DJW c16313bb6a 第一次提交 | 9 maanden geleden | |
---|---|---|
.. | ||
README.md | 9 maanden geleden | |
metafile.yml | 9 maanden geleden | |
yolox_l_8xb8-300e_coco.py | 9 maanden geleden | |
yolox_m_8xb8-300e_coco.py | 9 maanden geleden | |
yolox_nano_8xb8-300e_coco.py | 9 maanden geleden | |
yolox_s_8xb8-300e_coco.py | 9 maanden geleden | |
yolox_tiny_8xb8-300e_coco.py | 9 maanden geleden | |
yolox_tta.py | 9 maanden geleden | |
yolox_x_8xb8-300e_coco.py | 9 maanden geleden |
In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX. We switch the YOLO detector to an anchor-free manner and conduct other advanced detection techniques, i.e., a decoupled head and the leading label assignment strategy SimOTA to achieve state-of-the-art results across a large scale range of models: For YOLO-Nano with only 0.91M parameters and 1.08G FLOPs, we get 25.3% AP on COCO, surpassing NanoDet by 1.8% AP; for YOLOv3, one of the most widely used detectors in industry, we boost it to 47.3% AP on COCO, outperforming the current best practice by 3.0% AP; for YOLOX-L with roughly the same amount of parameters as YOLOv4-CSP, YOLOv5-L, we achieve 50.0% AP on COCO at a speed of 68.9 FPS on Tesla V100, exceeding YOLOv5-L by 1.8% AP. Further, we won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021) using a single YOLOX-L model. We hope this report can provide useful experience for developers and researchers in practical scenes, and we also provide deploy versions with ONNX, TensorRT, NCNN, and Openvino supported.
Backbone | size | Mem (GB) | box AP | Config | Download |
---|---|---|---|---|---|
YOLOX-tiny | 416 | 3.5 | 32.0 | config | model | log |
YOLOX-s | 640 | 7.6 | 40.5 | config | model | log |
YOLOX-l | 640 | 19.9 | 49.4 | config | model | log |
YOLOX-x | 640 | 28.1 | 50.9 | config | model | log |
Note:
yolox-nano
model. Please refer to https://github.com/Megvii-BaseDetection/YOLOX/issues/674 for more information.YOLOX-tiny
, YOLOX-s
, YOLOX-l
, and YOLOX-x
is 31.8, 40.3, 49.2, and 50.9, respectively. The performance is consistent with that of our re-implementation (see Table above) but still has a gap (0.3~0.8 AP) in comparison with the reported performance in their README.@article{yolox2021,
title={{YOLOX}: Exceeding YOLO Series in 2021},
author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
journal={arXiv preprint arXiv:2107.08430},
year={2021}
}