https://github.com/tpys/ai-models-fuxi

https://github.com/tpys/ai-models-fuxi

Last synced: 10 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/tpys/ai-models-fuxi
• Owner: tpys
• License: apache-2.0
• Created: 2023-10-31T00:05:23.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-05-10T08:18:11.000Z (6 months ago)
• Last Synced: 2024-06-06T12:48:28.884Z (5 months ago)
• Language: Python
• Size: 11.7 KB
• Stars: 34
• Watchers: 1
• Forks: 6
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-LWMs - [link

README

        
# ai-models-fuxi

`ai-models-fuxi` is an [ai-models](https://github.com/ecmwf-lab/ai-models) plugin to run [Fudan's FuXi](https://github.com/tpys/FuXi.git).

FuXi: A cascade machine learning forecasting system for 15-day global weather forecast,arXiv preprint: 2306.12873, 2022. https://arxiv.org/pdf/2306.12873.pdf

FuXi was created by Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Yuan Qi, Hao Li. It is released by Fudan University.

The model weights are made available under the terms of the BY-NC-SA 4.0 license.

The commercial use of these models is forbidden. Please download the pre-trained models from Google drive: https://drive.google.com/drive/folders/1CXxv-s4DdIHVxSCGsDLMn38n8Shk3fRs

For use other input data eg: ERA5 and GFS see  for further details.

### Installation

To install the package, run:

```bash

pip install ai-models-fuxi

```

This will install the package and its dependencies, in particular the ONNX runtime. The installation script will attempt to guess which runtime to install. You can force a given runtime by specifying the the `ONNXRUNTIME` variable, e.g.:

```bash

ONNXRUNTIME=onnxruntime-gpu pip install ai-models-fuxi

```