Eric-mingjie/rethinking-network-pruning

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1512 stars · 286 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

deep-learning machine-learning benchmarking deep-learning machine-learning computer-vision python network-pruning pytorch model-compression research-code iclr-2019 convolutional-neural-networks

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Eric-mingjie/rethinking-network-pruning")