Learn practical skills, build real-world projects, and advance your career

Diving into Tensor functions

Here we investigate 5 tensor functions

An short introduction about PyTorch and about the chosen functions.

  • index_fill_(dim, index, val)
  • expand(*sizes)
  • torch.numel(input)
  • torch.as_tensor(data, dtype=None, device=None)
  • torch.reshape(input, shape)
# Import torch and other required modules
import torch
import numpy

Function 1 - index_fill_(dim, index, val) -> Tensor

Parameters

  • dim (int) – dimension along which to index

  • index (LongTensor) – indices of self tensor to fill in

  • val (float) – the value to fill with

This function used to fill values in given index in PyTorch tensor

# Example 1 - Fill the values in vertically
x = torch.tensor([[2,3,4],[6,7,8]],dtype = torch.float)
index = torch.tensor([1])
x.index_fill_(1,index, 0) 
x
tensor([[2., 0., 4.],
        [6., 0., 8.]])

in here we add 0 for 1st column