10 juill. 2018 - Wide Compression: Tensor Ring Nets (CVPR 2018)
Description:
Three-component decomposition
Tensor Ring Nets (TRN), in
which layers of a deep neural network are compressed using tensor ring factorization.
结果:
TR-Nets approach is able to compress LeNet-5 by 11× without losing accuracy, and can compress the state-of-the-art Wide ResNet by 243× with only 2.3% degradation in Cifar10 image classification
Ajouté au bande de temps:
Date:
10 juill. 2018
Maintenaint
~ Il y a 5 ans et 10 mois