Torch-pruning

Latest version: v1.5.0

Safety actively analyzes 682457 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 2 of 5

1.3.6

What's Changed
* fix bug:inversed_idx do not match the origin index by pleb631 in https://github.com/VainF/Torch-Pruning/pull/321
* Remove ch_groups in tp.importance

New Contributors
* pleb631 made their first contribution in https://github.com/VainF/Torch-Pruning/pull/321

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.3.5...v1.3.6

1.3.5

What's Changed
* Merge by VainF in https://github.com/VainF/Torch-Pruning/pull/312
* V1.3 by VainF in https://github.com/VainF/Torch-Pruning/pull/315


**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.3.4...v1.3.5

1.3.4

What's Changed
* fix nan and inf bug in sparse learning by HollyLee2000 in https://github.com/VainF/Torch-Pruning/pull/310
* Fixed a bug in interactive pruning + iterative pruning + sparse training by VainF in https://github.com/VainF/Torch-Pruning/pull/311

New Contributors
* HollyLee2000 made their first contribution in https://github.com/VainF/Torch-Pruning/pull/310

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.3.3...v1.3.4

1.3.3

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.3.2...v1.3.3

1.3.2

* Fixed an issue in grouped conv.
* Include more normalization layers in importance estimation
* Add a MACs / FLOPs counter for timm Swin
* Add [sentinel normalizer](https://github.com/VainF/Torch-Pruning/commit/19dac7af9509e3946eae631cdc60152ac3972ec2), which normalizes the importance score by utilizing the k-th smallest element.
* ...

1.3.1

* Fixed several problems

Page 2 of 5

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.