weijiawu / TransDETR

[IJCV 2024] TransDETR: End-to-end Video Text Spotting with Transformer
101 stars 11 forks source link

Code Question #11

Open lsabrinax opened 2 years ago

lsabrinax commented 2 years ago

https://github.com/weijiawu/TransDETR/blob/b6c73c5fd773e5e0d87f394631cfcab6e167b070/models/TransDETR_ignored.py#L379

the code above should be track_instances.angle[active_idxes] = torch.abs(active_track_angle - gt_angle)? because the first dim of track_instances.angle is num_queries