microsoft/nni

Does nni contain some new pruning base methods？

Open

#4,567 opened on Feb 21, 2022

View on GitHub
 (6 comments) (0 reactions) (1 assignee)Python (13,504 stars) (1,830 forks)batch import
good first issuemodel compressionnew feature

Description

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

Tech stack
pythonpytorch
Domain
machine learningtooling
Issue type
research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Familiarity with NNI pruning moduleBasic PyTorch knowledge
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
The issue asks about adding a new pruning method (e.g., HRank) to NNI. The user wants to know which base class to extend and where to implement it. Refer to the abstract pruner in nni/compression/pytorch/pruning/basic pruner.py and the existing pruners like NormPruner. The research should explore how to create a new pruner class that inherits from the base and registers it. Also check the latest NNI documentation and examples for custom pruners.