Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can the Attention Network identify objects with dissimilar shape? #19

Open
wtupc96 opened this issue Mar 19, 2019 · 0 comments
Open

Can the Attention Network identify objects with dissimilar shape? #19

wtupc96 opened this issue Mar 19, 2019 · 0 comments

Comments

@wtupc96
Copy link

wtupc96 commented Mar 19, 2019

Hi, I've read the paper that it said the current model cannot transform zebras into horses and vice versa, and I tried doing so. However, I found that the masks from Attention Network were nearly all black and it failed finding the zebras or horses in the images, I've tried the threshold value with 0.1, 0.05, 0.01 but got the same result. I just cannot figure out why the Network can't find the object.

@wtupc96 wtupc96 closed this as completed Apr 21, 2019
@wtupc96 wtupc96 reopened this Apr 21, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant