YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6
This work provides an incremental improvement for object detection practitioners by enhancing speed and accuracy in a toolbox.
The authors improved YOLOX to create YOLOX-PAI, achieving 42.8 mAP on COCO dataset with 1.0 ms inference time on a V100 GPU, making it slightly faster than YOLOv6.
We develop an all-in-one computer vision toolbox named EasyCV to facilitate the use of various SOTA computer vision methods. Recently, we add YOLOX-PAI, an improved version of YOLOX, into EasyCV. We conduct ablation studies to investigate the influence of some detection methods on YOLOX. We also provide an easy use for PAI-Blade which is used to accelerate the inference process based on BladeDISC and TensorRT. Finally, we receive 42.8 mAP on COCO dateset within 1.0 ms on a single NVIDIA V100 GPU, which is a bit faster than YOLOv6. A simple but efficient predictor api is also designed in EasyCV to conduct end2end object detection. Codes and models are now available at: https://github.com/alibaba/EasyCV.