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

Assignment 1 of Deep Learning with PyTorch: Zero to GANs

pyTorch Tensor

Here is my five interesting functions that related to PyTorch tensors.

  • torch.arange()
  • torch.Tensor.view()
  • torch.reshape()
  • torch.det()
  • torch.matmul()
# Import torch and other required modules
import torch

Function 1 - torch.arange()

torch.arange(start=0, end, step=1, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor

This function return the 1-D Tensor. Typically this tensor contain linear squence of numbers when we define the start, end and step that we need to arrange. The default values for start and step are 0 and 1.

# Example 1 - working 
torch.arange(10)
tensor([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])

Above example we pass 10 a as argument. So the function will like arange(start=0,end=10, step=1). Therefore it return the 1-D tensor that has a linear sequnce of numbers in between 0 to 9. The start number is included and the end number is excluded.