How to convert a PyTorch tensor with gradient to a numpy array?

To convert a Torch tensor with gradient to a Numpy array, first we have to detach the tensor from the current computing graph. To do it, we use the Tensor.detach() operation. This operation detaches the tensor from the current computational graph. Now we cannot compute the gradient with respect to this tensor. After the detach() operation, we use the .numpy() method to convert it to a Numpy array.

If a tensor with requires_grad=True is defined on GPU, then to convert this tensor to a Numpy array, we have to perform one more step. First we have to move the tensor to CPU, then we perform Tensor.detach() operation and finally use .numpy() method to convert it to a Numpy array.

Steps

• Import the required library. The required library is torch.

• Create a tensor with gradient on CPU. If a tensor with gradient is already defined on the GPU, then we have to move it to the CPU.

• Detach the tensor from the current computational graph. You can use .detach() to perform this operation. After the detach() operation, the tensor is without gradient.

• Next, convert the tensor without gradient to a Numpy array. You can use .numpy() to convert it to a Numpy array.

• Print the Numpy array.

Example 1

# import torch library
import torch

# define a tensor with requires gradient true
x = torch.tensor([1.,2.], requires_grad = True)
print("x:", x)

# x.numpy()--> error
x = x.detach().numpy()
print("x:", x)
print("type of x:", type(x))

Output

x: tensor([1., 2.], requires_grad=True)
x: [1. 2.]
type of x: <class 'numpy.ndarray'>

Example 2

import torch

# define device
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# define tensors with gradients on gpu
x = torch.tensor([1.,2.], requires_grad = True, device = device)
y = torch.tensor([1.,2., 3.], requires_grad = True, device = device)

print("x:", x)
print("y:", y)

# first move the tensor from gpu to cpu
x = x.to('cpu') # or x = x.cpu()

# then detach the requires_grad
x = x.detach()

# and then convert to numpy
x = x.numpy()
print("x:",x)
print("type of x:", type(x))

y = y.cpu().detach().numpy()
print("y:", y)
print("type of y:", type(y))

Output 1 − If GPU is not available

x: tensor([1., 2.], requires_grad=True)
y: tensor([1., 2., 3.], requires_grad=True)
x: [1. 2.]
type of x: <class 'numpy.ndarray'>
y: [1. 2. 3.]
type of y: <class 'numpy.ndarray'>

Output 2 − If GPU is available

x: tensor([1., 2.], device='cuda:0', requires_grad=True)
y: tensor([1., 2., 3.], device='cuda:0', requires_grad=True)
x: [1. 2.]
type of x: <class 'numpy.ndarray'>
y: [1. 2. 3.]
type of y: <class 'numpy.ndarray'>

Shahid Akhtar Khan

Published on 06-Jan-2022 09:34:56

• Related Questions & Answers
• How to convert a NumPy ndarray to a PyTorch Tensor and vice versa?
• How to convert an image to a PyTorch Tensor?
• How to resize a tensor in PyTorch?
• How to normalize a tensor in PyTorch?
• How to narrow down a tensor in PyTorch?
• How to squeeze and unsqueeze a tensor in PyTorch?
• How to access the metadata of a tensor in PyTorch?
• How to sort the elements of a tensor in PyTorch?
• How to compute the histogram of a tensor in PyTorch?
• How to find the transpose of a tensor in PyTorch?
• How to check if an object is a PyTorch Tensor?
• How to pad the input tensor boundaries with a constant value in PyTorch?
• How to get the data type of a tensor in PyTorch?
• PyTorch – How to compute the error function of a tensor?
• How to convert a Torch Tensor to PIL image?