Pytorch.org/tutorials Tensor

Initializing a tensor

torch.tensor

torch.from_numpy

Input tensor

torch.ones_like() retain the shape

torch.rand_like() retain the shape

Input the shape

torch.rand()

torch.ones()

torch.zeros()

tensor.attribute

tensor.shape

tensor.dtype

tensor.device

Standard numpy-like indexing and slicing

tensor = torch.ones(4, 4)
print('First row: ', tensor[0])
print('First column: ', tensor[:, 0])
print('Last column:', tensor[..., -1])
tensor[:,1] = 0
print(tensor)

Joining tensors

torch.cat

tensor([[1., 0., 1., 1.],
        [1., 0., 1., 1.],
        [1., 0., 1., 1.],
        [1., 0., 1., 1.]])

t1 = torch.cat([tensor, tensor, tensor], dim=1)
print(t1)

tensor([[1., 0., 1., 1., 1., 0., 1., 1., 1., 0., 1., 1.],
        [1., 0., 1., 1., 1., 0., 1., 1., 1., 0., 1., 1.],
        [1., 0., 1., 1., 1., 0., 1., 1., 1., 0., 1., 1.],
        [1., 0., 1., 1., 1., 0., 1., 1., 1., 0., 1., 1.]])

Arithmetic Operations

matmul @

mul *

sum +

Single-element tensors If you have a one-element tensor, for example by aggregating all values of a tensor into one value, you can convert it to a Python numerical value using item():

agg = tensor.sum()
agg_item = agg.item()
print(agg_item, type(agg_item))

torch.item()

Out:

12.0 <class 'float'>

In-place operations Operations that store the result into the operand are called in-place. They are denoted by a _ suffix. For example: x.copy_(y), x.t_(), will change x.

print(tensor, "\n")
tensor.add_(5)
print(tensor)

tensor -> numpy

t.numpy()