search

Eclipsess / CHIP_NeurIPS2021

Code for CHIP: CHannel Independence-based Pruning for Compact Neural Networks (NeruIPS 2021).
33 stars 6 forks source link

How to decide sparsity on each layer for any model? #14

Closed leo811121 closed 1 year ago

leo811121 commented 1 year ago

First, thank you for contribution on structure pruning. I am impressed by this neat and efficient structure pruning method. However, I'd like to know how to decide sparsity on each layer for any model since I did not find any part mentioning this on paper and sparsity rate could make huge impact no matter on inference speed or accuracy.

Thank you.

Eclipsess commented 1 year ago

I appreciate your interest in our research.

Regarding your question, I just wanted to confirm that the sparsity in our work follows the configuration outlined in HRankPlus.