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

Regarding the upsampling layer #83

Open
netw0rkf10w opened this issue Jan 2, 2019 · 2 comments
Open

Regarding the upsampling layer #83

netw0rkf10w opened this issue Jan 2, 2019 · 2 comments

Comments

@netw0rkf10w
Copy link

Hi,

Thanks a lot for the implementation!

Regarding upsampling, you used a custom BilinearUpSampling2D layer, which I guess cannot be learned (sorry if I'm mistaken).

I believe a better solution is to use the built-in Conv2DTranspose Keras layer for upconvolution (c.f. section 3.3 of the FCN paper).

Best regards.

@netw0rkf10w
Copy link
Author

I have checked the code again and there seems to have a more serious problem: there is no skip connections at all between coarse and fine output layers :(

@NickChang97
Copy link

Yes I found it also. There is no skip connections, a little pity. But the code's structure is nice

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

2 participants