Training and Evaluation pipeline#105
Closed
Sharkyii wants to merge 4 commits intoopenclimatefix:mainfrom
Sharkyii:feature/training-eval-pipeline
Closed
Training and Evaluation pipeline#105Sharkyii wants to merge 4 commits intoopenclimatefix:mainfrom Sharkyii:feature/training-eval-pipeline
Sharkyii wants to merge 4 commits intoopenclimatefix:mainfrom
Sharkyii:feature/training-eval-pipeline
Conversation
| "zarr==2.18.3", | ||
| "pvnet==4.1.19", | ||
| "ocf-data-sampler==0.2.32", | ||
| "ocf-data-sampler==0.2.10", |
Contributor
There was a problem hiding this comment.
how come you had to move this down?
| # number_of_conv3d_layers: 6 | ||
| # conv3d_channels: 32 | ||
| # image_size_pixels: 24 | ||
| ukv: |
Contributor
There was a problem hiding this comment.
how did you use ukv? I thought only gfs was accessible?
| "cpu", "--device", help="Device to run evaluation on ('cpu' or 'cuda')" | ||
| ), | ||
| quantiles: str = typer.Option( | ||
| "0.02,0.1,0.25,0.5,0.75,0.9,0.98", |
Contributor
There was a problem hiding this comment.
Could you get this from the config?
| @@ -0,0 +1,183 @@ | |||
| import logging | |||
Contributor
There was a problem hiding this comment.
does https://github.com/openclimatefix/open-data-pvnet/blob/main/run.py not already do this?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This PR introduces a stable, end-to-end training and evaluation pipeline for PVNet, currently validated on GSP-only data.
To simplify debugging and ensure pipeline stability during initial integration, the optimizer was intentionally switched from
EmbAdamWReduceLROnPlateauto a plainAdamW. This change reduces training complexity while validating data flow, model wiring, and configuration handling.The original optimizer and learning-rate scheduling will be reintroduced in a follow-up PR once the full multi-encoder setup is finalized.
At this stage:
Planned follow-ups:
EmbAdamWReduceLROnPlateauonce architecture and inputs are finalizedTwo reference documents have been added to explain the pipeline design and usage for future contributors.
Fixes #7
How Has This Been Tested?
If your changes affect data processing, have you plotted any changes?
Checklist