Performance Benchmarking of YOLOv7 TensorRT
![Performance Benchmarking of YOLOv7 TensorRT](/content/images/size/w1200/max/800/1-uilai7xjc-5scp4rozd8-w.gif)
Object detection is one of the fundamental problems of computer vision. Instead of region detection and object classification separately in two stage detectors, object classification and bounding-box regression are done directly without using pre-generated region proposals in one stage detectors. YOLO (You Only Look Once) is one of the representative models of one-stage architecture. The YOLO family has continued to evolve since 2016, this summer we’ve got its latest update to version 7.
![](https://cmwang.net/content/images/fit/c/160/160/0-pex7bashe7svci5r.png)
If you are trying to learn how to train your model on a custom dataset from the beginning, there are already many tutorials, notebooks and videos available online. In Nilvana, we really care about its real-world performance on the embedded devices, especially Nvidia Jetson family devices. So we conducted a series performance testing of YOLOv7 variants models on different devices, from cloud GPUs A100 to the latest tiny powerhouse AGX Orin.
![](https://cmwang.net/content/images/fit/c/160/160/0-ze7j0-x469op2ttq.jpg)
The main reason YOLOv7 is more accurate, compare to other models with similar AP, YOLOv7 has only about half computational cost. — WongKinYiu
![](https://cmwang.net/content/images/max/800/1-egbwzwax-kjvas4om68ypa.png)
According to the results table, Xavier NX can run YOLOv7-tiny model pretty well. AGX Orin can even run YOLOv7x model more than 30 FPS, it’s amazing!
![](https://cmwang.net/content/images/max/800/1-qkotq0kxs9ewjblqz2h9ga.png)
Performance Benchmarking Playlist