CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression

Code

• github.com/Aldiom/nn_benchmark
  tf★ 0
• github.com/larry0123du/Decompose-CNN
  pytorch★ 0

Abstract

Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end smart devices such as smart phones. We propose a CNN compression method based on CP-decomposition and Tensor Power Method. We also propose an iterative fine tuning, with which we fine-tune the whole network after decomposing each layer, but before decomposing the next layer. Significant reduction in memory and computation cost is achieved compared to state-of-the-art previous work with no more accuracy loss.

Tasks

Reproductions