Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

If we're not training the u-net, then maybe don't include future satellite imagery in the batches? #136

Open
JackKelly opened this issue Jun 15, 2022 · 1 comment
Assignees
Labels
enhancement New feature or request

Comments

@JackKelly
Copy link
Member

Good to reduce memory requirements.

But will need some changes to the code (including the plotting code)

Not a priority

@JackKelly JackKelly self-assigned this Jun 16, 2022
@JackKelly JackKelly added the enhancement New feature or request label Jun 16, 2022
@JackKelly JackKelly moved this from Todo to In Progress in Nowcasting Jun 16, 2022
@JackKelly JackKelly moved this to Todo in Nowcasting Jun 16, 2022
@JackKelly
Copy link
Member Author

Actually, I keep running out of GPU RAM, so I am going to implement this today! I think it might be quite simple and won't actually need any code changes!! I'm attempting to run a model now with the change.

JackKelly added a commit that referenced this issue Jun 16, 2022
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
enhancement New feature or request
Projects
No open projects
Status: In Progress
Development

No branches or pull requests

1 participant