Both .flatten() and .view(-1) flatten a tensor in PyTorch. What’s the difference? Does .flatten() copy the data of the tensor? Is .view(-1) faster? Is there any situation that .flatten() doesn’t work? Answer

What is the difference between .flatten() and .view(-1) in PyTorch?

iacob

edited 15 Mar, 2021

ipid

asked 27 Jul, 2019

Both .flatten() and .view(-1) flatten a tensor in PyTorch. What’s the difference?