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-0.1.12.tar.gz
(31.7 kB
view details)
Built Distribution
wxbtool-0.1.12-py3-none-any.whl
(42.5 kB
view details)
File details
Details for the file wxbtool-0.1.12.tar.gz
.
File metadata
- Download URL: wxbtool-0.1.12.tar.gz
- Upload date:
- Size: 31.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.4.29
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 06b24736d2a74d823aa341799a2fe99278f6de19458c85d1771debb73ae5b094 |
|
MD5 | acf4c5d22e6a047fd7ca506d8a748d59 |
|
BLAKE2b-256 | 469bc9a887914f485e535a3ec32a40f3bb3a8490202c3c4b4ea5e8f02fe15777 |
File details
Details for the file wxbtool-0.1.12-py3-none-any.whl
.
File metadata
- Download URL: wxbtool-0.1.12-py3-none-any.whl
- Upload date:
- Size: 42.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.4.29
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 000983c65ce31866d3c22174530b4709e823917c228aff901f3d603becd80a5d |
|
MD5 | 133586d1c5c302ae514eacd428f7578d |
|
BLAKE2b-256 | 7510e339d2a01fa66fd5985ac5b84e9837cf2dedf27e886816554f7321a9292c |