A toolkit for WeatherBench based on PyTorch
Project description
wxbtool
A toolkit for WeatherBench based on PyTorch
Install
pip install wxbtool
Cheat sheet
Start a data set server for 3-days prediction of t850 by Weyn's solution
wxb dserve -m wxbtool.specs.res5_625.t850weyn -s Setting3d
Start a training process for a UNet model following Weyn's solution
wxb train -m wxbtool.zoo.res5_625.unet.t850d3sm_weyn
Start a testing process for a UNet model following Weyn's solution
wxb test -m wxbtool.zoo.res5_625.unet.t850d3sm_weyn
Start a data set server with unix socket binding
wxb dserve -m wxbtool.specs.res5_625.t850weyn -s Setting3d -b unix:/tmp/test.sock
Start a training process with unix socket binding
wxb train -m wxbtool.zoo.res5_625.unet.t850d3sm_weyn -d unix:/tmp/test.sock
How to use
- 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
uv build
uv publish
git tag va.b.c master
git push origin va.b.c
Contributors
- Mingli Yuan (Mountain)
- Ren Lu
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
wxbtool-0.1.18.tar.gz
(35.7 kB
view details)
Built Distribution
wxbtool-0.1.18-py3-none-any.whl
(46.8 kB
view details)
File details
Details for the file wxbtool-0.1.18.tar.gz
.
File metadata
- Download URL: wxbtool-0.1.18.tar.gz
- Upload date:
- Size: 35.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.4.29
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e6148b200a1fd6cbe10793cf4a8f0c3fa3c0471919d9dd9248642df70a8b4122 |
|
MD5 | 4a0ddb6c2eff566ee8289bba77690bf6 |
|
BLAKE2b-256 | 75f8dfab06692f7e222c5fd0cc0e46149b9462f553c68eed1a8cdb4002c0d942 |
File details
Details for the file wxbtool-0.1.18-py3-none-any.whl
.
File metadata
- Download URL: wxbtool-0.1.18-py3-none-any.whl
- Upload date:
- Size: 46.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.4.29
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d68a13ec74c7c6234f5a14bfc3c4ab7d9bba67294978b07bc5ab5279a2090be8 |
|
MD5 | f15a460305e58008c3a2c3bef16b4a99 |
|
BLAKE2b-256 | c7949deeafe650d25c5785e1b18e3f170c56eff942ed816aa55ef0d3902720a2 |