add MobileNetV1, SwinTransformer models (#1869)

docs/tutorials/models/support_model_list.md

@@ -29,7 +29,14 @@
 | PP-LCNetV2_small | [PP-LCNetV2_small.yaml](../../../paddlex/configs/image_classification/PP-LCNetV2_small.yaml)|
 | PP-LCNetV2_base | [PP-LCNetV2_base.yaml](../../../paddlex/configs/image_classification/PP-LCNetV2_base.yaml)|
 | PP-LCNetV2_large | [PP-LCNetV2_large.yaml](../../../paddlex/configs/image_classification/PP-LCNetV2_large.yaml)|
-### 3.MobileNetV2 系列
+### 3.MobileNetV1 系列
+| 模型名称 | config |
+| :--- | :---: |
+| MobileNetV1_x0_25 | [MobileNetV1_x0_25.yaml](../../../paddlex/configs/image_classification/MobileNetV1_x0_25.yaml)|
+| MobileNetV1_x0_5 | [MobileNetV1_x0_5.yaml](../../../paddlex/configs/image_classification/MobileNetV1_x0_5.yaml)|
+| MobileNetV1_x0_75 | [MobileNetV1_x0_75.yaml](../../../paddlex/configs/image_classification/MobileNetV1_x0_75.yaml)|
+| MobileNetV1_x1_0 | [MobileNetV1_x1_0.yaml](../../../paddlex/configs/image_classification/MobileNetV1_x1_0.yaml)|
+### 4.MobileNetV2 系列
 | 模型名称 | config |
 | :--- | :---: |
 | MobileNetV2_x0_25 | [MobileNetV2_x0_25.yaml](../../../paddlex/configs/image_classification/MobileNetV2_x0_25.yaml)|
@@ -37,7 +44,7 @@
 | MobileNetV2_x1_0 | [MobileNetV2_x1_0.yaml](../../../paddlex/configs/image_classification/MobileNetV2_x1_0.yaml)|
 | MobileNetV2_x1_5 | [MobileNetV2_x1_5.yaml](../../../paddlex/configs/image_classification/MobileNetV2_x1_5.yaml)|
 | MobileNetV2_x2_0 | [MobileNetV2_x2_0.yaml](../../../paddlex/configs/image_classification/MobileNetV2_x2_0.yaml)|
-### 4.MobileNetV3 系列
+### 5.MobileNetV3 系列
 | 模型名称 | config |
 | :--- | :---: |
 | MobileNetV3_small_x0_35 | [MobileNetV3_small_x0_35.yaml](../../../paddlex/configs/image_classification/MobileNetV3_small_x0_35.yaml)|
@@ -50,22 +57,22 @@
 | MobileNetV3_large_x0_75 | [MobileNetV3_large_x0_75.yaml](../../../paddlex/configs/image_classification/MobileNetV3_large_x0_75.yaml)|
 | MobileNetV3_large_x1_0 | [MobileNetV3_large_x1_0.yaml](../../../paddlex/configs/image_classification/MobileNetV3_large_x1_0.yaml)|
 | MobileNetV3_large_x1_25 | [MobileNetV3_large_x1_25.yaml](../../../paddlex/configs/image_classification/MobileNetV3_large_x1_25.yaml)|
-### 5.PP-HGNet 系列
+### 6.PP-HGNet 系列
 | 模型名称 | config |
 | :--- | :---: |
 | PP-HGNet_small | [PP-HGNet_small.yaml](../../../paddlex/configs/image_classification/PP-HGNet_small.yaml)|
-### 6.PP-HGNetV2 系列
+### 7.PP-HGNetV2 系列
 | 模型名称 | config |
 | :--- | :---: |
 | PP-HGNetV2-B0 | [PP-HGNetV2-B0.yaml](../../../paddlex/configs/image_classification/PP-HGNetV2-B0.yaml)|
 | PP-HGNetV2-B4 | [PP-HGNetV2-B4.yaml](../../../paddlex/configs/image_classification/PP-HGNetV2-B4.yaml)|
 | PP-HGNetV2-B6 | [PP-HGNetV2-B6.yaml](../../../paddlex/configs/image_classification/PP-HGNetV2-B6.yaml)|
-### 7.CLIP 系列
+### 8.CLIP 系列
 | 模型名称 | config |
 | :--- | :---: |
 | CLIP_vit_base_patch16_224 | [CLIP_vit_base_patch16_224.yaml](../../../paddlex/configs/image_classification/CLIP_vit_base_patch16_224.yaml)|
 | CLIP_vit_large_patch14_224 | [CLIP_vit_large_patch14_224.yaml](../../../paddlex/configs/image_classification/CLIP_vit_large_patch14_224.yaml)|
-### 8.ConvNeXt 系列
+### 9.ConvNeXt 系列
 | 模型名称 | config |
 | :--- | :---: |
 | ConvNeXt_tiny | [ConvNeXt_tiny.yaml](../../../paddlex/configs/image_classification/ConvNeXt_tiny.yaml)|
@@ -74,10 +81,15 @@
 | ConvNeXt_base_384 | [ConvNeXt_base_384.yaml](../../../paddlex/configs/image_classification/ConvNeXt_base_384.yaml)|
 | ConvNeXt_large_224 | [ConvNeXt_large_224.yaml](../../../paddlex/configs/image_classification/ConvNeXt_large_224.yaml)|
 | ConvNeXt_large_384 | [ConvNeXt_large_384.yaml](../../../paddlex/configs/image_classification/ConvNeXt_large_384.yaml)|
-### 9.SwinTransformer系列
+### 10.SwinTransformer系列
 | 模型名称 | config |
 | :--- | :---: |
+| SwinTransformer_tiny_patch4_window7_224 | [SwinTransformer_tiny_patch4_window7_224.yaml](../../../paddlex/configs/image_classification/SwinTransformer_tiny_patch4_window7_224.yaml)|
+| SwinTransformer_small_patch4_window7_224 | [SwinTransformer_small_patch4_window7_224.yaml](../../../paddlex/configs/image_classification/SwinTransformer_small_patch4_window7_224.yaml)|
 | SwinTransformer_base_patch4_window7_224 | [SwinTransformer_base_patch4_window7_224.yaml](../../../paddlex/configs/image_classification/SwinTransformer_base_patch4_window7_224.yaml)|
+| SwinTransformer_base_patch4_window12_384 | [SwinTransformer_base_patch4_window12_384.yaml](../../../paddlex/configs/image_classification/SwinTransformer_base_patch4_window12_384.yaml)|
+| SwinTransformer_large_patch4_window7_224 | [SwinTransformer_large_patch4_window7_224.yaml](../../../paddlex/configs/image_classification/SwinTransformer_large_patch4_window7_224.yaml)|
+| SwinTransformer_large_patch4_window12_384 | [SwinTransformer_large_patch4_window12_384.yaml](../../../paddlex/configs/image_classification/SwinTransformer_large_patch4_window12_384.yaml)|
 ## 二、目标检测
 ### 1. PP-YOLOE_plus 系列
 | 模型名称 | config |

paddlex/configs/image_classification/MobileNetV1_x0_25.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: MobileNetV1_x0_25
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.1
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/MobileNetV1_x0_5.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: MobileNetV1_x0_5
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.1
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/MobileNetV1_x0_75.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: MobileNetV1_x0_75
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.1
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/MobileNetV1_x1_0.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: MobileNetV1_x1_0
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.1
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/SwinTransformer_base_patch4_window12_384.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: SwinTransformer_base_patch4_window12_384
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 32
+  learning_rate: 0.003
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/SwinTransformer_large_patch4_window12_384.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: SwinTransformer_large_patch4_window12_384
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 32
+  learning_rate: 0.003
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/SwinTransformer_large_patch4_window7_224.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: SwinTransformer_large_patch4_window7_224
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.003
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/SwinTransformer_small_patch4_window7_224.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: SwinTransformer_small_patch4_window7_224
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.003
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/configs/image_classification/SwinTransformer_tiny_patch4_window7_224.yaml

@@ -0,0 +1,38 @@
+Global:
+  model: SwinTransformer_tiny_patch4_window7_224
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/cls/cls_flowers_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert: 
+    enable: False
+    src_dataset_type: null
+  split: 
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 102
+  epochs_iters: 20
+  batch_size: 64
+  learning_rate: 0.003
+  pretrain_weight_path: null
+  warmup_steps: 5
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+  save_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 1
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification_001.jpg"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1

paddlex/modules/base/predictor/utils/official_models.py

@@ -115,9 +115,36 @@ MobileNetV2_x0_25_infer.tar",
     "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/MobileNetV2_x1_5_infer.tar",
     "MobileNetV2_x2_0":
     "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/MobileNetV2_x2_0_infer.tar",
+    "MobileNetV1_x0_25":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+MobileNetV1_x0_25_infer.tar",
+    "MobileNetV1_x0_5":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+MobileNetV1_x0_5_infer.tar",
+    "MobileNetV1_x0_75":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+MobileNetV1_x0_75_infer.tar",
+    "MobileNetV1_x1_0":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+MobileNetV1_x1_0_infer.tar",
+    "SwinTransformer_tiny_patch4_window7_224":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+SwinTransformer_tiny_patch4_window7_224_infer.tar",
+    "SwinTransformer_small_patch4_window7_224":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+SwinTransformer_small_patch4_window7_224_infer.tar",
     "SwinTransformer_base_patch4_window7_224":
     "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
 SwinTransformer_base_patch4_window7_224_infer.tar",
+    "SwinTransformer_base_patch4_window12_384":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+SwinTransformer_base_patch4_window12_384_infer.tar",
+    "SwinTransformer_large_patch4_window7_224":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+SwinTransformer_large_patch4_window7_224_infer.tar",
+    "SwinTransformer_large_patch4_window12_384":
+    "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/\
+SwinTransformer_large_patch4_window12_384_infer.tar",
     "PP-HGNet_small":
     "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0/PP-HGNet_small_infer.tar",
     "PP-HGNetV2-B0":

paddlex/modules/image_classification/model_list.py

@@ -21,6 +21,10 @@ MODELS = [
     'ConvNeXt_base_384',
     'ConvNeXt_large_224',
     'ConvNeXt_large_384',
+    'MobileNetV1_x0_25',
+    'MobileNetV1_x0_5',
+    'MobileNetV1_x0_75',
+    'MobileNetV1_x1_0',
     'MobileNetV2_x0_25',
     'MobileNetV2_x0_5',
     'MobileNetV2_x1_0',
@@ -62,5 +66,10 @@ MODELS = [
     'ResNet18_vd',
     'ResNet34_vd',
     'ResNet50_vd',
+    'SwinTransformer_tiny_patch4_window7_224',
+    'SwinTransformer_small_patch4_window7_224',
     'SwinTransformer_base_patch4_window7_224',
+    'SwinTransformer_base_patch4_window12_384',
+    'SwinTransformer_large_patch4_window7_224',
+    'SwinTransformer_large_patch4_window12_384',
 ]

paddlex/repo_apis/PaddleClas_api/cls/register.py

@@ -33,6 +33,24 @@ register_suite_info({
 
 ################ Models Using Universal Config ################
 register_model_info({
+    'model_name': 'SwinTransformer_tiny_patch4_window7_224',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR,
+                            'SwinTransformer_tiny_patch4_window7_224.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
+    'model_name': 'SwinTransformer_small_patch4_window7_224',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR,
+                            'SwinTransformer_small_patch4_window7_224.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
     'model_name': 'SwinTransformer_base_patch4_window7_224',
     'suite': 'Cls',
     'config_path': osp.join(PDX_CONFIG_DIR,
@@ -41,6 +59,33 @@ register_model_info({
 })
 
 register_model_info({
+    'model_name': 'SwinTransformer_base_patch4_window12_384',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR,
+                            'SwinTransformer_base_patch4_window12_384.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
+    'model_name': 'SwinTransformer_large_patch4_window7_224',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR,
+                            'SwinTransformer_large_patch4_window7_224.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
+    'model_name': 'SwinTransformer_large_patch4_window12_384',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR,
+                            'SwinTransformer_large_patch4_window12_384.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
     'model_name': 'PP-LCNet_x0_25',
     'suite': 'Cls',
     'config_path': osp.join(PDX_CONFIG_DIR, 'PP-LCNet_x0_25.yaml'),
@@ -237,6 +282,38 @@ register_model_info({
 })
 
 register_model_info({
+    'model_name': 'MobileNetV1_x0_25',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR, 'MobileNetV1_x0_25.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
+    'model_name': 'MobileNetV1_x0_5',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR, 'MobileNetV1_x0_5.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
+    'model_name': 'MobileNetV1_x0_75',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR, 'MobileNetV1_x0_75.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
+    'model_name': 'MobileNetV1_x1_0',
+    'suite': 'Cls',
+    'config_path': osp.join(PDX_CONFIG_DIR, 'MobileNetV1_x1_0.yaml'),
+    'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+    'infer_config': 'deploy/configs/inference_cls.yaml'
+})
+
+register_model_info({
     'model_name': 'MobileNetV2_x0_25',
     'suite': 'Cls',
     'config_path': osp.join(PDX_CONFIG_DIR, 'MobileNetV2_x0_25.yaml'),

paddlex/repo_apis/PaddleClas_api/configs/MobileNetV1_x0_25.yaml

@@ -0,0 +1,142 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 120
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: MobileNetV1_x0_25
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Piecewise
+    learning_rate: 0.1
+    decay_epochs: [30, 60, 90]
+    values: [0.1, 0.01, 0.001, 0.0001]
+  regularizer:
+    name: 'L2'
+    coeff: 0.00003
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/MobileNetV1_x0_5.yaml

@@ -0,0 +1,142 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 120
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: MobileNetV1_x0_5
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Piecewise
+    learning_rate: 0.1
+    decay_epochs: [30, 60, 90]
+    values: [0.1, 0.01, 0.001, 0.0001]
+  regularizer:
+    name: 'L2'
+    coeff: 0.00003
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/MobileNetV1_x0_75.yaml

@@ -0,0 +1,142 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 120
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: MobileNetV1_x0_75
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Piecewise
+    learning_rate: 0.1
+    decay_epochs: [30, 60, 90]
+    values: [0.1, 0.01, 0.001, 0.0001]
+  regularizer:
+    name: 'L2'
+    coeff: 0.00003
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/MobileNetV1_x1_0.yaml

@@ -0,0 +1,144 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 120
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: MobileNetV1
+  class_num: 1000
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Piecewise
+    learning_rate: 0.1
+    decay_epochs: [30, 60, 90]
+    values: [0.1, 0.01, 0.001, 0.0001]
+  regularizer:
+    name: 'L2'
+    coeff: 0.00003
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 5]
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/SwinTransformer_base_patch4_window12_384.yaml

@@ -0,0 +1,172 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 384, 384]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: SwinTransformer_base_patch4_window12_384
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1e-8
+  weight_decay: 0.05
+  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm 
+  one_dim_param_no_weight_decay: True
+  lr:
+    # for 8 cards
+    name: Cosine
+    learning_rate: 1e-3
+    eta_min: 2e-5
+    warmup_epoch: 20
+    warmup_start_lr: 2e-6
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 384
+            interpolation: bicubic
+            backend: pil
+        - RandFlipImage:
+            flip_code: 1
+        - TimmAutoAugment:
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: 384 
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.25
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+      batch_transform_ops:
+        - OpSampler:
+            MixupOperator:
+              alpha: 0.8
+              prob: 0.5
+            CutmixOperator:
+              alpha: 1.0
+              prob: 0.5
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 438
+            interpolation: bicubic
+            backend: pil
+        - CropImage:
+            size: 384
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 438
+        interpolation: bicubic
+        backend: pil
+    - 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:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/SwinTransformer_large_patch4_window12_384.yaml

@@ -0,0 +1,172 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 384, 384]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: SwinTransformer_large_patch4_window12_384
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1e-8
+  weight_decay: 0.05
+  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm 
+  one_dim_param_no_weight_decay: True
+  lr:
+    # for 8 cards
+    name: Cosine
+    learning_rate: 1e-3
+    eta_min: 2e-5
+    warmup_epoch: 20
+    warmup_start_lr: 2e-6
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 384
+            interpolation: bicubic
+            backend: pil
+        - RandFlipImage:
+            flip_code: 1
+        - TimmAutoAugment:
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: 384 
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.25
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+      batch_transform_ops:
+        - OpSampler:
+            MixupOperator:
+              alpha: 0.8
+              prob: 0.5
+            CutmixOperator:
+              alpha: 1.0
+              prob: 0.5
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 438
+            interpolation: bicubic
+            backend: pil
+        - CropImage:
+            size: 384
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 438
+        interpolation: bicubic
+        backend: pil
+    - 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:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/SwinTransformer_large_patch4_window7_224.yaml

@@ -0,0 +1,172 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: SwinTransformer_large_patch4_window7_224
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1e-8
+  weight_decay: 0.05
+  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm 
+  one_dim_param_no_weight_decay: True
+  lr:
+    # for 8 cards
+    name: Cosine
+    learning_rate: 1e-3
+    eta_min: 2e-5
+    warmup_epoch: 20
+    warmup_start_lr: 2e-6
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+            interpolation: bicubic
+            backend: pil
+        - RandFlipImage:
+            flip_code: 1
+        - TimmAutoAugment:
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.25
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+      batch_transform_ops:
+        - OpSampler:
+            MixupOperator:
+              alpha: 0.8
+              prob: 0.5
+            CutmixOperator:
+              alpha: 1.0
+              prob: 0.5
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+            interpolation: bicubic
+            backend: pil
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+        interpolation: bicubic
+        backend: pil
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/SwinTransformer_small_patch4_window7_224.yaml

@@ -0,0 +1,172 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: SwinTransformer_small_patch4_window7_224
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1e-8
+  weight_decay: 0.05
+  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm 
+  one_dim_param_no_weight_decay: True
+  lr:
+    # for 8 cards
+    name: Cosine
+    learning_rate: 1e-3
+    eta_min: 2e-5
+    warmup_epoch: 20
+    warmup_start_lr: 2e-6
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+            interpolation: bicubic
+            backend: pil
+        - RandFlipImage:
+            flip_code: 1
+        - TimmAutoAugment:
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.25
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+      batch_transform_ops:
+        - OpSampler:
+            MixupOperator:
+              alpha: 0.8
+              prob: 0.5
+            CutmixOperator:
+              alpha: 1.0
+              prob: 0.5
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+            interpolation: bicubic
+            backend: pil
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+        interpolation: bicubic
+        backend: pil
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]

paddlex/repo_apis/PaddleClas_api/configs/SwinTransformer_tiny_patch4_window7_224.yaml

@@ -0,0 +1,172 @@
+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 300
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+
+
+# mixed precision
+AMP:
+  use_amp: False
+  use_fp16_test: False
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  use_promote: False
+  # O1: mixed fp16, O2: pure fp16
+  level: O1
+
+
+# model architecture
+Arch:
+  name: SwinTransformer_tiny_patch4_window7_224
+  class_num: 102
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1e-8
+  weight_decay: 0.05
+  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm 
+  one_dim_param_no_weight_decay: True
+  lr:
+    # for 8 cards
+    name: Cosine
+    learning_rate: 1e-3
+    eta_min: 2e-5
+    warmup_epoch: 20
+    warmup_start_lr: 2e-6
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+            interpolation: bicubic
+            backend: pil
+        - RandFlipImage:
+            flip_code: 1
+        - TimmAutoAugment:
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.25
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+      batch_transform_ops:
+        - OpSampler:
+            MixupOperator:
+              alpha: 0.8
+              prob: 0.5
+            CutmixOperator:
+              alpha: 1.0
+              prob: 0.5
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/ILSVRC2012/
+      cls_label_path: ./dataset/ILSVRC2012/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+            interpolation: bicubic
+            backend: pil
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+        interpolation: bicubic
+        backend: pil
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Eval:
+    - TopkAcc:
+        topk: [1, 5]