Eric-mingjie/rethinking-network-pruning
PyTorch implementation of a research paper investigating whether structured network pruning provides benefits compared to training models from scratch.
Not currently ranked — collecting fresh signals.
star history
This repository reproduces the ICLR 2019 paper demonstrating that for structured network pruning, training a pruned model from scratch often achieves comparable or better accuracy than the traditional train-prune-finetune approach. The work challenges common assumptions about the value of learned “important” weights in pruning, arguing that the pruned architecture itself is more crucial to final model efficiency. The code includes implementations of several pruning methods and trained ImageNet models for reproducibility.
Frequently asked
- What is Eric-mingjie/rethinking-network-pruning?
- PyTorch implementation of a research paper investigating whether structured network pruning provides benefits compared to training models from scratch.
- Is rethinking-network-pruning open source?
- Yes — Eric-mingjie/rethinking-network-pruning is open source, released under the MIT license.
- What language is rethinking-network-pruning written in?
- Eric-mingjie/rethinking-network-pruning is primarily written in Python.
- How popular is rethinking-network-pruning?
- Eric-mingjie/rethinking-network-pruning has 1.5k stars on GitHub.
- Where can I find rethinking-network-pruning?
- Eric-mingjie/rethinking-network-pruning is on GitHub at https://github.com/Eric-mingjie/rethinking-network-pruning.