search

seoungwugoh / STM

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

some problems in inference code #13

Closed pixelsmaker closed 4 years ago

pixelsmaker commented 4 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) )

I don't understand the meaning of B_list['o'], besides, x = self.conv1(f) + self.conv1_m(m) + self.conv1_o(o) f represents image, m means mask, while o I don't know its meaning.

I would be grateful if you could answer my questions.

seoungwugoh commented 4 years ago

Hi, o stands for other objects' mask. It is used only if there are other objects else it is a zero mask. o is created by summing all the masks except for the target object.

pixelsmaker commented 4 years ago

Hi, o stands for other objects' mask. It is used only if there are other objects else it is a zero mask. o is created by summing all the masks except for the target object.! thank you for you reply~