PyTorch torch.arange() method is “used to create a 1-dimensional tensor with a sequence of numbers.” This method is similar to Python’s built-in range() but returns a tensor.
torch.arange(start=0, end, step=1, *, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False)
- start (Number): It is the starting value for the set of points. Default: 0.
- end (Number): It is the ending value for the set of points
- step (Number): It is the gap between each pair of adjacent points. Default: 1.
- out: An output tensor.
- dtype: The desired data type of the tensor. Default is inferred.
- layout: Memory layout of the tensor. The default is the torch.strided.
- device: The desired device for the tensor. Default is the current default device.
- requires_grad: If set to True, the tensor will be created with gradient tracking enabled. The default is False.
Example 1: Creating a Tensor with Numbers from 0 to 4
import torch tensor1 = torch.arange(5) print(tensor1)
tensor([0, 1, 2, 3, 4])
Example 2: Creating a Tensor with Numbers from 2 to 8 in Steps 2
import torch tensor2 = torch.arange(2, 10, 2) print(tensor2)
tensor([2, 4, 6, 8])
Example 3: Creating a Tensor with Numbers from 0 to 1 in Steps of 0.1
import torch tensor3 = torch.arange(0, 1.1, 0.1) print(tensor3)
tensor([0.0000, 0.1000, 0.2000, 0.3000, 0.4000, 0.5000, 0.6000, 0.7000, 0.8000, 0.9000, 1.0000])