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

Training Problems #8

Closed
XiaoBuL opened this issue Sep 23, 2021 · 3 comments
Closed

Training Problems #8

XiaoBuL opened this issue Sep 23, 2021 · 3 comments

Comments

@XiaoBuL
Copy link

XiaoBuL commented Sep 23, 2021

I encountered some problems when training the Go_Pro dataset on MIMO-UNet++. May I ask the author during the training process, will there be some unknown color blocks in the image generated at certain positions of the image?

@chosj95
Copy link
Owner

chosj95 commented Sep 23, 2021

Hi,

I hope the following answers will help you.

I encountered some problems when training the Go_Pro dataset on MIMO-UNet++.

First, the MIMO-UNet++ model is the geometric ensemble of the MIMO-UNet+.
That is, there is no separate model.
The implementation details of the MIMO-UNet++ are described in our paper and this issue(#2).

May I ask the author during the training process, will there be some unknown color blocks in the image generated at certain positions of the image?

Sorry... I'm not sure what color block you're talking about.
Could you give me more information about such a phenomenon?

@XiaoBuL
Copy link
Author

XiaoBuL commented Sep 23, 2021

test
Such like this. Left is the sharp image, right is the generated image.

@chosj95
Copy link
Owner

chosj95 commented Oct 12, 2021

Sorry for the late reply.

I think it is a problem caused by the data type when saving the image.
Using the clamp (or clip) function may help you.

@chosj95 chosj95 closed this as completed Oct 12, 2021
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