_RATE:
-   function: 'Piecewise'
-   params:
-       lr: 0.1
-       decay_epochs: [30, 60, 90]
-       gamma: 0.1
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00003
-
-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:
-
-

configs/MobileNetV1/MobileNetV1_x0_75.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV1_x0_75"
-
-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]
-
-LEARNING_RATE:
-   function: 'Piecewise'
-   params:
-       lr: 0.1
-       decay_epochs: [30, 60, 90]
-       gamma: 0.1
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00003
-
-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:
-
-

configs/MobileNetV2/MobileNetV2.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV2"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
-    function: 'Cosine'
-    params:
-        lr: 0.045
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00004
-
-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:
-
-

configs/MobileNetV2/MobileNetV2_x0_25.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV2_x0_25"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
-    function: 'Cosine'
-    params:
-        lr: 0.045
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00003
-
-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
-            ratio: [1.0, 1.0]
-        - 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:
-
-

configs/MobileNetV2/MobileNetV2_x0_5.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV2_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
-    function: 'Cosine'
-    params:
-        lr: 0.045
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00003
-
-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
-            ratio: [1.0, 1.0]
-        - 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:
-
-

configs/MobileNetV2/MobileNetV2_x0_75.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV2_x0_75"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
-    function: 'Cosine'
-    params:
-        lr: 0.045
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00004
-
-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:
-
-

configs/MobileNetV2/MobileNetV2_x1_5.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV2_x1_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
-    function: 'Cosine'
-    params:
-        lr: 0.045
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00004
-
-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:
-
-

configs/MobileNetV2/MobileNetV2_x2_0.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV2_x2_0"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-validate: True
-valid_interval: 1
-epochs: 240
-topk: 5
-image_shape: [3, 224, 224]
-
-
-LEARNING_RATE:
-    function: 'Cosine'
-    params:
-        lr: 0.045
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00004
-
-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:
-
-

configs/MobileNetV3/MobileNetV3_large_x0_35.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV3_large_x0_35"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
-    function: 'CosineWarmup'
-    params:
-        lr: 2.6
-        warmup_epoch: 5
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00002
-
-TRAIN:
-    batch_size: 4096
-    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:
-
-

configs/MobileNetV3/MobileNetV3_large_x0_5.yaml

-mode: 'train'
-ARCHITECTURE:
-    name: "MobileNetV3_large_x0_5"
-
-pretrained_model: ""
-model_save_dir: "./output/"
-classes_num: 1000
-total_images: 1281167
-save_interval: 1
-ls_epsilon: 0.1
-validate: True
-valid_interval: 1
-epochs: 360
-topk: 5
-image_shape: [3, 224, 224]
-
-LEARNING_RATE:
-    function: 'CosineWarmup'
-    params:
-        lr: 1.3
-        warmup_epoch: 5
-
-OPTIMIZER:
-    function: 'Momentum'
-    params:
-        momentum: 0.9
-    regularizer:
-        function: 'L2'
-        factor: 0.00002
-
-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:
-
-