YOLOX Detection - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English

YOLOX is an anchor-free version of YOLO. It has a simpler design but better performance and aims to bridge the gap between the research and industrial communities. The input size of the model is 640*640, and the output is the score and coordinates of the object.

The following table lists the YOLOX detection models supported by the Vitis AI Library.

Table 1. TSD YOLOX Detection Models
No Model Name Framework
1 tsd_yolox_pt PyTorch
2 yolox_nano_pt