Learn practical skills, build real-world projects, and advance your career
Updated 4 years ago
Assignment 1 - All About torch.Tensor
PyTorch Library allows users to work efficiently with tensors.
I chose to look into and experiment with the below 5 functions of PyTorch as they allowed me clearly visualize and manipulate data among tensors.
even though I had no prior experience with Tensors.
- select()
- index_fill_()
- put_()
- repeat()
- index_add_()
# Import torch and other required modules
import torch
Function 1 - tensor.select
Slices the tensor along the dimension at the given index ; and returns a new tensor.
select(dim, index)
# Example 1 - working (change this)
x = torch.tensor([[1, 2, 3, 4, 5],
[2, 4, 6, 8, 10]])
y = x.select(1, 3)
print(y)
tensor([4, 8])
Explanation about example 1:
Here, the select() function divides the tensor x in the dimension as the column of the tensor and at index 3. Hence, this returns us a new 1 x 2 tensor.