Torch-pruning

* 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.
* ...

* Fixed several problems

What's Changed
* Add [head pruning](https://github.com/VainF/Torch-Pruning/tree/master/examples/transformers#pruning-attention-heads) for transformers.
* Add benchmark tools for latency, memory, throughput, etc.
* Improved interfaces.
* Transformer Pruning Benchmarks: https://github.com/VainF/Torch-Pruning/tree/master/examples/transformers
* ...

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.2.5...v1.3.0

What's Changed

* [Pruning & Finetuning examples for Vision Transformers](https://github.com/VainF/Torch-Pruning/tree/master/examples/transformers)
* ADD Group Hessian / Taylor Importance. Quantitative results can be found [here](https://github.com/VainF/Torch-Pruning/tree/master#group-level-pruning).
* ADD new OpCounters for timm attention.
* Fixed some bugs in ViT examples and iterative pruning
* ...

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.2.4...v1.2.5

What's Changed
* Fixed alignment issues in group sparse training.
* Importance estimation & sparse training for bias.

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.2.3...v1.2.4

What's Changed
* Add latency test in https://github.com/VainF/Torch-Pruning/pull/236
* Support [Bert, Swin Transformers, Vision Transformers](https://github.com/VainF/Torch-Pruning/tree/master/examples/hf_transformers)
* Bugfixing for global pruning with grouped channels/dims
* ...

**Full Changelog**: https://github.com/VainF/Torch-Pruning/compare/v1.2.2...v1.2.3