# Eric-mingjie/rethinking-network-pruning

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

Repository: https://github.com/Eric-mingjie/rethinking-network-pruning
Canonical: https://ross.abutalabs.com/products/rethinking-network-pruning
Language: Python
License: MIT
License Family: permissive
Topics: convolutional-neural-networks, network-pruning, deep-learning, pytorch
Last push: 2020-06-07T10:04:45+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2883, "days_push": 2278, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1512, forks 286 (observed 2026-08-28T04:04:56.138617+00:00)

## What it is
A PyTorch research codebase reproducing the ICLR 2019 paper 'Rethinking the Value of Network Pruning', which shows pruned models trained from scratch match or beat fine-tuned pruned models. It includes implementations of several structured pruning methods and trained ImageNet models.

## Use cases
- reproduce network pruning paper results
- train pruned CNN models from scratch
- compare structured pruning methods
- apply channel pruning implementations to my own research
- download pretrained pruned ImageNet models
- study whether lottery ticket initialization helps

## When to choose
- researching structured network pruning or model compression
- needing reference implementations of pruning algorithms in PyTorch
- reproducing or benchmarking against the ICLR 2019 paper

## When to avoid
- needing a production-ready model compression toolkit
- requiring actively maintained code with recent framework support
- working outside PyTorch or with non-CNN architectures

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, benchmarking
- domain: deep-learning, machine-learning, computer-vision
- platform: python
- tags: network-pruning, pytorch, model-compression, research-code, iclr-2019, convolutional-neural-networks

## Member repositories
- Eric-mingjie/rethinking-network-pruning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:56.138617+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:18.310347+00:00, confidence not recorded.
  - readme: https://github.com/Eric-mingjie/rethinking-network-pruning (fetched 2026-08-28T04:04:56.138617+00:00, sha b26c898cd88d)
- Data as of 2026-08-30T08:39:29.467469+00:00.