refine dygraph config (#2051)

* refine dygraph config, test=dygraph

* fix fcos config

dygraph/configs/cascade_mask_rcnn_r50_fpn_1x_coco.yml

-_BASE_: [
-  './_base_/models/cascade_mask_rcnn_r50_fpn.yml',
-  './_base_/optimizers/rcnn_1x.yml',
-  './_base_/datasets/coco_instance.yml',
-  './_base_/readers/mask_fpn_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/cascade_rcnn/README.md

+# Cascade R-CNN: High Quality Object Detection and Instance Segmentation
+
+## Model Zoo
+
+| 骨架网络             | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP |                           下载                          | 配置文件 |
+| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
+| ResNet50-FPN         | Cascade Faster         |    1    |   1x    |     ----     |  41.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_faster_rcnn_r50_fpn_1x_coco.yml) |
+| ResNet50-FPN         | Cascade Mask         |    1    |   1x    |     ----     |  41.6  |    35.3    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
+
+## Citations
+```
+@article{Cai_2019,
+   title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
+   ISSN={1939-3539},
+   url={http://dx.doi.org/10.1109/tpami.2019.2956516},
+   DOI={10.1109/tpami.2019.2956516},
+   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
+   author={Cai, Zhaowei and Vasconcelos, Nuno},
+   year={2019},
+   pages={1–1}
+}
+```

dygraph/configs/_base_/models/cascade_mask_rcnn_r50_fpn.yml → dygraph/configs/cascade_rcnn/_base_/cascade_mask_rcnn_r50_fpn.yml

 architecture: CascadeRCNN
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
-weights: output/cascade_mask_rcnn_r50_fpn_1x_coco/model_final
 load_static_weights: True
 roi_stages: 3
 

dygraph/configs/_base_/models/cascade_rcnn_r50_fpn.yml → dygraph/configs/cascade_rcnn/_base_/cascade_rcnn_r50_fpn.yml

 architecture: CascadeRCNN
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
-weights: output/cascade_rcnn_r50_fpn_1x_coco/model_final
 load_static_weights: True
 roi_stages: 3
 

dygraph/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_mask_rcnn_r50_fpn.yml',
+  '_base_/cascade_mask_fpn_reader.yml',
+]
+weights: output/cascade_mask_rcnn_r50_fpn_1x_coco/model_final

dygraph/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/cascade_rcnn_r50_fpn.yml',
+  '_base_/cascade_fpn_reader.yml',
+]
+weights: output/cascade_rcnn_r50_fpn_1x_coco/model_final

dygraph/configs/cascade_rcnn_r50_fpn_1x_coco.yml

-_BASE_: [
-  './_base_/models/cascade_rcnn_r50_fpn.yml',
-  './_base_/optimizers/rcnn_1x.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/faster_fpn_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/faster_rcnn/README.md

+# Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
+
+## Model Zoo
+
+| 骨架网络             | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP |                           下载                          | 配置文件 |
+| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
+| ResNet50             | Faster         |    1    |   1x    |     ----     |  35.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn_r50_1x_coco.yml) |
+| ResNet50-FPN         | Faster         |    1    |   1x    |     ----     |  37.0  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn_r50_fpn_1x_coco.yml) |
+
+## Citations
+```
+@article{Ren_2017,
+   title={Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks},
+   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
+   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
+   author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
+   year={2017},
+   month={Jun},
+}
+```

dygraph/configs/faster_rcnn/_base_/faster_fpn_reader.yml

+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - DecodeOp: { }
+  - RandomFlipImage: {prob: 0.5}
+  - NormalizeImage: {is_channel_first: false, is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - ResizeImage: {target_size: 800, max_size: 1333, interp: 1, use_cv2: true}
+  - Permute: {to_bgr: false, channel_first: true}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32, use_padded_im_info: false, pad_gt: true}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+
+
+EvalReader:
+  sample_transforms:
+  - DecodeOp: { }
+  - NormalizeImageOp: { is_scale: true, mean: [ 0.485,0.456,0.406 ], std: [ 0.229, 0.224,0.225 ] }
+  - ResizeOp: { interp: 1, target_size: [ 800, 1333 ], keep_ratio: True }
+  - PermuteOp: { }
+  batch_transforms:
+  - PadBatchOp: { pad_to_stride: 32, pad_gt: false }
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+  drop_empty: false
+
+
+TestReader:
+  sample_transforms:
+  - DecodeOp: { }
+  - NormalizeImageOp: { is_scale: true, mean: [ 0.485,0.456,0.406 ], std: [ 0.229, 0.224,0.225 ] }
+  - ResizeOp: { interp: 1, target_size: [ 800, 1333 ], keep_ratio: True }
+  - PermuteOp: { }
+  batch_transforms:
+  - PadBatchOp: { pad_to_stride: 32, pad_gt: false }
+  batch_size: 1
+  shuffle: false
+  drop_last: false

dygraph/configs/_base_/models/faster_rcnn_r50.yml → dygraph/configs/faster_rcnn/_base_/faster_rcnn_r50.yml

 architecture: FasterRCNN
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
-weights: output/faster_rcnn_r50_1x_coco/model_final.pdparams
 load_static_weights: True
 
 # Model Achitecture

dygraph/configs/_base_/models/faster_rcnn_r50_fpn.yml → dygraph/configs/faster_rcnn/_base_/faster_rcnn_r50_fpn.yml

 architecture: FasterRCNN
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
-weights: output/faster_rcnn_r50_fpn_1x_coco/model_final.pdparams
 load_static_weights: True
 
 # Model Achitecture

dygraph/configs/faster_rcnn/_base_/optimizer_1x.yml

+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2

dygraph/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/faster_rcnn_r50.yml',
+  '_base_/faster_reader.yml',
+]
+weights: output/faster_rcnn_r50_1x_coco/model_final

dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/faster_rcnn_r50_fpn.yml',
+  '_base_/faster_fpn_reader.yml',
+]
+weights: output/faster_rcnn_r50_fpn_1x_coco/model_final

dygraph/configs/faster_rcnn_r50_1x_coco.yml

-_BASE_: [
-  './_base_/models/faster_rcnn_r50.yml',
-  './_base_/optimizers/rcnn_1x.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/faster_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/faster_rcnn_r50_fpn_1x_coco.yml

-_BASE_: [
-  './_base_/models/faster_rcnn_r50_fpn.yml',
-  './_base_/optimizers/rcnn_1x.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/faster_fpn_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/fcos/fcos_r50_fpn_1x_coco.yml

 _BASE_: [
-  '../_base_/datasets/coco_detection.yml', 
-  '../_base_/runtime.yml',
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
   '_base_/fcos_r50_fpn.yml',
   '_base_/optimizer_1x.yml',
   '_base_/fcos_reader.yml',

dygraph/configs/mask_rcnn/README.md

+# Mask R-CNN
+
+## Model Zoo
+
+| 骨架网络             | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP |                           下载                          | 配置文件 |
+| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
+| ResNet50             | Mask         |    1    |   1x    |     ----     |  36.4  |    31.9    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn_r50_1x_coco.yml) |
+| ResNet50-FPN         | Mask         |    1    |   1x    |     ----     |  38.3  |    34.5    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn_r50_fpn_1x_coco.yml) |
+
+## Citations
+```
+@article{He_2017,
+   title={Mask R-CNN},
+   journal={2017 IEEE International Conference on Computer Vision (ICCV)},
+   publisher={IEEE},
+   author={He, Kaiming and Gkioxari, Georgia and Dollar, Piotr and Girshick, Ross},
+   year={2017},
+   month={Oct}
+}
+```

dygraph/configs/mask_rcnn/_base_/mask_fpn_reader.yml

+worker_num: 2
+TrainReader:
+  sample_transforms:
+  - DecodeOp: {}
+  - RandomFlipImage: {prob: 0.5, is_mask_flip: true}
+  - NormalizeImage: {is_channel_first: false, is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - ResizeImage: {target_size: 800, max_size: 1333, interp: 1, use_cv2: true}
+  - Permute: {to_bgr: false, channel_first: true}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32, use_padded_im_info: false, pad_gt: true}
+  batch_size: 1
+  shuffle: true
+  drop_last: true
+
+
+EvalReader:
+  sample_transforms:
+  - DecodeOp: {}
+  - NormalizeImageOp: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - ResizeOp: {interp: 1, target_size: [800, 1333], keep_ratio: True}
+  - PermuteOp: {}
+  batch_transforms:
+  - PadBatchOp: {pad_to_stride: 32, pad_gt: false}
+  batch_size: 1
+  shuffle: false
+  drop_last: false
+  drop_empty: false
+
+
+TestReader:
+  sample_transforms:
+  - DecodeOp: {}
+  - NormalizeImageOp: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - ResizeOp: {interp: 1, target_size: [800, 1333], keep_ratio: True}
+  - PermuteOp: {}
+  batch_transforms:
+  - PadBatchOp: {pad_to_stride: 32, pad_gt: false}
+  batch_size: 1
+  shuffle: false
+  drop_last: false

dygraph/configs/_base_/models/mask_rcnn_r50.yml → dygraph/configs/mask_rcnn/_base_/mask_rcnn_r50.yml

 architecture: MaskRCNN
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
-weights: output/mask_rcnn_r50_fpn_1x/model_final
 load_static_weights: True
 
 # Model Achitecture

dygraph/configs/_base_/models/mask_rcnn_r50_fpn.yml → dygraph/configs/mask_rcnn/_base_/mask_rcnn_r50_fpn.yml

 architecture: MaskRCNN
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
-weights: output/mask_rcnn_r50_fpn_1x/model_final
 load_static_weights: True
 
 # Model Achitecture

dygraph/configs/mask_rcnn/_base_/optimizer_1x.yml

+epoch: 12
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 500
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0001
+    type: L2

dygraph/configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/mask_rcnn_r50.yml',
+  '_base_/mask_reader.yml',
+]
+weights: output/mask_rcnn_r50_1x_coco/model_final

dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1x.yml',
+  '_base_/mask_rcnn_r50_fpn.yml',
+  '_base_/mask_fpn_reader.yml',
+]
+weights: output/mask_rcnn_r50_fpn_1x_coco/model_final

dygraph/configs/mask_rcnn_r50_1x_coco.yml

-_BASE_: [
-  './_base_/models/mask_rcnn_r50.yml',
-  './_base_/optimizers/rcnn_1x.yml',
-  './_base_/datasets/coco_instance.yml',
-  './_base_/readers/mask_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/mask_rcnn_r50_fpn_1x_coco.yml

-_BASE_: [
-  './_base_/models/mask_rcnn_r50_fpn.yml',
-  './_base_/optimizers/rcnn_1x.yml',
-  './_base_/datasets/coco_instance.yml',
-  './_base_/readers/mask_fpn_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/ssd/README.md

+# SSD: Single Shot MultiBox Detector
+
+## Model Zoo
+
+### SSD on Pascal VOC
+
+| 骨架网络        | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP |                           下载                          | 配置文件 |
+| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
+| VGG             | SSD            |    8    |   240e    |     ----     |  78.2  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/ssd_vgg16_300_240e_voc.yml) |
+
+**注意：** SSD使用4GPU训练，训练240个epoch
+
+## Citations
+```
+@article{Liu_2016,
+   title={SSD: Single Shot MultiBox Detector},
+   journal={ECCV},
+   author={Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and Berg, Alexander C.},
+   year={2016},
+}
+```

dygraph/configs/_base_/models/ssd_mobilenet_v1_300.yml → dygraph/configs/ssd/_base_/ssd_mobilenet_v1_300.yml

 architecture: SSD
 pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/ssd_mobilenet_v1_coco_pretrained.tar
-weights: output/ssd_mobilenetv1/model_final
+load_static_weights: True
 
 SSD:
   backbone: MobileNet

dygraph/configs/_base_/models/ssd_vgg16_300.yml → dygraph/configs/ssd/_base_/ssd_vgg16_300.yml

 architecture: SSD
 pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/dygraph/VGG16_caffe_pretrained.pdparams
-weights: output/ssd_vgg16/model_final
+load_static_weights: True
 
 # Model Achitecture
 SSD:

dygraph/configs/_base_/models/ssdlite_mobilenet_v1_300.yml → dygraph/configs/ssd/_base_/ssdlite_mobilenet_v1_300.yml

 architecture: SSD
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_ssld_pretrained.tar
-weights: output/ssdlite_mobilenet_v1/model_final
+load_static_weights: True
 
 SSD:
   backbone: MobileNet

dygraph/configs/_base_/models/ssdlite_mobilenet_v3_large_320.yml → dygraph/configs/ssd/_base_/ssdlite_mobilenet_v3_large_320.yml

 architecture: SSD
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_pretrained.tar
-weights: output/ssdlite_mobilenet_v3_large/model_final
+load_static_weights: True
 
 SSD:
   backbone: MobileNetV3

dygraph/configs/_base_/models/ssdlite_mobilenet_v3_small_320.yml → dygraph/configs/ssd/_base_/ssdlite_mobilenet_v3_small_320.yml

 architecture: SSD
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_ssld_pretrained.tar
-weights: output/ssd_mobilenet_v3_small/model_final
+load_static_weights: True
 
 SSD:
   backbone: MobileNetV3

dygraph/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml

+_BASE_: [
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  '_base_/optimizer_120e.yml',
+  '_base_/ssd_mobilenet_v1_300.yml',
+  '_base_/ssd_mobilenet_reader.yml',
+]
+weights: output/ssd_mobilenet_v1_300_120e_voc/model_final

dygraph/configs/ssd/ssd_vgg16_300_240e_voc.yml

+_BASE_: [
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  '_base_/optimizer_240e.yml',
+  '_base_/ssd_vgg16_300.yml',
+  '_base_/ssd_reader.yml',
+]
+weights: output/ssd_vgg16_300_240e_voc/model_final

dygraph/configs/ssd/ssdlite_mobilenet_v1_300_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1000e.yml',
+  '_base_/ssdlite_mobilenet_v1_300.yml',
+  '_base_/ssdlite300_reader.yml',
+]
+weights: output/ssdlite_mobilenet_v1_300_coco/model_final

dygraph/configs/ssd/ssdlite_mobilenet_v3_large_320_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1000e.yml',
+  '_base_/ssdlite_mobilenet_v3_large_320.yml',
+  '_base_/ssdlite320_reader.yml',
+]
+weights: output/ssdlite_mobilenet_v3_large_320_coco/model_final

dygraph/configs/ssd/ssdlite_mobilenet_v3_small_320_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_1000e.yml',
+  '_base_/ssdlite_mobilenet_v3_small_320.yml',
+  '_base_/ssdlite320_reader.yml',
+]
+weights: output/ssdlite_mobilenet_v3_small_320_coco/model_final

dygraph/configs/ssd_mobilenet_v1_300_120e_voc.yml

-_BASE_: [
-  './_base_/models/ssd_mobilenet_v1_300.yml',
-  './_base_/optimizers/ssd_mobilenet_120e.yml',
-  './_base_/datasets/voc.yml',
-  './_base_/readers/ssd_mobilenet_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/ssd_vgg16_300_240e_voc.yml

-_BASE_: [
-  './_base_/models/ssd_vgg16_300.yml',
-  './_base_/optimizers/ssd_240e.yml',
-  './_base_/datasets/voc.yml',
-  './_base_/readers/ssd_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/ssdlite_mobilenet_v1_300_coco.yml

-_BASE_: [
-  './_base_/models/ssdlite_mobilenet_v1_300.yml',
-  './_base_/optimizers/ssdlite_1000e.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/ssdlite300_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/ssdlite_mobilenet_v3_large_320_coco.yml

-_BASE_: [
-  './_base_/models/ssdlite_mobilenet_v3_large_320.yml',
-  './_base_/optimizers/ssdlite_1000e.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/ssdlite320_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/ssdlite_mobilenet_v3_small_320_coco.yml

-_BASE_: [
-  './_base_/models/ssdlite_mobilenet_v3_small_320.yml',
-  './_base_/optimizers/ssdlite_1000e.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/ssdlite320_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/yolov3/README.md

+# YOLOv3
+
+## Model Zoo
+
+### YOLOv3 on COCO
+
+| 骨架网络             | 输入尺寸   | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP |                           下载                          | 配置文件 |
+| :------------------- | :------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
+| DarkNet53(paper)  | 608         |    8    |   270e    |     ----     |  33.0  |    -   |    -   |
+| DarkNet53(paper)  | 416         |    8    |   270e    |     ----     |  31.0  |    -   |    -   |
+| DarkNet53(paper)  | 320         |    8    |   270e    |     ----     |  28.2  |    -   |    -   |
+| DarkNet53         | 608         |    8    |   270e    |     ----     |  39.0  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
+| DarkNet53         | 416         |    8    |   270e    |     ----     |  37.5  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
+| DarkNet53         | 320         |    8    |   270e    |     ----     |  34.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
+| MobileNet-V1         | 608         |    8    |   270e    |     ----     |  28.8  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
+| MobileNet-V1         | 416         |    8    |   270e    |     ----     |  28.7  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
+| MobileNet-V1         | 320         |    8    |   270e    |     ----     |  26.5  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
+| MobileNet-V3         | 608         |    8    |   270e    |     ----     |  31.4  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
+| MobileNet-V3         | 416         |    8    |   270e    |     ----     |  29.7  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
+| MobileNet-V3         | 320         |    8    |   270e    |     ----     |  26.9  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
+
+### YOLOv3 on Pasacl VOC
+
+| 骨架网络     | 输入尺寸 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | 下载 | 配置文件 |
+| :----------- | :--: | :-----: | :-----: |:------------: |:----: | :-------: | :----: |
+| MobileNet-V1 | 608  |    8    |   270e  |      -        |  75.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
+| MobileNet-V1 | 416  |    8    |   270e  |      -        |  76.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
+| MobileNet-V1 | 320  |    8    |   270e  |      -        |  73.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
+| MobileNet-V3 | 608  |    8    |   270e  |      -        |  79.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
+| MobileNet-V3 | 416  |    8    |   270e  |      -        |  78.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
+| MobileNet-V3 | 320  |    8    |   270e  |      -        |  76.4  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
+
+**注意：** YOLOv3均使用8GPU训练，训练270个epoch
+
+
+## Citations
+```
+@misc{redmon2018yolov3,
+    title={YOLOv3: An Incremental Improvement},
+    author={Joseph Redmon and Ali Farhadi},
+    year={2018},
+    eprint={1804.02767},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```

dygraph/configs/_base_/models/yolov3_darknet53.yml → dygraph/configs/yolov3/_base_/yolov3_darknet53.yml

 architecture: YOLOv3
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_pretrained.tar
-weights: output/yolov3_darknet/model_final
 use_fine_grained_loss: false
 load_static_weights: True
 norm_type: sync_bn

dygraph/configs/_base_/models/yolov3_mobilenet_v1.yml → dygraph/configs/yolov3/_base_/yolov3_mobilenet_v1.yml

 architecture: YOLOv3
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar
-weights: output/yolov3_mobilenet_v1/model_final
 load_static_weights: True
 norm_type: sync_bn
 

dygraph/configs/_base_/models/yolov3_mobilenet_v3_large.yml → dygraph/configs/yolov3/_base_/yolov3_mobilenet_v3_large.yml

 architecture: YOLOv3
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar
-weights: output/yolov3_mobilenet_v3_large/model_final
 load_static_weights: True
 norm_type: sync_bn
 

dygraph/configs/_base_/models/yolov3_mobilenet_v3_small.yml → dygraph/configs/yolov3/_base_/yolov3_mobilenet_v3_small.yml

 architecture: YOLOv3
 pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar
-weights: output/yolov3_mobilenet_v3_small/model_final
 load_static_weights: True
 norm_type: sync_bn
 

dygraph/configs/yolov3/yolov3_darknet53_270e_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_270e.yml',
+  '_base_/yolov3_darknet53.yml',
+  '_base_/yolov3_reader.yml',
+]
+weights: output/yolov3_darknet53_coco/model_final

dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_270e.yml',
+  '_base_/yolov3_mobilenet_v1.yml',
+  '_base_/yolov3_reader.yml',
+]
+weights: output/yolov3_mobilenet_v1_coco/model_final

dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml → dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml

 _BASE_: [
-  './_base_/models/yolov3_mobilenet_v1.yml',
-  './_base_/optimizers/yolov3_270e.yml',
-  './_base_/datasets/voc.yml',
-  './_base_/readers/yolov3_reader.yml',
-  './_base_/runtime.yml',
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  '_base_/optimizer_270e.yml',
+  '_base_/yolov3_mobilenet_v1.yml',
+  '_base_/yolov3_reader.yml',
 ]
+weights: output/yolov3_mobilenet_v1_voc/model_final
 
 TrainReader:
   inputs_def:

dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '_base_/optimizer_270e.yml',
+  '_base_/yolov3_mobilenet_v3_large.yml',
+  '_base_/yolov3_reader.yml',
+]
+weights: output/yolov3_mobilenet_v3_large_coco/model_final

dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml → dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml

 _BASE_: [
-  './_base_/models/yolov3_mobilenet_v3_large.yml',
-  './_base_/optimizers/yolov3_270e.yml',
-  './_base_/datasets/voc.yml',
-  './_base_/readers/yolov3_reader.yml',
-  './_base_/runtime.yml',
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  '_base_/optimizer_270e.yml',
+  '_base_/yolov3_mobilenet_v3_large.yml',
+  '_base_/yolov3_reader.yml',
 ]
+weights: output/yolov3_mobilenet_v3_large_voc/model_final
 
 TrainReader:
   inputs_def:

dygraph/configs/yolov3_darknet53_270e_coco.yml

-_BASE_: [
-  './_base_/models/yolov3_darknet53.yml',
-  './_base_/optimizers/yolov3_270e.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/yolov3_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml

-_BASE_: [
-  './_base_/models/yolov3_mobilenet_v1.yml',
-  './_base_/optimizers/yolov3_270e.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/yolov3_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml

-_BASE_: [
-  './_base_/models/yolov3_mobilenet_v3_large.yml',
-  './_base_/optimizers/yolov3_270e.yml',
-  './_base_/datasets/coco_detection.yml',
-  './_base_/readers/yolov3_reader.yml',
-  './_base_/runtime.yml',
-]

dygraph/docs/MODEL_ZOO_cn.md

@@ -23,67 +23,35 @@
 
 ## ImageNet预训练模型
 
-Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型均通过标准的Imagenet-1k数据集训练得到。[下载链接](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/image_classification#supported-models-and-performances)
+Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型均通过标准的Imagenet-1k数据集训练得到，ResNet和MobileNet等是采用余弦学习率调整策略或SSLD知识蒸馏训练得到的高精度预训练模型，可在[PaddleClas](https://github.com/PaddlePaddle/PaddleClas)查看模型细节。
 
-- 注：ResNet50模型通过余弦学习率调整策略训练得到。[ResNet50下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_pretrained.tar),
- [ResNet50_vd下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar)
 
 ## 基线
 
-### Faster & Mask R-CNN
+### Faster R-CNN
 
-| 骨架网络             | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP |                           下载                          | 配置文件 |
-| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
-| ResNet50             | Faster         |    1    |   1x    |     ----     |  35.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn_r50_1x_coco.yml) |
-| ResNet50-FPN         | Faster         |    1    |   1x    |     ----     |  37.0  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn_r50_fpn_1x_coco.yml) |
-| ResNet50             | Mask         |    1    |   1x    |     ----     |  36.4  |    31.9    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn_r50_1x_coco.yml) |
-| ResNet50-FPN         | Mask         |    1    |   1x    |     ----     |  38.3  |    34.5    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn_r50_fpn_1x_coco.yml) |
-| ResNet50-FPN         | Cascade Faster         |    1    |   1x    |     ----     |  41.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_faster_rcnn_r50_fpn_1x_coco.yml) |
-| ResNet50-FPN         | Cascade Mask         |    1    |   1x    |     ----     |  41.6  |    35.3    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
+请参考[Faster R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/)
 
+### Mask R-CNN
 
-### YOLOv3 on COCO
+请参考[Mask R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn/)
 
-| 骨架网络             | 输入尺寸   | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP |                           下载                          | 配置文件 |
-| :------------------- | :------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
-| DarkNet53(paper)  | 608         |    8    |   270e    |     ----     |  33.0  |    -   |    -   |
-| DarkNet53(paper)  | 416         |    8    |   270e    |     ----     |  31.0  |    -   |    -   |
-| DarkNet53(paper)  | 320         |    8    |   270e    |     ----     |  28.2  |    -   |    -   |
-| DarkNet53         | 608         |    8    |   270e    |     ----     |  39.0  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
-| DarkNet53         | 416         |    8    |   270e    |     ----     |  37.5  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
-| DarkNet53         | 320         |    8    |   270e    |     ----     |  34.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
-| MobileNet-V1         | 608         |    8    |   270e    |     ----     |  28.8  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
-| MobileNet-V1         | 416         |    8    |   270e    |     ----     |  28.7  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
-| MobileNet-V1         | 320         |    8    |   270e    |     ----     |  26.5  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
-| MobileNet-V3         | 608         |    8    |   270e    |     ----     |  31.4  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
-| MobileNet-V3         | 416         |    8    |   270e    |     ----     |  29.7  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
-| MobileNet-V3         | 320         |    8    |   270e    |     ----     |  26.9  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
+### Cascade R-CNN
 
-### YOLOv3 on Pasacl VOC
+请参考[Cascade R-CNN](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_rcnn/)
 
-| 骨架网络     | 输入尺寸 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | 下载 | 配置文件 |
-| :----------- | :--: | :-----: | :-----: |:------------: |:----: | :-------: | :----: |
-| MobileNet-V1 | 608  |    8    |   270e  |      -        |  75.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
-| MobileNet-V1 | 416  |    8    |   270e  |      -        |  76.1  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
-| MobileNet-V1 | 320  |    8    |   270e  |      -        |  73.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
-| MobileNet-V3 | 608  |    8    |   270e  |      -        |  79.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
-| MobileNet-V3 | 416  |    8    |   270e  |      -        |  78.6  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
-| MobileNet-V3 | 320  |    8    |   270e  |      -        |  76.4  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
+### YOLOv3
 
-**注意：** YOLOv3均使用8GPU训练，训练270个epoch
+请参考[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3/)
 
-### SSD on Pascal VOC
+### SSD
 
-| 骨架网络        | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP |                           下载                          | 配置文件 |
-| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
-| VGG             | SSD            |    8    |   240e    |     ----     |  78.2  | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/ssd_vgg16_300_240e_voc.yml) |
-
-**注意：** SSD使用4GPU训练，训练240个epoch
+请参考[SSD](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/ssd/)
 
 ### FCOS
 
-请参考[fcos](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/fcos/)
+请参考[FCOS](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/fcos/)
 
 ### SOLOv2
 
-请参考[solov2](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/solov2/)
+请参考[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/solov2/)