Metadata-Version: 2.1
Name: wxbtool
Version: 0.0.50
Summary: A toolkit for WeatherBench based on PyTorch
Home-page: https://github.com/caiyunapp/wxbtool
Author: Mingli Yuan
Author-email: mingli.yuan@gmail.com
License: UNKNOWN
Project-URL: Documentation, https://packaging.python.org/tutorials/distributing-packages/
Project-URL: Source, https://github.com/caiyunapp/wxbtool
Project-URL: Tracker, https://github.com/caiyunapp/wxbtool/issues
Description: # wxbtool
        
        A toolkit for WeatherBench based on PyTorch
        
        Warning: This project is at its early stage and the api is not very stable
        
        Install
        --------
        
        ```bash
        pip install wxbtool
        ```
        
        Cheat sheet
        -----------
        
        Start a data set server for 3-days prediction of t850 by Weyn's solution
        ```bash
        wxb dserve -m wxbtool.specs.res5_625.t850weyn -s Setting3d
        ```
        
        Start a training process for a UNet model following Weyn's solution
        ```bash
        wxb train -m wxbtool.zoo.res5_625.unet.t850d3sm_weyn
        ```
        
        Start a testing process for a UNet model following Weyn's solution
        ```bash
        wxb test -m wxbtool.zoo.res5_625.unet.t850d3sm_weyn
        ```
        
        How to use
        -----------
        
        * [quick start](https://github.com/caiyunapp/wxbtool/wiki/quick-start)
        * understanding the physical process by plotting
        * develop your own neural model
        * try a toy physical model
        * explore the possibility to combine neural and physical model together
        
        How to release
        ---------------
        
        ```bash
        python3 setup.py sdist bdist_wheel
        python3 -m twine upload dist/*
        
        git tag va.b.c master
        git push origin va.b.c
        ```
        
        Contributors
        ------------
        
        * Mingli Yuan ([Mountain](https://github.com/mountain))
        * Ren Lu
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
