This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)
Apache License 2.0
358
stars
48
forks
source link
If there's a bug? target_classes_onehot.scatter_(2, target_classes.unsqueeze(-1), 1) #24