yangjun dfa27afb39 提交PaddleDetection develop 分支 d56cf3f7c294a7138013dac21f87da4ea6bee829		1 éve
..
_base_	dfa27afb39 提交PaddleDetection develop 分支 d56cf3f7c294a7138013dac21f87da4ea6bee829	1 éve
README.md	dfa27afb39 提交PaddleDetection develop 分支 d56cf3f7c294a7138013dac21f87da4ea6bee829	1 éve
yolof_r50_c5_1x_coco.yml	dfa27afb39 提交PaddleDetection develop 分支 d56cf3f7c294a7138013dac21f87da4ea6bee829	1 éve

YOLOF (You Only Look One-level Feature)

ModelZOO

注意:

YOLOF模型训练过程中默认使用8 GPUs进行混合精度训练，总batch_size默认为32。

Citations

@inproceedings{chen2021you,
  title={You Only Look One-level Feature},
  author={Chen, Qiang and Wang, Yingming and Yang, Tong and Zhang, Xiangyu and Cheng, Jian and Sun, Jian},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2021}
}

网络网络	输入尺寸	图片数/GPU	Epochs	模型推理耗时(ms)	mAP^val 0.5:0.95	Params(M)	FLOPs(G)	下载链接	配置文件
YOLOF-R_50_C5 (paper)	800x1333	4	12	-	37.7	-	-	-	-
YOLOF-R_50_C5	800x1333	4	12	-	38.1	44.16	241.64	下载链接	配置文件

README.md

YOLOF (You Only Look One-level Feature)

ModelZOO

Citations