PyDPF

PyDPF is an extensible package for differentiable particle filtering. Designed for researchers and practitioners working with deep sequential Monte Carlo methods.

See the full documentation at: https://python-dpf.readthedocs.io/en/latest/index.html

Check out our getting started tutorial at: https://python-dpf.readthedocs.io/en/latest/tutorial.html

If you use this package in your publication please cite our paper:

@article{brady2025pydpf,
      title={PyDPF: A Python Package for Differentiable Particle Filtering},
      author={John-Joseph Brady and Benjamin Cox and Yunpeng Li and V\'{i}ctor Elvira},
      year={2025},
      journal={arXiv preprint arXiv:2510.25693},
      url={https://arxiv.org/abs/2510.25693},
}

Metadata

Release files for pydpf 1.2.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pydpf 1.2.3
File	Size	Uploaded
pydpf-1.2.3.tar.gz	17.5 MB	Sep 29, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for pydpf 1.2.3
File	Interpreter	ABI	Platform	Reset
pydpf-1.2.3-py3-none-any.whl 78.9 kB Sep 29, 2026	Python 3	none	any	Details

Total release size: 17.6 MB

Release files / pydpf-1.2.3.tar.gz

Download URL	pydpf-1.2.3.tar.gz
Size	17.5 MB
Tags	Source
SHA-256 checksum How to use checksums	`a25dcec2023a7bf084b005f1ba31414b04f2122557527f5957b21b3c93898fde`
BLAKE2b-256 checksum How to use checksums	`a2f92b935ce1f488caf5a858badecedabc9899bb3a1cf4bc56cfbbe33947c5e3`
Upload date	Sep 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.14.3`

Release files / pydpf-1.2.3-py3-none-any.whl

Download URL	pydpf-1.2.3-py3-none-any.whl
Size	78.9 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d25644d08d4b99793f76d0dcdaa5be366a698edb60b9143766467945c063f97d`
BLAKE2b-256 checksum How to use checksums	`1334a816ebde5450c1bcc6c0dcbf12d3ee4bb08d424db5aa4220e0219ef5b06f`
Upload date	Sep 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.14.3`