Skip to content

Latest commit

 

History

History
15 lines (10 loc) · 469 Bytes

File metadata and controls

15 lines (10 loc) · 469 Bytes

Diversity_Networks_CNN_Pytorch

This project uses the Determinant point process, a method proposed by the Diversity Network. It is a project that the model is lightened by applying it to a CNN model.

Zelda Mariet, Suvrit Sra "Diversity Networks: Neural Network Compression Using Determinantal Point Processes" https://arxiv.org/abs/1511.05077

Results

CIFAR-10/100

Run

we conducted experiments under

  • python 3.6
  • pytorch 1.2.0, torchvision 0.4.0, cuda10