Title Here

Subtitle Here

An short introduction about PyTorch and about the chosen functions.

function 1
function 2
function 3
function 4
function 5

# Import torch and other required modules
import torch
import numpy as np

Function 1 - torch.tensor vs torch.as_tensor

torch.tensor always copies data. torch.tensor(data, dtype=None, device=None, requires_grad=False, pin_memory=False) → Tensor
torch.as_tensor uses same memory place

# Example 1
arr = np.array([[1, 2, 3], [4, 5, 6]], dtype="float32")
t = torch.tensor(arr)
t_copy = torch.tensor(t)

# if change data in t it will not reflect to t_copy
t[0,1] = 100
print("t: ", t)
print("t_copy: ", t_copy)

t:  tensor([[  1., 100.,   3.],
        [  4.,   5.,   6.]])
t_copy:  tensor([[1., 2., 3.],
        [4., 5., 6.]])

/srv/conda/envs/notebook/lib/python3.7/site-packages/ipykernel_launcher.py:4: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  after removing the cwd from sys.path.

if change data in t it will not reflect to t_copy