search

meituan / YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.
GNU General Public License v3.0
5.72k stars 1.03k forks source link

Is there a way to change model_fitness similar to YOLOv5 so you can increase recall or precision? #323

Closed sarmientoj24 closed 2 years ago

mtjhl commented 2 years ago

Did you mean how to increase the model's depth and width? If it is, you can change the depth_multiple and width_multiple here: https://github.com/meituan/YOLOv6/blob/ccf8b43e0ec575c2ee7b6e035e5ccb0f1512c4c8/configs/yolov6_tiny.py#L5

Chilicyy commented 2 years ago

@sarmientoj24 Thanks for your attention! Currently we don't support this feature. We will consider your suggestion and add it in subsequent releases.