detection models with ir promblems (#1983)

* detection models with ir promblems

* add export model_path in config

---------

Co-authored-by: Sunflower7788 <263037929@qq.com>

README.md

@@ -70,7 +70,7 @@ PaddleX 3.0 覆盖了 16 条产业级模型产线，其中 9 条基础产线可
     <td>通用目标检测</td>
     <td>目标检测</td>
     <td>PicoDet-S<br/>PicoDet-L<details>
-    <summary><b>more</b></summary><br/>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<br/>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>YOLOv3-DarkNet53<br/>YOLOv3-MobileNetV3<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOX-L<br/>YOLOX-M<br/>YOLOX-N<br/>YOLOX-S<br/>YOLOX-T<br/>YOLOX-X</details></td>
+    <summary><b>more</b></summary><br/>PP-YOLOE_plus-S<br/>PP-YOLOE_plus-M<br/>PP-YOLOE_plus-L<br/>PP-YOLOE_plus-X<br/>RT-DETR-L<br/>RT-DETR-H<br/>RT-DETR-X<br/>RT-DETR-R18<br/>RT-DETR-R50<br/>YOLOv3-DarkNet53<br/>YOLOv3-MobileNetV3<br/>YOLOv3-ResNet50_vd_DCN<br/>YOLOX-L<br/>YOLOX-M<br/>YOLOX-N<br/>YOLOX-S<br/>YOLOX-T<br/>YOLOX-X<br/>FasterRCNN-ResNet34-FPN<br/>FasterRCNN-ResNet50<br/>FasterRCNN-ResNet50-FPN<br/>FasterRCNN-ResNet50-vd-FPN<br/>FasterRCNN-ResNet50-vd-SSLDv2-FPN<br/>FasterRCNN-ResNet101<br/>FasterRCNN-ResNet101-FPN<br/>FasterRCNN-ResNeXt101-vd-FPN<br/>FasterRCNN-Swin-Tiny-FPN<br/>Cascade-FasterRCNN-ResNet50-FPN<br/>Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN</details></td>
   </tr>
   <tr>
     <td>基础产线</td>

docs/tutorials/models/support_model_list.md

@@ -143,6 +143,23 @@
 | YOLOX-S | [YOLOX-S.yaml](../../../paddlex/configs/object_detection/YOLOX-S.yaml)|
 | YOLOX-T | [YOLOX-T.yaml](../../../paddlex/configs/object_detection/YOLOX-T.yaml)|
 | YOLOX-X | [YOLOX-X.yaml](../../../paddlex/configs/object_detection/YOLOX-X.yaml)|
+### 6. FasterRCNN 系列
+| 模型名称 | config |
+| :--- | :---: |
+| FasterRCNN-ResNet34-FPN | [FasterRCNN-ResNet34-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet34-FPN.yaml)|
+| FasterRCNN-ResNet50 | [FasterRCNN-ResNet50.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet50.yaml)|
+| FasterRCNN-ResNet50-FPN | [FasterRCNN-ResNet50-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet50-FPN.yaml)|
+| FasterRCNN-ResNet50-vd-FPN | [FasterRCNN-ResNet50-vd-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-FPN.yaml)|
+| FasterRCNN-ResNet50-vd-SSLDv2-FPN | [FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
+| FasterRCNN-ResNet101 | [FasterRCNN-ResNet101.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet101.yaml)|
+| FasterRCNN-ResNet101-FPN | [FasterRCNN-ResNet101-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNet101-FPN.yaml)|
+| FasterRCNN-ResNeXt101-vd-FPN | [FasterRCNN-ResNeXt101-vd-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-ResNeXt101-vd-FPN.yaml)|
+| FasterRCNN-Swin-Tiny-FPN | [FasterRCNN-Swin-Tiny-FPN.yaml](../../../paddlex/configs/object_detection/FasterRCNN-Swin-Tiny-FPN.yaml)|
+### 7. Cascade 系列
+| 模型名称 | config |
+| :--- | :---: |
+| Cascade-FasterRCNN-ResNet50-FPN | [Cascade-FasterRCNN-ResNet50-FPN.yaml](../../../paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-FPN.yaml)|
+| Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN | [Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml](../../../paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml)|
 ## 三、实例分割
 ### 1.Mask-RT-DETR 系列
 | 模型名称 | config |

paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-FPN.yaml

@@ -0,0 +1,40 @@
+Global:
+  model: Cascade-FasterRCNN-ResNet50-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_fpn_1x_coco.pdparams

paddlex/configs/object_detection/Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_vd_fpn_ssld_2x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNeXt101-vd-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNeXt101-vd-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet101-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet101-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_fpn_2x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet101.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet101
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet34-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet34-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet50-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet50-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet50-vd-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet50-vd-SSLDv2-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_ssld_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-ResNet50.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-ResNet50
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 5
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_1x_coco.pdparams

paddlex/configs/object_detection/FasterRCNN-Swin-Tiny-FPN.yaml

@@ -0,0 +1,41 @@
+Global:
+  model: FasterRCNN-Swin-Tiny-FPN
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/det/det_coco_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: 4
+  epochs_iters: 50
+  batch_size: 2
+  learning_rate: #0.08
+  pretrain_weight_path: null
+  warmup_steps: #100
+  resume_path: null
+  log_interval: 10
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model.pdparams"
+  log_interval: 10
+
+Predict:
+  model_dir: "output/best_model"
+  input_path: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_object_detection_002.png"
+  kernel_option:
+    run_mode: paddle
+    batch_size: 1
+
+
+Export:
+  weight_path: https://paddledet.bj.bcebos.com/models/faster_rcnn_swin_tiny_fpn_1x_coco.pdparams

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

@@ -187,6 +187,17 @@ openatom_rec_svtrv2_ch_infer.tar",
     "PicoDet_layout_1x": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/PicoDet-L_layout_infer.tar",
     "SLANet": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/SLANet_infer.tar",
     "LaTeX_OCR_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/LaTeX_OCR_rec_infer.tar",
+    "FasterRCNN-ResNet34-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet34-FPN_infer.tar",
+    "FasterRCNN-ResNet50": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet50_infer.tar",
+    "FasterRCNN-ResNet50-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet50-FPN_infer.tar",
+    "FasterRCNN-ResNet50-vd-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet50-vd-FPN_infer.tar",
+    "FasterRCNN-ResNet50-vd-SSLDv2-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet50-vd-SSLDv2-FPN_infer.tar",
+    "FasterRCNN-ResNet101": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet101_infer.tar",
+    "FasterRCNN-ResNet101-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNet101-FPN_infer.tar",
+    "FasterRCNN-ResNeXt101-vd-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-ResNeXt101-vd-FPN_infer.tar",
+    "FasterRCNN-Swin-Tiny-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/FasterRCNN-Swin-Tiny-FPN_infer.tar",
+    "Cascade-FasterRCNN-ResNet50-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/Cascade-FasterRCNN-ResNet50-FPN_infer.tar",
+    "Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN_infer.tar",
     "UVDoc": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/UVDoc_infer.tar",
     "DLinear": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/DLinear_infer.tar",
     "NLinear": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b1/NLinear_infer.tar",

paddlex/modules/object_detection/model_list.py

@@ -35,4 +35,15 @@ MODELS = [
     "YOLOX-S",
     "YOLOX-T",
     "YOLOX-X",
+    "FasterRCNN-ResNet34-FPN",
+    "FasterRCNN-ResNet50",
+    "FasterRCNN-ResNet50-FPN",
+    "FasterRCNN-ResNet50-vd-FPN",
+    "FasterRCNN-ResNet50-vd-SSLDv2-FPN",
+    "FasterRCNN-ResNet101",
+    "FasterRCNN-ResNet101-FPN",
+    "FasterRCNN-ResNeXt101-vd-FPN",
+    "FasterRCNN-Swin-Tiny-FPN",
+    "Cascade-FasterRCNN-ResNet50-FPN",
+    "Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN",
 ]

paddlex/repo_apis/PaddleDetection_api/configs/Cascade-FasterRCNN-ResNet50-FPN.yaml

@@ -0,0 +1,182 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: CascadeRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+
+CascadeRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: CascadeHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 2000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+CascadeHead:
+  head: CascadeTwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  cascade_iou: [0.5, 0.6, 0.7]
+  use_random: True
+
+CascadeTwoFCHead:
+  out_channel: 1024
+
+BBoxPostProcess:
+  decode:
+    name: RCNNBox
+    prior_box_var: [30.0, 30.0, 15.0, 15.0]
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.001
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml

@@ -0,0 +1,186 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: CascadeRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_v2_pretrained.pdparams
+
+
+CascadeRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: CascadeHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  lr_mult_list: [0.05, 0.05, 0.1, 0.15]
+
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 2000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+CascadeHead:
+  head: CascadeTwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  cascade_iou: [0.5, 0.6, 0.7]
+  use_random: True
+
+CascadeTwoFCHead:
+  out_channel: 1024
+
+BBoxPostProcess:
+  decode:
+    name: RCNNBox
+    prior_box_var: [30.0, 30.0, 15.0, 15.0]
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 24
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [12, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNeXt101-vd-FPN.yaml

@@ -0,0 +1,183 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNeXt101_vd_64x4d_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # for ResNeXt: groups, base_width, base_channels
+  depth: 101
+  groups: 64
+  base_width: 4
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet101-FPN.yaml

@@ -0,0 +1,180 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet101_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet101.yaml

@@ -0,0 +1,173 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: -1}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: -1}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: -1}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet101_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [2]
+  num_stages: 3
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [32, 64, 128, 256, 512]
+    strides: [16]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 12000
+    post_nms_top_n: 2000
+    topk_after_collect: False
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 6000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: Res5Head
+  roi_extractor:
+    resolution: 14
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+  with_pool: true
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet34-FPN.yaml

@@ -0,0 +1,180 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet34_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # index 0 stands for res2
+  depth: 34
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet50-FPN.yaml

@@ -0,0 +1,180 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet50-vd-FPN.yaml

@@ -0,0 +1,181 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml

@@ -0,0 +1,181 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+ResNet:
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  lr_mult_list: [0.05, 0.05, 0.1, 0.15]
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-ResNet50.yaml

@@ -0,0 +1,173 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: -1}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: -1}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: -1}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_cos_pretrained.pdparams
+
+FasterRCNN:
+  backbone: ResNet
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [2]
+  num_stages: 3
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [32, 64, 128, 256, 512]
+    strides: [16]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 12000
+    post_nms_top_n: 2000
+    topk_after_collect: False
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 6000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: Res5Head
+  roi_extractor:
+    resolution: 14
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+  with_pool: true
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/configs/FasterRCNN-Swin-Tiny-FPN.yaml

@@ -0,0 +1,179 @@
+# Runtime
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+log_iter: 20
+save_dir: output
+snapshot_epoch: 1
+print_flops: false
+print_params: false
+use_ema: true
+
+# Dataset
+metric: COCO
+num_classes: 80
+
+TrainDataset:
+  name: COCODataSet
+  image_dir: train2017
+  anno_path: annotations/instances_train2017.json
+  dataset_dir: dataset/coco
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODataSet
+  image_dir: val2017
+  anno_path: annotations/instances_val2017.json
+  dataset_dir: dataset/coco
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instances_val2017.json # also support txt (like VOC's label_list.txt)
+  dataset_dir: dataset/coco # if set, anno_path will be 'dataset_dir/anno_path'
+
+
+# Reader
+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomResizeCrop: {resizes: [400, 500, 600], cropsizes: [[384, 600], ], prob: 0.5}
+  - RandomResize: {target_size: [[480, 1333], [512, 1333], [544, 1333], [576, 1333], [608, 1333], [640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], keep_ratio: True, interp: 2}
+  - RandomFlip: {prob: 0.5}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 2
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+
+TestReader:
+  inputs_def:
+    image_shape: [-1, 3, 640, 640]
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: 640, keep_ratio: True}
+  - Pad: {size: 640}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+
+# Model
+architecture: FasterRCNN
+# pretrain_weights: # rewrite in SwinTransformer.pretrained in ppdet/modeling/backbones/swin_transformer.py
+
+FasterRCNN:
+  backbone: SwinTransformer
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  bbox_post_process: BBoxPostProcess
+
+SwinTransformer:
+  arch: 'swin_T_224'
+  ape: false
+  drop_path_rate: 0.1
+  patch_norm: true
+  out_indices: [0, 1, 2, 3]
+  pretrained: https://paddledet.bj.bcebos.com/models/pretrained/swin_tiny_patch4_window7_224_22kto1k_pretrained.pdparams
+
+FPN:
+  out_channel: 256
+
+RPNHead:
+  anchor_generator:
+    aspect_ratios: [0.5, 1.0, 2.0]
+    anchor_sizes: [[32], [64], [128], [256], [512]]
+    strides: [4, 8, 16, 32, 64]
+  rpn_target_assign:
+    batch_size_per_im: 256
+    fg_fraction: 0.5
+    negative_overlap: 0.3
+    positive_overlap: 0.7
+    use_random: True
+  train_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 2000
+    post_nms_top_n: 1000
+    topk_after_collect: True
+  test_proposal:
+    min_size: 0.0
+    nms_thresh: 0.7
+    pre_nms_top_n: 1000
+    post_nms_top_n: 1000
+
+
+BBoxHead:
+  head: TwoFCHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+BBoxAssigner:
+  batch_size_per_im: 512
+  bg_thresh: 0.5
+  fg_thresh: 0.5
+  fg_fraction: 0.25
+  use_random: True
+
+TwoFCHead:
+  out_channel: 1024
+
+BBoxPostProcess:
+  decode: RCNNBox
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    score_threshold: 0.05
+    nms_threshold: 0.5
+
+# Optimizer
+epoch: 12
+
+LearningRate:
+  base_lr: 0.0001
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+OptimizerBuilder:
+  clip_grad_by_norm: 1.0
+  optimizer:
+    type: AdamW
+    weight_decay: 0.05
+    param_groups:
+      - params: ['absolute_pos_embed', 'relative_position_bias_table', 'norm']
+        weight_decay: 0.0
+
+# Exporting the model
+export:
+  post_process: True  # Whether post-processing is included in the network when export model.
+  nms: True           # Whether NMS is included in the network when export model.
+  benchmark: False    # It is used to testing model performance, if set `True`, post-process and NMS will not be exported.
+  fuse_conv_bn: False

paddlex/repo_apis/PaddleDetection_api/object_det/register.py

@@ -373,3 +373,181 @@ register_model_info(
         "hpi_config_path": HPI_CONFIG_DIR / "YOLOX-X.yaml",
     }
 )
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet34-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet34-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet50',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet50.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet50-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet50-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet50-vd-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet50-vd-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet50-vd-SSLDv2-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet101',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet101.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNet101-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNet101-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-ResNeXt101-vd-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-ResNeXt101-vd-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'FasterRCNN-Swin-Tiny-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'FasterRCNN-Swin-Tiny-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'Cascade-FasterRCNN-ResNet50-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'Cascade-FasterRCNN-ResNet50-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+
+register_model_info(
+    {
+        'model_name': 'Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN',
+        'suite': 'Det',
+        'config_path': osp.join(PDX_CONFIG_DIR, 'Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN.yaml'),
+        'supported_apis': ['train', 'evaluate', 'predict', 'export', 'infer'],
+        'supported_dataset_types': ['COCODetDataset'],
+        'supported_train_opts': {
+            'device': ['cpu', 'gpu_nxcx', 'xpu', 'npu', 'mlu'],
+            'dy2st': False,
+            'amp': ['OFF']
+        },
+    }
+)
+
+