search

amazon-science / omni-detr

PyTorch implementation of Omni-DETR for omni-supervised object detection: https://arxiv.org/abs/2203.16089
Other
64 stars 6 forks source link

about the ratio of full and omni label #13

Closed lo202ng closed 1 year ago

lo202ng commented 1 year ago

Can I set fully_labeled to 0 while pointsK to 1 which means train with only point anotation？