v1.3.3: Bugfixing

Full Changelog: v1.3.2...v1.3.3

v1.3.2: A regular release with minor BugFixing.

• Fixed an issue in grouped conv.
• Include more normalization layers in importance estimation
• Add a MACs / FLOPs counter for timm Swin
• Add sentinel normalizer, which normalizes the importance score by utilizing the k-th smallest element.
• ...

v1.3.1

• Fixed several problems

v1.3.0

What's Changed

• Add head pruning 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: v1.2.5...v1.3.0

v1.2.5

What's Changed

• Pruning & Finetuning examples for Vision Transformers
• ADD Group Hessian / Taylor Importance. Quantitative results can be found here.
• ADD new OpCounters for timm attention.
• Fixed some bugs in ViT examples and iterative pruning
• ...

Full Changelog: v1.2.4...v1.2.5

v1.2.4

What's Changed

• Fixed alignment issues in group sparse training.
• Importance estimation & sparse training for bias.

Full Changelog: v1.2.3...v1.2.4

v1.2.3

What's Changed

• Add latency test in #236
• Support Bert, Swin Transformers, Vision Transformers
• Bugfixing for global pruning with grouped channels/dims
• ...

Full Changelog: v1.2.2...v1.2.3

v1.2.2: Improved tp.pruner & tp.importance

What's Changed

• Improved tp.pruner & tp.importance
• A pruning example of Huggingface Bert

Full Changelog: v1.2.1...v1.2.2

v1.2.1: Support Vision Transformers from Huggingface Transformers & Timm

• Support ViTs from Huggingface Transformers & Timm
• Improved Channel Grouping

Full Changelog: v.1.2.0...v1.2.1

v1.2.0: Improved Index Mapping

What's Changed

• Improved index mapping. Now tp.pruner can handle more networks.
• Fixed several bugs
• Support Growing Regularization
• Add Documents & Toturials