https://github.com/labouteille/torchprune

Deep learning compression framework in Pytorch [WIP]
https://github.com/labouteille/torchprune

deep-learning knowledge-distillation model-compression pruning quantization

Last synced: 3 months ago
JSON representation

Deep learning compression framework in Pytorch [WIP]

• Host: GitHub
• URL: https://github.com/labouteille/torchprune
• Owner: LABouteille
• Created: 2021-09-26T12:23:55.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-07-30T17:59:48.000Z (over 3 years ago)
• Last Synced: 2025-04-11T22:39:15.445Z (about 1 year ago)
• Topics: deep-learning, knowledge-distillation, model-compression, pruning, quantization
• Language: Python
• Homepage:
• Size: 313 KB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# torchcompress

- A deep learning compression framework in Pytorch (work in progress) 

    - Support Filter pruning:

        - Conv -> Conv

        - Linear -> Linear

        - Conv -> Flatten -> Linear

        - Batchnorm2d/1d

        

# To do

- [ ] Pruning

    - [ ] Unstructured pruning

    - [ ] Structured pruning

- [ ] Quantization

    - [ ] Post Training Quantization

    - [ ] Quantization aware training

- [ ] Knowledge distillation

   - [ ] Offline distillation

   - [ ] Online distillation

   - [ ] Self distillation