论文标题
Yolox-pai：改进的Yolox，比Yolov6更强大，更快
YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6
论文作者
论文摘要
我们开发一个名为EasyCV的多合一计算机视觉工具箱，以促进使用各种SOTA计算机视觉方法。最近，我们将Yolox-Pai（改进的Yolox版本）添加到EasyCV中。我们进行消融研究以研究某些检测方法对YOLOX的影响。我们还为PAI-blade提供了一种易于使用，用于加速基于Bladedisc和Tensorrt的推理过程。最后，我们在单个NVIDIA V100 GPU上在1.0毫秒内收到可可末次的42.8次地图，该gpu比yolov6快一点。简单但有效的预测变量API也在EasyCV中设计，以进行END2END对象检测。现在可以在以下网址提供代码和模型，请访问：https：//github.com/alibaba/easycv。
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.
