-
Notifications
You must be signed in to change notification settings - Fork 75
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
R2Conv acts on 5-D tensor #22
Comments
Hi @yokinglou Let me understand exactly what you need to do.
then your (reshaped) input can have field type
Then, you can use the R2Conv as usual.
Does this answer your question? Best, |
Hi Gabriele Thanks for your detailed reply! I think the first case is what I want to do. Thanks, |
Hi @yokinglou I think this is an expected behaviour, as you are effectively increasing the batch size. I feel like this issues is not really related to our library, but rather to some design choice in your experiments. Unfortunately, I am not sure I understand what you mean in your last question. Best, |
I agree with you. I will try more to improve efficiency. Best, |
Hi @yokinglou , I am happy to read this! Thanks! Please, let me know if you encounter any other issues :) Best, |
There is a situation when images are stacked twice. The shape of the structured image tensor is (B, S, C, H, W) where B represents batch size and S the number of stacked images.
Could R2conv directly act or broadcast on such a 5-D tensor?
The text was updated successfully, but these errors were encountered: