seoungwugoh / STM

Video Object Segmentation using Space-Time Memory Networks
405 stars 81 forks source link

use of B_list['o'] #36

Open jaypatravali opened 3 years ago

jaypatravali commented 3 years ago

B_list['o'].append( (torch.sum(masks[:,1:o], dim=1) + \ torch.sum(masks[:,o+1:num_objects+1], dim=1)).clamp(0,1) ) at https://github.com/seoungwugoh/STM/blob/905f11492a6692dd0d0fa395881a8ec09b211a36/model.py#L217

sorry, I follow this operation can you explain?

sugar-fly commented 2 years ago

I have same question,

B_list['o'].append( (torch.sum(masks[:,1:o], dim=1) + \ torch.sum(masks[:,o+1:num_objects+1], dim=1)).clamp(0,1) ) at

https://github.com/seoungwugoh/STM/blob/905f11492a6692dd0d0fa395881a8ec09b211a36/model.py#L217

sorry, I follow this operation can you explain?

I have same question, do you have solved it now?