Tensor Decomposition: Fast CNN in your pocket

Kerem Turgutlu
Jul 5, 2018 · 6 min read
import torch
import tensorly as tl # using pytorch >= 0.4 backend
A = torch.randint(0, 100, (3,3,3))
B = torch.randint(0, 100, (3,3,3))
tl.tenalg.inner(A, B) == torch.sum((A*B))
Minimizing Frobenius Norm

Kerem Turgutlu

Written by

Machine Learning Engineer

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade