How do I slice tensors in PyTorch?

How do I slice tensors in PyTorch?

You can slice tensors in PyTorch using the indexing syntax. For example, if you have a tensor x, you can slice it like this: x[start:end].

Can you give me an example with a 2D tensor?

Sure! If you have a 2D tensor x = torch.tensor([[1, 2, 3], [4, 5, 6]]), you can slice it like x[0, 1:3] to get the elements from the first row, columns 1 to 2.

What if I want to slice all rows but only specific columns?

You can use the colon : operator for all rows. For example, x[:, 1:3] will give you all rows but only columns 1 and 2.

Is there a way to slice with a step size?

Yes! You can specify a step size in the slice. For example, x[::2] will select every second row from the tensor.