An implementation of bayesian neural networks which I use for research purposes.
Installation
pip install bnn-pytorch
bnn-pytorch requires Python 3.11 or newer and is imported as bnn.
The following repositories were partly a basis for this package:
Javier Antoran - Bayesian Neural Networks
Kumar Shridhar - PyTorch Bayesian CNN
Development
If you want to work on this repository, clone it (or your fork)
git clone https://github.com/RonMcKay/bnn.git
and install it using uv
uv sync
Run the checks locally with:
make test
This runs Ruff formatting/linting and the unit tests with a minimum 95% coverage requirement for the reusable bnn package. The bnn/examples modules are reviewed and smoke-tested separately, but are excluded from that coverage threshold.
Check the fully Bayesian example against the current public APIs without running its full training loop with:
make example-smoke
Please make all your pull requests against main.
1 maintainer
Metadata
1 maintainer
Release files for bnn-pytorch 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| bnn_pytorch-1.0.0.tar.gz | 95.7 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| bnn_pytorch-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 110.5 kB
Release files / bnn_pytorch-1.0.0.tar.gz
| Download URL | bnn_pytorch-1.0.0.tar.gz |
|---|---|
| Size | 95.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
69120f2fae860353bf8a92d5ca0cf36f9f77b3f55470914889737be5809c1f0b
|
|
BLAKE2b-256 checksum How to use checksums |
fdda5b8905c80199ee6008f51178fa575941e846f36e03f18d228a1627454dab
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 20, 2026.
Transparency logRelease files / bnn_pytorch-1.0.0-py3-none-any.whl
| Download URL | bnn_pytorch-1.0.0-py3-none-any.whl |
|---|---|
| Size | 14.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4e7f6936930c6292b33c030e58cd624cc855261336182256c9db400fc8e822b7
|
|
BLAKE2b-256 checksum How to use checksums |
36832d0764c21267596c4b7e9e9a23992e0552bed5ef624358edb08156deb2a3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 20, 2026.
Transparency logSecurity for bnn-pytorch 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for bnn_pytorch-1.0.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 20, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
