Torch-uncertainty

Latest version: v0.3.1

Safety actively analyzes 682244 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 3 of 3

0.1.3

New functionalities

* Regression training and testing (routine, dataset, experiment, etc)
* Bayesian Neural Networks (Linear, Conv, Sampler, ELBO, tutorial)
* Deep Ensembles (Routine & model)
* Add VGG
* relax constraints on the packages
* Improve coverage

Pull Requests merged
* Add contribution page and rework readme :book: in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/26
* :sparkles: Enable regression & misc in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/27
* :sparkles: Add support for regression & BNNs in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/30


**Full Changelog**: https://github.com/ENSTA-U2IS/torch-uncertainty/compare/v0.1.2...v0.1.3

0.1.2

What's Changed

* Rework baselines to increase code reuse and simplify their use.
* Add post-hoc temperature scaling
* Add ImageNet variations (A, O, R)
* Add dataset autodownload
* Add transforms for PixMix.
* Update packages

Pull Requests
* Rework baselines by alafage in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/25
* Merge dev in main :sparkles: by o-laurent in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/24


**Full Changelog**: https://github.com/ENSTA-U2IS/torch-uncertainty/compare/v0.1.1...v0.1.2

0.1.1

What's Changed
* Doc theme by alafage in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/12
* Add logos :art:
* Add WR baselines for BatchEnsembles and Masksembles :sparkles:
* Switch to ImageNet structure by default and add the corresponding parameter :hammer:
* Add CIFAR-10H support :sparkles:
* Refactor Packed layers to ease understanding :hammer:
* Start handling HF weights :sparkles:
* Improve the documentation & ReadMe :books:
* Add a reference page :book:
* Improve test coverage :heavy_check_mark:
* Update packages :zap:
* Make the logo's background transparent :shirt:
* Remove old implementations of the metrics :fire:
* Add channel-last support :sparkles:
* Major metrics updates :bug: :art:
* Improve tests

New Contributors
* pomonam made their first contribution in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/13
* nshdesai made their first contribution in https://github.com/ENSTA-U2IS/torch-uncertainty/pull/14

**Full Changelog**: https://github.com/ENSTA-U2IS/torch-uncertainty/compare/v0.1.0...v0.1.1

0.1.0

- Add first baselines
- Add metrics
- Add tests
- Add documentation

Page 3 of 3

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.