torchfits 1.0.0rc4

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

torchfits

torchfits is FITS I/O for PyTorch: images and tables as tensors / Arrow, with a multi-threaded C++ engine (vendored CFITSIO). Optional datasets, transforms, and a torchfits CLI sit on top.

Current: 1.0.0rc4 (prerelease). Docs: stable (latest v* tag) · edge (main tip).

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). Source / GPU notes: Install.

At a glance

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

Quick start

import torchfits

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

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
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

Develop

Pixi-first (do not use bare python for project work):

git clone https://github.com/astroai/torchfits.git
cd torchfits
pixi install
pixi run preflight-push   # fast gate while editing
pixi run test             # full unit suite
pixi run ci-local         # pre-push parity

Agent conventions: AGENTS.md. Release process: docs/release.md.

License

MIT