metnet

metnet copied to clipboard

Pytorch-Lightning

3

# Pull Request ## Description Converted to pytorch-lightning for easy parallelization. Needs work on the forward pass. How do we create a forward pass dependent on a random lead time...

ValterFallenius

Network not learning

7

**Training loss is not decreasing** I have implemented the network in the PR "lightning" branch with pytorch lightning and tried to find any bugs. The network compiles without issues and...

ValterFallenius

Memory issues in training loop

15

## Detailed Description I am running on a slightly down sampled dataset with spatial dimensions 448x448. The shape of my input tensor is (None, t = 7, c = 75,...

ValterFallenius

## Detailed Description MetNet was trained on GOES and MRMS data, and MetNet-2 on that plus some NWP initialization parameters. All that data is publicly accessible with no restrictions from...

jacobbieker

Add HF model cards with carbon costs for training

2

## Detailed Description HF model hub allows for model cards for models uploaded there, and they have a section for more standardized reporting of carbon costs associated with training that...

jacobbieker

## Detailed Description There is a huggingface repo taht can construct our MetNet and run example through it with gradio. It still neds to be updated to the latest version,...

jacobbieker

# Pull Request ## Description Adds the same pydocstyle linter as in https://github.com/openclimatefix/nowcasting_utils/pull/23 Relates to issue #1 ## How Has This Been Tested? It runs in GitHub Actions - [...

jacobbieker

Format docstrings so they pass `pydocstyle`'s criteria

1

## Detailed Description We plan to use [`pydocstyle`](http://www.pydocstyle.org/en/stable/) to automatically check that our docstrings conform to a standard format. It would be amazing to have help tweaking our existing docstrings...

JackKelly

[pre-commit.ci] pre-commit autoupdate

1

updates: - [github.com/pre-commit/pre-commit-hooks: v4.4.0 → v4.6.0](https://github.com/pre-commit/pre-commit-hooks/compare/v4.4.0...v4.6.0) - https://github.com/charliermarsh/ruff-pre-commit → https://github.com/astral-sh/ruff-pre-commit - [github.com/astral-sh/ruff-pre-commit: v0.0.261 → v0.6.4](https://github.com/astral-sh/ruff-pre-commit/compare/v0.0.261...v0.6.4) - [github.com/psf/black: 23.3.0 → 24.8.0](https://github.com/psf/black/compare/23.3.0...24.8.0) - [github.com/pre-commit/mirrors-prettier: v3.0.0-alpha.6 → v4.0.0-alpha.8](https://github.com/pre-commit/mirrors-prettier/compare/v3.0.0-alpha.6...v4.0.0-alpha.8)

pre-commit-ci[bot]

Is there a way to easily change the target patch size?

1

For example, if I wanted the target patch to be 1/2 of the input size instead of 1/4, would that be possible?

lucasbs97