deepcam-cn / yolov5-face

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
GNU General Public License v3.0
2.06k stars 497 forks source link

yolov5m-face training mAP is 0 #286

Open tiedan9999 opened 5 months ago

tiedan9999 commented 5 months ago

同样的参数配置,在yolov5s-face上训练结果和作者一样,但在yolov5m-face上训练就一点效果没有?如果换成yolov5m-face的话,需要额外修改什么配置或者参数么? With the same parameter configuration, the training results on yolov5s-face are the same as the author's, but the training results on yolov5m-face are not effective at all. Are there any additional configurations or parameters that need to be changed if switching to yolov5m-face?