microsoft/nni

Does nni contain some new pruning base methods?

Open

#4.567 geöffnet am 21. Feb. 2022

Auf GitHub ansehen
 (6 Kommentare) (0 Reaktionen) (1 zugewiesene Person)Python (13.504 Stars) (1.830 Forks)batch import
good first issuemodel compressionnew feature

Beschreibung

Describe the issue: Sorry to bother you, in nni, the current basic pruning strategies are Norm, FPGM, ActivationPruner, TaylorFOWeightPruner, etc. Are there other basic strategies, such as HRank, if I want to add it myself, where do I need to rewrite it?

Environment:

  • NNI version: V2.6
  • Training service (local|remote|pai|aml|etc): local
  • Client OS: linux
  • Server OS (for remote mode only):
  • Python version: 3.8
  • PyTorch/TensorFlow version: pytorch1.8
  • Is conda/virtualenv/venv used?: conda
  • Is running in Docker?: no

How to reproduce it?:

Contributor Guide