23 févr. 2015 - Speeding-up convolutional neural networks using fine-tuned cp-decomposition (ICLR 2014)
Description:
Four-component Decomposition结果：
For the standard ImageNet architecture (AlexNet), the approach speeds up the second convolution layer by a factor of 4x at the cost of 1% increase of the overall top-5 classification error.
Ajouté au bande de temps:
Date:
23 févr. 2015
Maintenaint
~ Il y a 9 ans et 2 mois
