- PP-YOLO is trained on COCO train2017 datast and evaluated on 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 datast 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 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.
...
...
@@ -63,12 +63,12 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods:
- PP-YOLO tiny is trained on COCO train2017 datast and evaluated on val2017 dataset，Box AP50<sup>val</sup> is evaluation results of `mAP(IoU=0.5)`.
- PP-YOLO tiny is trained on COCO train2017 datast and evaluated on val2017 & test-dev2017 dataset，Box AP50<sup>val</sup> is evaluation results of `mAP(IoU=0.5)`.
- PP-YOLO tiny 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 tiny inference speeding testing environment and configuration is same as PP-YOLO above.
...
...
@@ -165,7 +165,8 @@ Optimizing method and ablation experiments of PP-YOLO compared with YOLOv3.
| 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 |
