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

Downscaled Images are black #17

Open
BenjaminGemperle opened this issue May 27, 2021 · 4 comments
Open

Downscaled Images are black #17

BenjaminGemperle opened this issue May 27, 2021 · 4 comments

Comments

@BenjaminGemperle
Copy link

I managed to get the provided models running, however when I run it the downscaled pictures are just black and therefore so are the upscaled pictures. The pictures have the correct amount of pixels and the ratio is correct. Does anyone know what might cause this issue?

@vardenppp
Copy link

Please check the value of pixels.The default setting is 0~255(rgb range).

@RobinDeBock
Copy link

RobinDeBock commented Dec 24, 2021

Please check the value of pixels.The default setting is 0~255(rgb range).

Can you tell me how to check this properly? And, if so, could this be included in the README?

I'm considering a variety of issues, and I'd like to rule out this option as quickly as possible.

@tprdk
Copy link

tprdk commented Feb 2, 2022

I get the exact same result with you. All down sampled image pixels are 0. I think issue is in the adaptive grid sampler model.
In the grid sampler.py file forward(img, kernels, offsets_h, offsets_v, offset_unit, padding, output) line output array always return full of 0. Is there any advice to handle that?

@garrett-partenza-us
Copy link

I am experiencing the same issue, all output arrays from the forward method of the custom downsampler function are zero.

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

5 participants