更换文档检测模型

2024-08-27 14:42:45 +08:00
parent aea6f19951
commit 1514e09c40
2072 changed files with 254336 additions and 4967 deletions
--- a/paddle_detection/configs/ppyolo/README.md
+++ b/paddle_detection/configs/ppyolo/README.md
@@ -0,0 +1,240 @@
+English | [简体中文](README_cn.md)
+
+# PP-YOLO
+
+## Table of Contents
+- [Introduction](#Introduction)
+- [Model Zoo](#Model_Zoo)
+- [Getting Start](#Getting_Start)
+- [Future Work](#Future_Work)
+- [Appendix](#Appendix)
+
+## Introduction
+
+[PP-YOLO](https://arxiv.org/abs/2007.12099) is a optimized model based on YOLOv3 in PaddleDetection，whose performance(mAP on COCO) and inference spped are better than [YOLOv4](https://arxiv.org/abs/2004.10934)，PaddlePaddle 2.0.2(available on pip now) or [Daily Version](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/install/Tables.html#whl-develop) is required to run this PP-YOLO。
+
+PP-YOLO reached mmAP(IoU=0.5:0.95) as 45.9% on COCO test-dev2017 dataset, and inference speed of FP32 on single V100 is 72.9 FPS, inference speed of FP16 with TensorRT on single V100 is 155.6 FPS.
+
+<div align="center">
+  <img src="../../docs/images/ppyolo_map_fps.png" width=500 />
+</div>
+
+PP-YOLO and PP-YOLOv2 improved performance and speed of YOLOv3 with following methods:
+
+- Better backbone: ResNet50vd-DCN
+- Larger training batch size: 8 GPUs and mini-batch size as 24 on each GPU
+- [Drop Block](https://arxiv.org/abs/1810.12890)
+- [Exponential Moving Average](https://www.investopedia.com/terms/e/ema.asp)
+- [IoU Loss](https://arxiv.org/pdf/1902.09630.pdf)
+- [Grid Sensitive](https://arxiv.org/abs/2004.10934)
+- [Matrix NMS](https://arxiv.org/pdf/2003.10152.pdf)
+- [CoordConv](https://arxiv.org/abs/1807.03247)
+- [Spatial Pyramid Pooling](https://arxiv.org/abs/1406.4729)
+- Better ImageNet pretrain weights
+- [PAN](https://arxiv.org/abs/1803.01534)
+- Iou aware Loss
+- larger input size
+
+## Model Zoo
+
+### PP-YOLO
+
+|          Model           | GPU number | images/GPU |  backbone  | input shape | Box AP<sup>val</sup> | Box AP<sup>test</sup> | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config  |
+|:------------------------:|:-------:|:-------------:|:----------:| :-------:| :------------------: | :-------------------: | :------------: | :---------------------: | :------: | :------: |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     608     |         44.8         |         45.2          |      72.9      |          155.6          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     512     |         43.9         |         44.4          |      89.9      |          188.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     416     |         42.1         |         42.5          |      109.1      |          215.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     320     |         38.9         |         39.3          |      132.2      |          242.2          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     608     |         45.3         |         45.9          |      72.9      |          155.6          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     512     |         44.4         |         45.0          |      89.9      |          188.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     416     |         42.7         |         43.2          |      109.1      |          215.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     320     |         39.5         |         40.1          |      132.2      |          242.2          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO               |     4      |     32     | ResNet18vd |     512     |         29.2         |         29.5          |      357.1      |          657.9          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r18vd_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r18vd_coco.yml)                   |
+| PP-YOLO               |     4      |     32     | ResNet18vd |     416     |         28.6         |         28.9          |      409.8      |          719.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r18vd_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r18vd_coco.yml)                   |
+| PP-YOLO               |     4      |     32     | ResNet18vd |     320     |         26.2         |         26.4          |      480.7      |          763.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r18vd_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r18vd_coco.yml)                   |
+| PP-YOLOv2               |     8      |     12     | ResNet50vd |     640     |         49.1         |         49.5          |      68.9      |          106.5          | [model](https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml)                   |
+| PP-YOLOv2               |     8      |     12     | ResNet101vd |     640     |         49.7         |         50.3          |     49.5     |         87.0         | [model](https://paddledet.bj.bcebos.com/models/ppyolov2_r101vd_dcn_365e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco.yml)                   |
+
+
+**Notes:**
+
+- PP-YOLO is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset，Box AP<sup>test</sup> is evaluation results of `mAP(IoU=0.5:0.95)`.
+- PP-YOLO used 8 GPUs for training and mini-batch size as 24 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ).
+- PP-YOLO inference speed is tested on single Tesla V100 with batch size as 1, CUDA 10.2, CUDNN 7.5.1, TensorRT 5.1.2.2 in TensorRT mode.
+- PP-YOLO FP32 inference speed testing uses inference model exported by `tools/export_model.py` and benchmarked by running `depoly/python/infer.py` with `--run_benchmark`. All testing results do not contains the time cost of data reading and post-processing(NMS), which is same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) in testing method.
+- TensorRT FP16 inference speed testing exclude the time cost of bounding-box decoding(`yolo_box`) part comparing with FP32 testing above, which means that data reading, bounding-box decoding and post-processing(NMS) is excluded(test method same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) too)
+- If you set `--run_benchmark=True`，you should install these dependencies at first, `pip install pynvml psutil GPUtil`.
+
+### PP-YOLO for mobile
+
+|            Model             | GPU number | images/GPU | Model Size | input shape | Box AP<sup>val</sup> |  Box AP50<sup>val</sup> | Kirin 990 1xCore(FPS) | download | config  |
+|:----------------------------:|:-------:|:-------------:|:----------:| :-------:| :------------------: |  :--------------------: | :--------------------: | :------: | :------: |
+| PP-YOLO_MobileNetV3_large    |    4    |      32       |    28MB    |   320    |         23.2         |           42.6          |           14.1         | [model](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_large_coco.yml)                   |
+| PP-YOLO_MobileNetV3_small    |    4    |      32       |    16MB    |   320    |         17.2         |           33.8          |           21.5         | [model](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_small_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_small_coco.yml)                   |
+
+**Notes:**
+
+- PP-YOLO_MobileNetV3 is trained on COCO train2017 datast and evaluated on val2017 dataset，Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5:0.95)`, Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5)`.
+- PP-YOLO_MobileNetV3 used 4 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ).
+- PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread.
+
+### PP-YOLO tiny
+
+|            Model             | GPU number | images/GPU | Model Size | Post Quant Model Size | input shape | Box AP<sup>val</sup> | Kirin 990 4xCore(FPS) | download | config | post quant model |
+|:----------------------------:|:-------:|:-------------:|:----------:| :-------------------: | :---------: | :------------------: | :-------------------: | :------: | :----: | :--------------: |
+| PP-YOLO tiny                 |    8    |      32       |   4.2MB    |       **1.3M**        |     320     |         20.6         |          92.3         | [model](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_650e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_tiny_650e_coco.yml)  | [inference model](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_quant.tar) |
+| PP-YOLO tiny                 |    8    |      32       |   4.2MB    |       **1.3M**        |     416     |         22.7         |          65.4         | [model](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_650e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_tiny_650e_coco.yml)  | [inference model](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_quant.tar) |
+
+**Notes:**
+
+- PP-YOLO-tiny is trained on COCO train2017 datast and evaluated on val2017 dataset，Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5:0.95)`, Box AP<sup>val</sup> is evaluation results of `mAP(IoU=0.5)`.
+- PP-YOLO-tiny used 8 GPUs for training and mini-batch size as 32 on each GPU, if GPU number and mini-batch size is changed, learning rate and iteration times should be adjusted according [FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ/README.md).
+- PP-YOLO-tiny inference speed is tested on Kirin 990 with 4 threads by arm8
+- we alse provide PP-YOLO-tiny post quant inference model, which can compress model to **1.3MB** with nearly no inference on inference speed and performance
+
+### PP-YOLO on Pascal VOC
+
+PP-YOLO trained on Pascal VOC dataset as follows:
+
+|       Model        | GPU number | images/GPU |  backbone  | input shape | Box AP50<sup>val</sup> | download | config  |
+|:------------------:|:----------:|:----------:|:----------:| :----------:| :--------------------: | :------: | :-----: |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     608     |          84.9          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml)                   |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     416     |          84.3          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml)                   |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     320     |          82.2          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml)                   |
+
+## Getting Start
+
+### 1. Training
+
+Training PP-YOLO on 8 GPUs with following command(all commands should be run under PaddleDetection dygraph directory as default)
+
+```bash
+python -m paddle.distributed.launch --log_dir=./ppyolo_dygraph/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml &>ppyolo_dygraph.log 2>&1 &
+```
+
+optional: Run `tools/anchor_cluster.py` to get anchors suitable for your dataset, and modify the anchor setting in model configuration file and reader configuration file, such as `configs/ppyolo/_base_/ppyolo_tiny.yml` and `configs/ppyolo/_base_/ppyolo_tiny_reader.yml`.
+
+``` bash
+python tools/anchor_cluster.py -c configs/ppyolo/ppyolo_tiny_650e_coco.yml -n 9 -s 320 -m v2 -i 1000
+```
+
+### 2. Evaluation
+
+Evaluating PP-YOLO on COCO val2017 dataset in single GPU with following commands:
+
+```bash
+# use weights released in PaddleDetection model zoo
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
+
+# use saved checkpoint in training
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=output/ppyolo_r50vd_dcn_1x_coco/model_final
+```
+
+For evaluation on COCO test-dev2017 dataset, `configs/ppyolo/ppyolo_test.yml` should be used, please download COCO test-dev2017 dataset from [COCO dataset download](https://cocodataset.org/#download) and decompress to pathes configured by `EvalReader.dataset` in `configs/ppyolo/ppyolo_test.yml` and run evaluation by following command:
+
+```bash
+# use weights released in PaddleDetection model zoo
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
+
+# use saved checkpoint in training
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o weights=output/ppyolo_r50vd_dcn_1x_coco/model_final
+```
+
+Evaluation results will be saved in `bbox.json`, compress it into a `zip` package and upload to [COCO dataset evaluation](https://competitions.codalab.org/competitions/20794#participate) to evaluate.
+
+**NOTE 1:** `configs/ppyolo/ppyolo_test.yml` is only used for evaluation on COCO test-dev2017 dataset, could not be used for training or COCO val2017 dataset evaluating.
+
+**NOTE 2:** Due to the overall upgrade of the dynamic graph framework, the following weight models published by paddledetection need to be evaluated by adding the -- bias field, such as
+
+```bash
+# use weights released in PaddleDetection model zoo
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --bias
+```
+These models are:
+
+1.ppyolo_r50vd_dcn_1x_coco
+
+2.ppyolo_r50vd_dcn_voc
+
+3.ppyolo_r18vd_coco
+
+4.ppyolo_mbv3_large_coco
+
+5.ppyolo_mbv3_small_coco
+
+6.ppyolo_tiny_650e_coco
+
+### 3. Inference
+
+Inference images in single GPU with following commands, use `--infer_img` to inference a single image and `--infer_dir` to inference all images in the directory.
+
+```bash
+# inference single image
+CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439_640x640.jpg
+
+# inference all images in the directory
+CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_dir=demo
+```
+
+### 4. Inference deployment
+
+For inference deployment or benchmard, model exported with `tools/export_model.py` should be used and perform inference with Paddle inference library with following commands:
+
+```bash
+# export model, model will be save in output/ppyolo as default
+python tools/export_model.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
+
+# inference with Paddle Inference library
+CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyolo_r50vd_dcn_1x_coco --image_file=demo/000000014439_640x640.jpg --device=GPU
+```
+
+
+## Appendix
+
+Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3.
+
+| NO.  |        Model                 | Box AP<sup>val</sup> | Box AP<sup>test</sup> | Params(M) | FLOPs(G) | V100 FP32 FPS |
+| :--: | :--------------------------- | :------------------: |:--------------------: | :-------: | :------: | :-----------: |
+|  A   | YOLOv3-DarkNet53             |         38.9         |           -           |   59.13   |  65.52   |      58.2     |
+|  B   | YOLOv3-ResNet50vd-DCN        |         39.1         |           -           |   43.89   |  44.71   |      79.2     |
+|  C   | B + LB + EMA + DropBlock     |         41.4         |           -           |   43.89   |  44.71   |      79.2     |
+|  D   | C + IoU Loss                 |         41.9         |           -           |   43.89   |  44.71   |      79.2     |
+|  E   | D + IoU Aware                |         42.5         |           -           |   43.90   |  44.71   |      74.9     |
+|  F   | E + Grid Sensitive           |         42.8         |           -           |   43.90   |  44.71   |      74.8     |
+|  G   | F + Matrix NMS               |         43.5         |           -           |   43.90   |  44.71   |      74.8     |
+|  H   | G + CoordConv                |         44.0         |           -           |   43.93   |  44.76   |      74.1     |
+|  I   | H + SPP                      |         44.3         |         45.2          |   44.93   |  45.12   |      72.9     |
+|  J   | I + Better ImageNet Pretrain |         44.8         |         45.2          |   44.93   |  45.12   |      72.9     |
+|  K   | J + 2x Scheduler             |         45.3         |         45.9          |   44.93   |  45.12   |      72.9     |
+
+**Notes:**
+
+- Performance and inference spedd are measure with input shape as 608
+- All models are trained on COCO train2017 datast and evaluated on val2017 & test-dev2017 dataset，`Box AP` is evaluation results as `mAP(IoU=0.5:0.95)`.
+- Inference speed is tested on single Tesla V100 with batch size as 1 following test method and environment configuration in benchmark above.
+- [YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection，see [YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/README.md) for details.
+
+## Citation
+
+```
+@article{huang2021pp,
+  title={PP-YOLOv2: A Practical Object Detector},
+  author={Huang, Xin and Wang, Xinxin and Lv, Wenyu and Bai, Xiaying and Long, Xiang and Deng, Kaipeng and Dang, Qingqing and Han, Shumin and Liu, Qiwen and Hu, Xiaoguang and others},
+  journal={arXiv preprint arXiv:2104.10419},
+  year={2021}
+}
+@misc{long2020ppyolo,
+title={PP-YOLO: An Effective and Efficient Implementation of Object Detector},
+author={Xiang Long and Kaipeng Deng and Guanzhong Wang and Yang Zhang and Qingqing Dang and Yuan Gao and Hui Shen and Jianguo Ren and Shumin Han and Errui Ding and Shilei Wen},
+year={2020},
+eprint={2007.12099},
+archivePrefix={arXiv},
+primaryClass={cs.CV}
+}
+@misc{ppdet2019,
+title={PaddleDetection, Object detection and instance segmentation toolkit based on PaddlePaddle.},
+author={PaddlePaddle Authors},
+howpublished = {\url{https://github.com/PaddlePaddle/PaddleDetection}},
+year={2019}
+}
+```
--- a/paddle_detection/configs/ppyolo/README_cn.md
+++ b/paddle_detection/configs/ppyolo/README_cn.md
@@ -0,0 +1,233 @@
+简体中文 | [English](README.md)
+
+# PP-YOLO 模型
+
+## 内容
+- [简介](#简介)
+- [模型库与基线](#模型库与基线)
+- [使用说明](#使用说明)
+- [未来工作](#未来工作)
+- [附录](#附录)
+
+## 简介
+
+[PP-YOLO](https://arxiv.org/abs/2007.12099)是PaddleDetection优化和改进的YOLOv3的模型，其精度(COCO数据集mAP)和推理速度均优于[YOLOv4](https://arxiv.org/abs/2004.10934)模型，要求使用PaddlePaddle 2.0.2(可使用pip安装) 或适当的[develop版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/install/Tables.html#whl-develop)。
+
+PP-YOLO在[COCO](http://cocodataset.org) test-dev2017数据集上精度达到45.9%，在单卡V100上FP32推理速度为72.9 FPS, V100上开启TensorRT下FP16推理速度为155.6 FPS。
+
+<div align="center">
+  <img src="../../docs/images/ppyolo_map_fps.png" width=500 />
+</div>
+
+PP-YOLO和PP-YOLOv2从如下方面优化和提升YOLOv3模型的精度和速度：
+
+- 更优的骨干网络: ResNet50vd-DCN
+- 更大的训练batch size: 8 GPUs，每GPU batch_size=24，对应调整学习率和迭代轮数
+- [Drop Block](https://arxiv.org/abs/1810.12890)
+- [Exponential Moving Average](https://www.investopedia.com/terms/e/ema.asp)
+- [IoU Loss](https://arxiv.org/pdf/1902.09630.pdf)
+- [Grid Sensitive](https://arxiv.org/abs/2004.10934)
+- [Matrix NMS](https://arxiv.org/pdf/2003.10152.pdf)
+- [CoordConv](https://arxiv.org/abs/1807.03247)
+- [Spatial Pyramid Pooling](https://arxiv.org/abs/1406.4729)
+- 更优的预训练模型
+- [PAN](https://arxiv.org/abs/1803.01534)
+- Iou aware Loss
+- 更大的输入尺寸
+
+## 模型库
+
+### PP-YOLO模型
+
+|          模型            | GPU个数 | 每GPU图片个数 |  骨干网络  | 输入尺寸 | Box AP<sup>val</sup> | Box AP<sup>test</sup> | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | 模型下载 | 配置文件 |
+|:------------------------:|:-------:|:-------------:|:----------:| :-------:| :------------------: | :-------------------: | :------------: | :---------------------: | :------: | :------: |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     608     |         44.8         |         45.2          |      72.9      |          155.6          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     512     |         43.9         |         44.4          |      89.9      |          188.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     416     |         42.1         |         42.5          |      109.1      |          215.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO                  |     8      |     24     | ResNet50vd |     320     |         38.9         |         39.3          |      132.2      |          242.2          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     608     |         45.3         |         45.9          |      72.9      |          155.6          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     512     |         44.4         |         45.0          |      89.9      |          188.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     416     |         42.7         |         43.2          |      109.1      |          215.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO_2x               |     8      |     24     | ResNet50vd |     320     |         39.5         |         40.1          |      132.2      |          242.2          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml)                   |
+| PP-YOLO               |     4      |     32     | ResNet18vd |     512     |         29.2         |         29.5          |      357.1      |          657.9          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r18vd_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r18vd_coco.yml)                   |
+| PP-YOLO               |     4      |     32     | ResNet18vd |     416     |         28.6         |         28.9          |      409.8      |          719.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r18vd_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r18vd_coco.yml)                   |
+| PP-YOLO               |     4      |     32     | ResNet18vd |     320     |         26.2         |         26.4          |      480.7      |          763.4          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r18vd_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r18vd_coco.yml)                   |
+| PP-YOLOv2               |     8      |     12     | ResNet50vd |     640     |         49.1         |         49.5          |      68.9      |          106.5          | [model](https://paddledet.bj.bcebos.com/models/ppyolov2_r50vd_dcn_365e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml)                   |
+| PP-YOLOv2               |     8      |     12     | ResNet101vd |     640     |         49.7         |         50.3          |     49.5     |         87.0         | [model](https://paddledet.bj.bcebos.com/models/ppyolov2_r101vd_dcn_365e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco.yml)                   |
+
+**注意:**
+
+- PP-YOLO模型使用COCO数据集中train2017作为训练集，使用val2017和test-dev2017作为测试集，Box AP<sup>test</sup>为`mAP(IoU=0.5:0.95)`评估结果。
+- PP-YOLO模型训练过程中使用8 GPUs，每GPU batch size为24进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ)调整学习率和迭代次数。
+- PP-YOLO模型推理速度测试采用单卡V100，batch size=1进行测试，使用CUDA 10.2, CUDNN 7.5.1，TensorRT推理速度测试使用TensorRT 5.1.2.2。
+- PP-YOLO模型FP32的推理速度测试数据为使用`tools/export_model.py`脚本导出模型后，使用`deploy/python/infer.py`脚本中的`--run_benchnark`参数使用Paddle预测库进行推理速度benchmark测试结果, 且测试的均为不包含数据预处理和模型输出后处理(NMS)的数据(与[YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet)测试方法一致)。
+- TensorRT FP16的速度测试相比于FP32去除了`yolo_box`(bbox解码)部分耗时，即不包含数据预处理，bbox解码和NMS(与[YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet)测试方法一致)。
+
+### PP-YOLO 轻量级模型
+
+|          模型                | GPU个数 | 每GPU图片个数 |  模型体积  | 输入尺寸 | Box AP<sup>val</sup> |  Box AP50<sup>val</sup> | Kirin 990 1xCore (FPS) | 模型下载 |  配置文件 |
+|:----------------------------:|:-------:|:-------------:|:----------:| :-------:| :------------------: |  :--------------------: | :--------------------: | :------: | :------: |
+| PP-YOLO_MobileNetV3_large    |    4    |      32       |    28MB    |   320    |         23.2         |           42.6          |           14.1         | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_large_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_large_coco.yml)                   |
+| PP-YOLO_MobileNetV3_small    |    4    |      32       |    16MB    |   320    |         17.2         |           33.8          |           21.5         | [下载链接](https://paddledet.bj.bcebos.com/models/ppyolo_mbv3_small_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_mbv3_small_coco.yml)                   |
+
+- PP-YOLO_MobileNetV3 模型使用COCO数据集中train2017作为训练集，使用val2017作为测试集，Box AP<sup>val</sup>为`mAP(IoU=0.5:0.95)`评估结果, Box AP50<sup>val</sup>为`mAP(IoU=0.5)`评估结果。
+- PP-YOLO_MobileNetV3 模型训练过程中使用4GPU，每GPU batch size为32进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ)调整学习率和迭代次数。
+- PP-YOLO_MobileNetV3 模型推理速度测试环境配置为麒麟990芯片单线程。
+
+### PP-YOLO tiny模型
+
+|            模型              |  GPU 个数  | 每GPU图片个数 |  模型体积  | 后量化模型体积 |   输入尺寸  | Box AP<sup>val</sup> | Kirin 990 1xCore (FPS) | 模型下载 | 配置文件 | 量化后模型 |
+|:----------------------------:|:----------:|:-------------:| :--------: | :------------: | :----------:| :------------------: | :--------------------: | :------: | :------: | :--------: |
+| PP-YOLO tiny                 |     8      |      32       |   4.2MB    |   **1.3M**     |     320     |         20.6         |          92.3         | [model](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_650e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_tiny_650e_coco.yml) | [预测模型](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_quant.tar) |
+| PP-YOLO tiny                 |     8      |      32       |   4.2MB    |   **1.3M**     |     416     |         22.7         |          65.4         | [model](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_650e_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_tiny_650e_coco.yml) | [预测模型](https://paddledet.bj.bcebos.com/models/ppyolo_tiny_quant.tar) |
+
+- PP-YOLO-tiny 模型使用COCO数据集中train2017作为训练集，使用val2017作为测试集，Box AP<sup>val</sup>为`mAP(IoU=0.5:0.95)`评估结果, Box AP50<sup>val</sup>为`mAP(IoU=0.5)`评估结果。
+- PP-YOLO-tiny 模型训练过程中使用8GPU，每GPU batch size为32进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/docs/tutorials/FAQ/README.md)调整学习率和迭代次数。
+- PP-YOLO-tiny 模型推理速度测试环境配置为麒麟990芯片4线程，arm8架构。
+- 我们也提供的PP-YOLO-tiny的后量化压缩模型，将模型体积压缩到**1.3M**，对精度和预测速度基本无影响
+
+### Pascal VOC数据集上的PP-YOLO
+
+PP-YOLO在Pascal VOC数据集上训练模型如下:
+
+|       模型         | GPU个数 | 每GPU图片个数 |  骨干网络  |   输入尺寸  | Box AP50<sup>val</sup> | 模型下载 | 配置文件 |
+|:------------------:|:-------:|:-------------:|:----------:| :----------:| :--------------------: | :------: | :-----: |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     608     |          84.9          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml)                   |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     416     |          84.3          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml)                   |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     320     |          82.2          | [model](https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml)                   |
+
+## 使用说明
+
+### 1. 训练
+
+使用8GPU通过如下命令一键式启动训练(以下命令均默认在PaddleDetection根目录运行), 通过`--eval`参数开启训练中交替评估。
+
+```bash
+python -m paddle.distributed.launch --log_dir=./ppyolo_dygraph/ --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml &>ppyolo_dygraph.log 2>&1 &
+```
+
+可选：在训练之前使用`tools/anchor_cluster.py`得到适用于你的数据集的anchor，并注意修改模型配置文件和Reader配置文件中的anchor设置，如`configs/ppyolo/_base_/ppyolo_tiny.yml`和`configs/ppyolo/_base_/ppyolo_tiny_reader.yml`中anchor设置
+```bash
+python tools/anchor_cluster.py -c configs/ppyolo/ppyolo_tiny_650e_coco.yml -n 9 -s 320 -m v2 -i 1000
+```
+
+### 2. 评估
+
+使用单GPU通过如下命令一键式评估模型在COCO val2017数据集效果
+
+```bash
+# 使用PaddleDetection发布的权重
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
+
+# 使用训练保存的checkpoint
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=output/ppyolo_r50vd_dcn_1x_coco/model_final
+```
+
+我们提供了`configs/ppyolo/ppyolo_test.yml`用于评估COCO test-dev2017数据集的效果，评估COCO test-dev2017数据集的效果须先从[COCO数据集下载页](https://cocodataset.org/#download)下载test-dev2017数据集，解压到`configs/ppyolo/ppyolo_test.yml`中`EvalReader.dataset`中配置的路径，并使用如下命令进行评估
+
+```bash
+# 使用PaddleDetection发布的权重
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
+
+# 使用训练保存的checkpoint
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o weights=output/ppyolo_r50vd_dcn_1x_coco/model_final
+```
+
+评估结果保存于`bbox.json`中，将其压缩为zip包后通过[COCO数据集评估页](https://competitions.codalab.org/competitions/20794#participate)提交评估。
+
+**注意1:** `configs/ppyolo/ppyolo_test.yml`仅用于评估COCO test-dev数据集，不用于训练和评估COCO val2017数据集。
+
+**注意2:** 由于动态图框架整体升级，以下几个PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如
+
+```bash
+# 使用PaddleDetection发布的权重
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --bias
+```
+主要有:
+
+1.ppyolo_r50vd_dcn_1x_coco
+
+2.ppyolo_r50vd_dcn_voc
+
+3.ppyolo_r18vd_coco
+
+4.ppyolo_mbv3_large_coco
+
+5.ppyolo_mbv3_small_coco
+
+6.ppyolo_tiny_650e_coco
+
+### 3. 推理
+
+使用单GPU通过如下命令一键式推理图像，通过`--infer_img`指定图像路径，或通过`--infer_dir`指定目录并推理目录下所有图像
+
+```bash
+# 推理单张图像
+CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_img=demo/000000014439_640x640.jpg
+
+# 推理目录下所有图像
+CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --infer_dir=demo
+```
+
+### 4. 推理部署
+
+PP-YOLO模型部署及推理benchmark需要通过`tools/export_model.py`导出模型后使用Paddle预测库进行部署和推理，可通过如下命令一键式启动。
+
+```bash
+# 导出模型，默认存储于output/ppyolo目录
+python tools/export_model.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams
+
+# 预测库推理
+CUDA_VISIBLE_DEVICES=0 python deploy/python/infer.py --model_dir=output_inference/ppyolo_r50vd_dcn_1x_coco --image_file=demo/000000014439_640x640.jpg --device=GPU
+```
+
+
+## 附录
+
+PP-YOLO模型相对于YOLOv3模型优化项消融实验数据如下表所示。
+
+| 序号 |        模型                  | Box AP<sup>val</sup> | Box AP<sup>test</sup> | 参数量(M) | FLOPs(G) | V100 FP32 FPS |
+| :--: | :--------------------------- | :------------------: | :-------------------: | :-------: | :------: | :-----------: |
+|  A   | YOLOv3-DarkNet53             |         38.9         |            -          |   59.13   |  65.52   |      58.2     |
+|  B   | YOLOv3-ResNet50vd-DCN        |         39.1         |            -          |   43.89   |  44.71   |      79.2     |
+|  C   | B + LB + EMA + DropBlock     |         41.4         |            -          |   43.89   |  44.71   |      79.2     |
+|  D   | C + IoU Loss                 |         41.9         |            -          |   43.89   |  44.71   |      79.2     |
+|  E   | D + IoU Aware                |         42.5         |            -          |   43.90   |  44.71   |      74.9     |
+|  F   | E + Grid Sensitive           |         42.8         |            -          |   43.90   |  44.71   |      74.8     |
+|  G   | F + Matrix NMS               |         43.5         |            -          |   43.90   |  44.71   |      74.8     |
+|  H   | G + CoordConv                |         44.0         |            -          |   43.93   |  44.76   |      74.1     |
+|  I   | H + SPP                      |         44.3         |          45.2         |   44.93   |  45.12   |      72.9     |
+|  J   | I + Better ImageNet Pretrain |         44.8         |          45.2         |   44.93   |  45.12   |      72.9     |
+|  K   | J + 2x Scheduler             |         45.3         |          45.9         |   44.93   |  45.12   |      72.9     |
+
+**注意:**
+
+- 精度与推理速度数据均为使用输入图像尺寸为608的测试结果
+- Box AP为在COCO train2017数据集训练，val2017和test-dev2017数据集上评估`mAP(IoU=0.5:0.95)`数据
+- 推理速度为单卡V100上，batch size=1, 使用上述benchmark测试方法的测试结果，测试环境配置为CUDA 10.2，CUDNN 7.5.1
+- [YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_darknet53_270e_coco.yml)精度38.9为PaddleDetection优化后的YOLOv3模型，可参见[YOLOv3](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/yolov3/README.md)
+
+## 引用
+
+```
+@article{huang2021pp,
+  title={PP-YOLOv2: A Practical Object Detector},
+  author={Huang, Xin and Wang, Xinxin and Lv, Wenyu and Bai, Xiaying and Long, Xiang and Deng, Kaipeng and Dang, Qingqing and Han, Shumin and Liu, Qiwen and Hu, Xiaoguang and others},
+  journal={arXiv preprint arXiv:2104.10419},
+  year={2021}
+}
+@misc{long2020ppyolo,
+title={PP-YOLO: An Effective and Efficient Implementation of Object Detector},
+author={Xiang Long and Kaipeng Deng and Guanzhong Wang and Yang Zhang and Qingqing Dang and Yuan Gao and Hui Shen and Jianguo Ren and Shumin Han and Errui Ding and Shilei Wen},
+year={2020},
+eprint={2007.12099},
+archivePrefix={arXiv},
+primaryClass={cs.CV}
+}
+@misc{ppdet2019,
+title={PaddleDetection, Object detection and instance segmentation toolkit based on PaddlePaddle.},
+author={PaddlePaddle Authors},
+howpublished = {\url{https://github.com/PaddlePaddle/PaddleDetection}},
+year={2019}
+}
+```
--- a/paddle_detection/configs/ppyolo/_base_/optimizer_1x.yml
+++ b/paddle_detection/configs/ppyolo/_base_/optimizer_1x.yml
@@ -0,0 +1,22 @@
+epoch: 405
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 243
+    - 324
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  clip_grad_by_norm: 35.
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/_base_/optimizer_2x.yml
+++ b/paddle_detection/configs/ppyolo/_base_/optimizer_2x.yml
@@ -0,0 +1,22 @@
+epoch: 811
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 649
+    - 730
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  clip_grad_by_norm: 35.
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/_base_/optimizer_365e.yml
+++ b/paddle_detection/configs/ppyolo/_base_/optimizer_365e.yml
@@ -0,0 +1,21 @@
+epoch: 365
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 243
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  clip_grad_by_norm: 35.
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/_base_/optimizer_650e.yml
+++ b/paddle_detection/configs/ppyolo/_base_/optimizer_650e.yml
@@ -0,0 +1,22 @@
+epoch: 650
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 430
+    - 540
+    - 610
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_mbv3_large.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_mbv3_large.yml
@@ -0,0 +1,56 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_large_x1_0_ssld_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+YOLOv3:
+  backbone: MobileNetV3
+  neck: PPYOLOFPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+MobileNetV3:
+  model_name: large
+  scale: 1.
+  with_extra_blocks: false
+  extra_block_filters: []
+  feature_maps: [13, 16]
+
+PPYOLOFPN:
+  in_channels: [160, 368]
+  coord_conv: true
+  conv_block_num: 0
+  spp: true
+  drop_block: true
+
+YOLOv3Head:
+  anchors: [[11, 18], [34, 47], [51, 126],
+            [115, 71], [120, 195], [254, 235]]
+  anchor_masks: [[3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.5
+  downsample: [32, 16]
+  label_smooth: false
+  scale_x_y: 1.05
+  iou_loss: IouLoss
+
+IouLoss:
+  loss_weight: 2.5
+  loss_square: true
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+    scale_x_y: 1.05
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    nms_threshold: 0.45
+    nms_top_k: 1000
+    score_threshold: 0.005
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_mbv3_small.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_mbv3_small.yml
@@ -0,0 +1,56 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_small_x1_0_ssld_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+YOLOv3:
+  backbone: MobileNetV3
+  neck: PPYOLOFPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+MobileNetV3:
+  model_name: small
+  scale: 1.
+  with_extra_blocks: false
+  extra_block_filters: []
+  feature_maps: [9, 12]
+
+PPYOLOFPN:
+  in_channels: [96, 304]
+  coord_conv: true
+  conv_block_num: 0
+  spp: true
+  drop_block: true
+
+YOLOv3Head:
+  anchors: [[11, 18], [34, 47], [51, 126],
+            [115, 71], [120, 195], [254, 235]]
+  anchor_masks: [[3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.5
+  downsample: [32, 16]
+  label_smooth: false
+  scale_x_y: 1.05
+  iou_loss: IouLoss
+
+IouLoss:
+  loss_weight: 2.5
+  loss_square: true
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+    scale_x_y: 1.05
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    nms_threshold: 0.45
+    nms_top_k: 1000
+    score_threshold: 0.005
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_r18vd.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_r18vd.yml
@@ -0,0 +1,57 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet18_vd_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+YOLOv3:
+  backbone: ResNet
+  neck: PPYOLOFPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+ResNet:
+  depth: 18
+  variant: d
+  return_idx: [2, 3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.
+
+PPYOLOFPN:
+  drop_block: true
+  block_size: 3
+  keep_prob: 0.9
+  conv_block_num: 0
+
+YOLOv3Head:
+  anchor_masks: [[3, 4, 5], [0, 1, 2]]
+  anchors: [[10, 14], [23, 27], [37, 58],
+            [81, 82], [135, 169], [344, 319]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16]
+  label_smooth: false
+  scale_x_y: 1.05
+  iou_loss: IouLoss
+
+IouLoss:
+  loss_weight: 2.5
+  loss_square: true
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.01
+    downsample_ratio: 32
+    clip_bbox: true
+    scale_x_y: 1.05
+  nms:
+    name: MatrixNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    post_threshold: 0.01
+    nms_top_k: -1
+    background_label: -1
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_r50vd_dcn.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_r50vd_dcn.yml
@@ -0,0 +1,66 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+YOLOv3:
+  backbone: ResNet
+  neck: PPYOLOFPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+ResNet:
+  depth: 50
+  variant: d
+  return_idx: [1, 2, 3]
+  dcn_v2_stages: [3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.
+
+PPYOLOFPN:
+  coord_conv: true
+  drop_block: true
+  block_size: 3
+  keep_prob: 0.9
+  spp: true
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+  iou_aware: true
+  iou_aware_factor: 0.4
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+  scale_x_y: 1.05
+  iou_loss: IouLoss
+  iou_aware_loss: IouAwareLoss
+
+IouLoss:
+  loss_weight: 2.5
+  loss_square: true
+
+IouAwareLoss:
+  loss_weight: 1.0
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.01
+    downsample_ratio: 32
+    clip_bbox: true
+    scale_x_y: 1.05
+  nms:
+    name: MatrixNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    post_threshold: 0.01
+    nms_top_k: -1
+    background_label: -1
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_reader.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_reader.yml
@@ -0,0 +1,42 @@
+worker_num: 2
+TrainReader:
+  inputs_def:
+    num_max_boxes: 50
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]], downsample_ratios: [32, 16, 8]}
+  batch_size: 24
+  shuffle: true
+  drop_last: true
+  mixup_epoch: 25000
+  use_shared_memory: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 608, 608]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [608, 608], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_tiny.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_tiny.yml
@@ -0,0 +1,55 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/MobileNetV3_large_x0_5_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+YOLOv3:
+  backbone: MobileNetV3
+  neck: PPYOLOTinyFPN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+MobileNetV3:
+  model_name: large
+  scale: .5
+  with_extra_blocks: false
+  extra_block_filters: []
+  feature_maps: [7, 13, 16]
+
+PPYOLOTinyFPN:
+  detection_block_channels: [160, 128, 96]
+  spp: true
+  drop_block: true
+
+YOLOv3Head:
+  anchors: [[10, 15], [24, 36], [72, 42],
+            [35, 87], [102, 96], [60, 170],
+            [220, 125], [128, 222], [264, 266]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+
+YOLOv3Loss:
+  ignore_thresh: 0.5
+  downsample: [32, 16, 8]
+  label_smooth: false
+  scale_x_y: 1.05
+  iou_loss: IouLoss
+
+IouLoss:
+  loss_weight: 2.5
+  loss_square: true
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.005
+    downsample_ratio: 32
+    clip_bbox: true
+    scale_x_y: 1.05
+  nms:
+    name: MultiClassNMS
+    keep_top_k: 100
+    nms_threshold: 0.45
+    nms_top_k: 1000
+    score_threshold: 0.005
--- a/paddle_detection/configs/ppyolo/_base_/ppyolo_tiny_reader.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolo_tiny_reader.yml
@@ -0,0 +1,42 @@
+worker_num: 4
+TrainReader:
+  inputs_def:
+    num_max_boxes: 100
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [192, 224, 256, 288, 320, 352, 384, 416, 448, 480, 512], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 100}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[10, 15], [24, 36], [72, 42], [35, 87], [102, 96], [60, 170], [220, 125], [128, 222], [264, 266]], downsample_ratios: [32, 16, 8]}
+  batch_size: 32
+  shuffle: true
+  drop_last: true
+  mixup_epoch: 500
+  use_shared_memory: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
--- a/paddle_detection/configs/ppyolo/_base_/ppyolov2_r50vd_dcn.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolov2_r50vd_dcn.yml
@@ -0,0 +1,68 @@
+architecture: YOLOv3
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vd_ssld_pretrained.pdparams
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+# AMP training
+master_grad: true
+
+YOLOv3:
+  backbone: ResNet
+  neck: PPYOLOPAN
+  yolo_head: YOLOv3Head
+  post_process: BBoxPostProcess
+
+ResNet:
+  depth: 50
+  variant: d
+  return_idx: [1, 2, 3]
+  dcn_v2_stages: [3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.
+
+PPYOLOPAN:
+  drop_block: true
+  block_size: 3
+  keep_prob: 0.9
+  spp: true
+
+YOLOv3Head:
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  loss: YOLOv3Loss
+  iou_aware: true
+  iou_aware_factor: 0.5
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  downsample: [32, 16, 8]
+  label_smooth: false
+  scale_x_y: 1.05
+  iou_loss: IouLoss
+  iou_aware_loss: IouAwareLoss
+
+IouLoss:
+  loss_weight: 2.5
+  loss_square: true
+
+IouAwareLoss:
+  loss_weight: 1.0
+
+BBoxPostProcess:
+  decode:
+    name: YOLOBox
+    conf_thresh: 0.01
+    downsample_ratio: 32
+    clip_bbox: true
+    scale_x_y: 1.05
+  nms:
+    name: MatrixNMS
+    keep_top_k: 100
+    score_threshold: 0.01
+    post_threshold: 0.01
+    nms_top_k: -1
+    background_label: -1
--- a/paddle_detection/configs/ppyolo/_base_/ppyolov2_reader.yml
+++ b/paddle_detection/configs/ppyolo/_base_/ppyolov2_reader.yml
@@ -0,0 +1,42 @@
+worker_num: 2
+TrainReader:
+  inputs_def:
+    num_max_boxes: 100
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 100}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]], downsample_ratios: [32, 16, 8]}
+  batch_size: 12
+  shuffle: true
+  drop_last: true
+  mixup_epoch: 25000
+  use_shared_memory: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [640, 640], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 640, 640]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [640, 640], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
--- a/paddle_detection/configs/ppyolo/ppyolo_mbv3_large_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_mbv3_large_coco.yml
@@ -0,0 +1,84 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_mbv3_large.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 10
+weights: output/ppyolo_mbv3_large_coco/model_final
+
+# AMP training
+master_grad: true
+
+TrainReader:
+  inputs_def:
+    num_max_boxes: 90
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize:
+        target_size: [224, 256, 288, 320, 352, 384, 416, 448, 480, 512]
+        random_size: True
+        random_interp: True
+        keep_ratio: False
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 90}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
+        anchor_masks: [[3, 4, 5], [0, 1, 2]]
+        anchors: [[11, 18], [34, 47], [51, 126], [115, 71], [120, 195], [254, 235]]
+        downsample_ratios: [32, 16]
+        iou_thresh: 0.25
+        num_classes: 80
+  batch_size: 32
+  mixup_epoch: 200
+  shuffle: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
+
+epoch: 270
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 162
+    - 216
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/ppyolo_mbv3_small_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_mbv3_small_coco.yml
@@ -0,0 +1,81 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_mbv3_small.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 10
+weights: output/ppyolo_mbv3_small_coco/model_final
+
+TrainReader:
+  inputs_def:
+    num_max_boxes: 90
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize:
+        target_size: [224, 256, 288, 320, 352, 384, 416, 448, 480, 512]
+        random_size: True
+        random_interp: True
+        keep_ratio: False
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 90}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
+        anchor_masks: [[3, 4, 5], [0, 1, 2]]
+        anchors: [[11, 18], [34, 47], [51, 126], [115, 71], [120, 195], [254, 235]]
+        downsample_ratios: [32, 16]
+        iou_thresh: 0.25
+        num_classes: 80
+  batch_size: 32
+  mixup_epoch: 200
+  shuffle: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
+
+epoch: 270
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 162
+    - 216
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/ppyolo_r18vd_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_r18vd_coco.yml
@@ -0,0 +1,81 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r18vd.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 10
+weights: output/ppyolo_r18vd_coco/model_final
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize:
+        target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
+        random_size: True
+        random_interp: True
+        keep_ratio: False
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage:
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        is_scale: True
+    - Permute: {}
+    - Gt2YoloTarget:
+        anchor_masks: [[3, 4, 5], [0, 1, 2]]
+        anchors: [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]]
+        downsample_ratios: [32, 16]
+
+  batch_size: 32
+  mixup_epoch: 500
+  shuffle: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [512, 512], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 512, 512]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [512, 512], keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1
+
+epoch: 270
+
+LearningRate:
+  base_lr: 0.004
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 162
+    - 216
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml
@@ -0,0 +1,10 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 16
+weights: output/ppyolo_r50vd_dcn_1x_coco/model_final
--- a/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_1x_minicoco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_1x_minicoco.yml
@@ -0,0 +1,44 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 8
+use_ema: true
+weights: output/ppyolo_r50vd_dcn_1x_minicoco/model_final
+
+TrainReader:
+  batch_size: 12
+
+TrainDataset:
+  !COCODataSet
+    image_dir: train2017
+    # refer to https://github.com/giddyyupp/coco-minitrain
+    anno_path: annotations/instances_minitrain2017.json
+    dataset_dir: dataset/coco
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+epoch: 192
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 153
+    - 173
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml
@@ -0,0 +1,10 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_2x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 16
+weights: output/ppyolo_r50vd_dcn_2x_coco/model_final
--- a/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_r50vd_dcn_voc.yml
@@ -0,0 +1,42 @@
+_BASE_: [
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 83
+weights: output/ppyolo_r50vd_dcn_voc/model_final
+
+TrainReader:
+  mixup_epoch: 350
+  batch_size: 12
+
+# set collate_batch to false because ground-truth info is needed
+# on voc dataset and should not collate data in batch when batch size
+# is larger than 1.
+EvalReader:
+  collate_batch: false
+
+epoch: 583
+
+LearningRate:
+  base_lr: 0.00333
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 466
+    - 516
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
--- a/paddle_detection/configs/ppyolo/ppyolo_test.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_test.yml
@@ -0,0 +1,15 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 16
+
+EvalDataset:
+  !COCODataSet
+    image_dir: test2017
+    anno_path: annotations/image_info_test-dev2017.json
+    dataset_dir: dataset/coco
--- a/paddle_detection/configs/ppyolo/ppyolo_tiny_650e_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolo_tiny_650e_coco.yml
@@ -0,0 +1,10 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_tiny.yml',
+  './_base_/optimizer_650e.yml',
+  './_base_/ppyolo_tiny_reader.yml',
+]
+
+snapshot_epoch: 1
+weights: output/ppyolo_tiny_650e_coco/model_final
--- a/paddle_detection/configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco.yml
@@ -0,0 +1,20 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolov2_r50vd_dcn.yml',
+  './_base_/optimizer_365e.yml',
+  './_base_/ppyolov2_reader.yml',
+]
+
+snapshot_epoch: 8
+weights: output/ppyolov2_r101vd_dcn_365e_coco/model_final
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet101_vd_ssld_pretrained.pdparams
+
+ResNet:
+  depth: 101
+  variant: d
+  return_idx: [1, 2, 3]
+  dcn_v2_stages: [3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.
--- a/paddle_detection/configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml
+++ b/paddle_detection/configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml
@@ -0,0 +1,10 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolov2_r50vd_dcn.yml',
+  './_base_/optimizer_365e.yml',
+  './_base_/ppyolov2_reader.yml',
+]
+
+snapshot_epoch: 8
+weights: output/ppyolov2_r50vd_dcn_365e_coco/model_final
--- a/paddle_detection/configs/ppyolo/ppyolov2_r50vd_dcn_voc.yml
+++ b/paddle_detection/configs/ppyolo/ppyolov2_r50vd_dcn_voc.yml
@@ -0,0 +1,42 @@
+_BASE_: [
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  './_base_/ppyolov2_r50vd_dcn.yml',
+  './_base_/optimizer_365e.yml',
+  './_base_/ppyolov2_reader.yml',
+]
+
+snapshot_epoch: 83
+weights: output/ppyolov2_r50vd_dcn_voc/model_final
+
+TrainReader:
+  mixup_epoch: 350
+  batch_size: 12
+
+# set collate_batch to false because ground-truth info is needed
+# on voc dataset and should not collate data in batch when batch size
+# is larger than 1.
+EvalReader:
+  collate_batch: false
+
+epoch: 583
+
+LearningRate:
+  base_lr: 0.00333
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 466
+    - 516
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2