- 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 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](../../../docs/FAQ.md).
- 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/master/docs/FAQ.md).
- PP-YOLO inference speed is tesed 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 inference speed is tesed 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.
- 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)
- 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)
...
@@ -62,13 +62,13 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods:
...
@@ -62,13 +62,13 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods:
| 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 |
| 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 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 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](../../../docs/FAQ.md).
- 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/master/docs/FAQ.md).
- PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread.
- PP-YOLO_MobileNetV3 inference speed is tested on Kirin 990 with 1 thread.
### PP-YOLO on Pascal VOC
### PP-YOLO on Pascal VOC
...
@@ -77,9 +77,9 @@ PP-YOLO trained on Pascal VOC dataset as follows:
...
@@ -77,9 +77,9 @@ PP-YOLO trained on Pascal VOC dataset as follows:
| Model | GPU number | images/GPU | backbone | input shape | Box AP50<sup>val</sup> | download | config |
| Model | GPU number | images/GPU | backbone | input shape | Box AP50<sup>val</sup> | download | config |
@@ -170,4 +170,4 @@ Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3.
...
@@ -170,4 +170,4 @@ Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3.
- Performance and inference spedd are measure with input shape as 608
- 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)`.
- 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.
- Inference speed is tested on single Tesla V100 with batch size as 1 following test method and environment configuration in benchmark above.
-[YOLOv3-DarkNet53](../yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection，see [Model Zoo](../../../docs/MODEL_ZOO.md) for details.
-[YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.yml) with mAP as 39.0 is optimized YOLOv3 model in PaddleDetection，see [Model Zoo](https://github.com/PaddlePaddle/PaddleDetection/blob/master/docs/MODEL_ZOO.md) for details.
