Open AlexeyAB opened 2 years ago
Paperswithcode provides a comparison to other networks with references to values in papers: https://paperswithcode.com/sota/real-time-object-detection-on-coco?dimension=FPS%20%28V100%2C%20b%3D1%29
but by default, yolov7 uses half-precision setting for test while yolov5 uses fp32 precision. https://github.com/WongKinYiu/yolov7/blob/b8956dd5a5bcbb81c92944545ca03390c22a695f/test.py#L40
I have ran inference tests with both yolov7 and yolov5 on a Jetson AGX Orin 32Gb, but they both had the same inference time (20ms, in my case). While when I tested with same data on an Amazon instance yolov5 was aound 60ms and yolov7 was around 15ms. Any idea why yolov7 not performing better on the Jetson AGX Orin ?
@AlexeyAB any idea about issue just above ?
When tested in an identical environment on a nVidia T4 GPU:
+0.9%
AP more accurate and 4x times faster than YOLOv5x6 1280x1280 (55.0% AP, 188.1ms)YOLOv7 (51.2% AP, 12.6ms) is
1.5x
times faster and+6.3%
AP more accurate than YOLOv5s6 (44.9% AP, 18.7ms)https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/compare_YOLOv7_vs_YOLOv5s6.ipynb
YOLOv7 (51.2% AP, 12.6ms) has almost the same accuracy but 4x times faster than YOLOv5m6 (51.3% AP, 49.1ms)
https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/compare_YOLOv7_vs_YOLOv5m6.ipynb
YOLOv7-e6 1280x1280 (55.9% AP, 46.6ms) is
+0.9%
AP more accurate and 4x times faster than YOLOv5x6 1280x1280 (55.0% AP, 188.1ms)https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/compare_YOLOv7e6_vs_YOLOv5x6.ipynb