Jacobi93 / Alpha-IoU

[NeurIPS 2021] Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
GNU General Public License v3.0
154 stars 21 forks source link

求助 #11

Closed yxx-byte closed 2 years ago

Jacobi93 commented 2 years ago

感谢关注,请看:

Alpha-IoU Losses

Alpha-IoU losses can be configured in Line 131 of utils/loss.py, functionesd as 'bbox_alpha_iou'. The alpha values and types of losses (e.g., IoU, GIoU, DIoU, CIoU) can be selected in this function, which are defined in utils/general.py. Note that we should use a small constant epsilon to avoid torch.pow(0, alpha) or denominator=0.