Learn practical skills, build real-world projects, and advance your career
Updated 4 years ago
Pytorch Tensor functions
Here are my five Tensor functions in Pytorch
- torch.as_tensor
- torch.arange
- torch.reshape
- torch.abs
- torch.is_leaf
# Import torch and other required modules
import torch
import numpy as np
Function 1 - torch.as_tensor
In Pytorch the recommended way to build tensors are either using torch.tensor()
and torch.as_tensor()
. So what is the difference. torch.tensor()
always copies the data where as torch.as_tensor()
always tries to avoid copies of the data. This is especially useful if you have a numpy array and want to avoid copying the numpy array into a tensor. Let's see an example
# Example 1
arr = np.array([1, 2, 3])
arr
array([1, 2, 3])
t = torch.tensor(arr)
print(t)
print(t.dtype)
tensor([1, 2, 3])
torch.int64