Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
Deep Learning building blocks: 5 popular torch tensor functions
Hi all, in this short introduction about PyTorch, I decided to explore 5 main functions that are a must in most of Deep Learning models nowadays:
torch.view()
torch.reshape()
torch.permute()
torch.flatten()
torch.cat()
Particularly, I chose them not only because they are famous, but also because some of them can generate some confusion as they behave quite similarly.
import torch
import jovian
Function 1 - torch.view()
This function returns a new tensor with the same data as the original tensor but of a different shape.
tensor1 = torch.tensor([[1, 2], [3, 4.]])
tensor1
tensor([[1., 2.],
[3., 4.]])
Imagine we want to reshape our tensor to a (1, 4) shape