📘Documentation | 🛠️Installation | 🆕News
This repository is an open-source project for weather prediction (single and multiple variable prediction), which is built as an extensive project of OpenSTL. We are working on it and new features is updating!
[2023-04-27] UniWeat
v0.1.0 is initalized (on updating).
This project has provided an environment setting file of conda, users can easily reproduce the environment by the following commands:
git clone https://github.com/Westlake-AI/UniWeat
cd UniWeat
conda env create -f environment.yml
conda activate UniWeat
python setup.py develop # or `pip install -e .`
Dependencies
- argparse
- fvcore
- numpy
- hickle
- scikit-image
- scikit-learn
- torch
- timm
- tqdm
- xarray==0.19.0
Please refer to install.md for more detailed instructions.
Please see get_started.md for the basic usage. Here is an example of single GPU non-distributed training SimVP on Moving MNIST dataset.
bash tools/prepare_data/download_mmnist.sh
python tools/train.py -d mmnist --lr 1e-3 -c configs/mmnist/simvp/SimVP_gSTA.py --ex_name mmnist_simvp_gsta
We support various spatiotemporal prediction learning (STL) methods and will provide benchmarks on various STL datasets.
-
Spatiotemporal Prediction Methods.
Currently supported methods
Currently supported MetaFormer models for SimVP
- ViT (ICLR'2021)
- Swin-Transformer (ICCV'2021)
- MLP-Mixer (NIPS'2021)
- ConvMixer (Openreview'2021)
- UniFormer (ICLR'2022)
- PoolFormer (CVPR'2022)
- ConvNeXt (CVPR'2022)
- VAN (ArXiv'2022)
- IncepU (SimVP.V1) (CVPR'2022)
- gSTA (SimVP.V2) (ArXiv'2022)
- HorNet (NIPS'2022)
- MogaNet (ArXiv'2022)
-
Spatiotemporal Predictive Learning Benchmarks.
Currently supported datasets
- Human3.6M (TPAMI'2014) [download] [config]
- KTH Action (ICPR'2004) [download] [config]
- KittiCaltech Pedestrian (IJRR'2013) [download] [config]
- Moving MNIST (ICML'2015) [download] [config]
- Moving FMNIST (ICML'2015) [download] [config]
- TaxiBJ (AAAI'2017) [download] [config]
- WeatherBench (ArXiv'2020) [download] [config]
This project is released under the Apache 2.0 license. See LICENSE
for more information.
UniWeat is an open-source project for single and multiple variable weather prediction applications created by researchers in CAIRI AI Lab. We encourage researchers interested in weather prediction to contribute to UniWeat! UniWeat is an extensive project of OpenSTL.
If you are interested in our repository or our paper, please cite the following paper:
@misc{li2023uniweat,
title={UniWeat: Unified Toolbox for Weather Prediction},
author={Li, Siyuan and Lin, Haitao and Tan, Cheng and Chen, Lei and Li, Stan Z},
howpublished = {\url{https://github.com/Westlake-AI/UniWeat}},
year={2023}
}
For adding new features, needing helps, or reporting bugs associated with UniWeat
, please open a GitHub issue and pull request with the tag "new features", "help wanted", or "enhancement". Feel free to contact us through email if you have any questions. Enjoy!
- Siyuan Li (lisiyuan@westlake.edu.cn), Westlake University & Zhejiang University
- Haitao Lin (linhaitao@westlake.edu.cn), Westlake University & Zhejiang University
- Cheng Tan (tancheng@westlake.edu.cn), Westlake University & Zhejiang University