Closed twmht closed 5 years ago
just remove the loss of attribute classification, or set lambda to 0 in https://github.com/iamhankai/attribute-aware-attention/blob/ab3210705524bcb56f0121de0bcd47f3f93fb6c5/cub_demo.py#L98
very interesting. I am going to do the experiment. How about the other lambda? Do they remain unchanged?
very interesting. I am going to do the experiment. How about the other lambda? Do they remain unchanged?
Yes, unchanged.
close.
Hi,
from the table(1) in the paper, you mentioned that the network can be trained without attribute label.
in such manner, what is the form of the final loss function? Do we only need to care about the categorization loss?