A Python package for Earthformer
Project description
Earthformer
A Python package for Earth forecasting transformer
- Free software: Apache Software License 2.0
- Documentation: https://opengeos.github.io/earthformer
Introduction
This repository turns the amazon-science/earth-forecasting-transformer repository into a Python package, making it easier to install and use. To learn more about Earthformer, please refer to the NeurIPS 2022 paper: Earthformer: Exploring Space-Time Transformers for Earth System Forecasting. Credits to the authors and their repository for the original implementation.
Installation
The earthformer
package is available on PyPI. To install it, run:
pip install earthformer
Earthformer has several optional dependencies. It is recommended to create a new conda environment and install the dependencies with conda:
conda create -n earthformer python=3.10
conda activate earthformer
conda install -c conda-forge mamba
mamba install -c conda-forge pytorch torchvision pytorch-lightning==1.7.7
mamba install -c conda-forge nvidia-apex omegaconf
mamba install -c conda-forge xarray netcdf4 opencv
pip install earthnet earthformer
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file earthformer-0.0.4.tar.gz
.
File metadata
- Download URL: earthformer-0.0.4.tar.gz
- Upload date:
- Size: 1.2 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 038b7620e511789d6e8905aaeb687911ecea1c61f09980dddff8d7ad95cb77fa |
|
MD5 | 1c1b73f4a7f9deb01d1daa326efeede2 |
|
BLAKE2b-256 | 1fdb3b69f54dc4b15f8d163a7335f002b9bb55e1e593c8144f0b408410401ed5 |
File details
Details for the file earthformer-0.0.4-py2.py3-none-any.whl
.
File metadata
- Download URL: earthformer-0.0.4-py2.py3-none-any.whl
- Upload date:
- Size: 1.2 MB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 808b698dbe5c11b1543ec51b4b4ccc41ce6610e16f202d3351428ecc46750770 |
|
MD5 | 59066312cec6b39892a407ff8b7b8a86 |
|
BLAKE2b-256 | 60dbd5fa5c076512f2fb1802d01f345f0cb294a47ca3feac68aedaa2001c3ed9 |