torchfits 1.0.0rc1

FITS I/O for PyTorch with native tensor reads, datasets, and transforms

torchfits

torchfits reads and writes FITS as PyTorch tensors and Arrow dataframes. A multi-threaded C++ engine (vendored CFITSIO) handles images, tables, headers, compression, and MEF files. Optional datasets, transforms, and a torchfits CLI sit on top.

Current release: 1.0b1. Docs: astroai.github.io/torchfits.

Install

pip install torchfits

Requires Python 3.10+ and PyTorch 2.10. Pre-built wheels for Linux x86_64 and macOS arm64 (CFITSIO is vendored).

At a Glance

Task	torchfits
Image → GPU tensor	torchfits.read_tensor("img.fits", device="cuda")
Write a tensor	torchfits.write("out.fits", tensor)
Filter a catalog in C++	table.read(..., where="MAG < 20")
Open a MEF	with torchfits.open("mef.fits") as hdul: …
Train	FitsImageDataset + make_loader(..., num_workers=4)
Shell	torchfits info / header / convert / …

Quick Start

import torchfits

tensor = torchfits.read_tensor("image.fits", hdu=0, device="cpu")

# FITS tables → dataframes (Arrow by default)
table = torchfits.table.read(
    "catalog.fits",
    columns=["RA", "DEC", "MAG_G"],
    where="MAG_G < 20.0",
)

torchfits info science.fits
torchfits convert catalog.fits out.parquet --hdu 1   # --to optional
torchfits cutout 'science.fits[100:256,100:256]' cutout.fits

Learn more

Documentation	Quickstart, API, CLI, galleries
Examples	Runnable scripts + transform plots
Benchmarks	Methodology and scorecards
Changelog	Release notes

Contributing

git clone https://github.com/astroai/torchfits.git
cd torchfits
pixi install
pixi run test

License

MIT