CODEWITHSUNDEEP
pythonnumpypytorch
Gulzar
Gulzar

Reputation: 28054

How to convert a pytorch tensor into a numpy array?

How do I convert a torch tensor to numpy?

Upvotes: 27

Views: 79369

Answers (8)

Madiyar
Madiyar

Reputation: 1089

You can use the force=True parameter from torch.Tensor.numpy:

import torch

t = torch.rand(3, 2, device='cuda:0')
print(t.numpy(force=True))

t.numpy(force=True) is a shorthand to:

t.detach().cpu().resolve_conj().resolve_neg().numpy()

The force parameter was introduced in PyTorch 1.13.

Upvotes: 1

KingLiu
KingLiu

Reputation: 305

x = torch.tensor([0.1,0.32], device='cuda:0')

x.detach().cpu().data.numpy()

Upvotes: -1

Gulzar
Gulzar

Reputation: 28054

copied from pytorch doc:

a = torch.ones(5)
print(a)

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

b = a.numpy()
print(b)

[1. 1. 1. 1. 1.]

Following from the below discussion with @John:

In case the tensor is (or can be) on GPU, or in case it (or it can) require grad, one can use

t.detach().cpu().numpy()

I recommend to uglify your code only as much as required.

Upvotes: 44

Eyshika
Eyshika

Reputation: 1109

Another useful way :

a = torch(0.1, device='cuda')

a.cpu().data.numpy()

Answer

array(0.1, dtype=float32)

Upvotes: 4

prosti
prosti

Reputation: 46469

This is a function from fastai core:

def to_np(x):
    "Convert a tensor to a numpy array."
    return apply(lambda o: o.data.cpu().numpy(), x)

Possible using a function from prospective PyTorch library is a nice choice.

If you look inside PyTorch Transformers you will find this code:

preds = logits.detach().cpu().numpy()

So you may ask why the detach() method is needed? It is needed when we would like to detach the tensor from AD computational graph.

Still note that the CPU tensor and numpy array are connected. They share the same storage:

import torch
tensor = torch.zeros(2)
numpy_array = tensor.numpy()
print('Before edit:')
print(tensor)
print(numpy_array)

tensor[0] = 10

print()
print('After edit:')
print('Tensor:', tensor)
print('Numpy array:', numpy_array)

Output:

Before edit:
tensor([0., 0.])
[0. 0.]

After edit:
Tensor: tensor([10.,  0.])
Numpy array: [10.  0.]

The value of the first element is shared by the tensor and the numpy array. Changing it to 10 in the tensor changed it in the numpy array as well.

This is why we need to be careful, since altering the numpy array my alter the CPU tensor as well.

Upvotes: 4

Ashiq Imran
Ashiq Imran

Reputation: 2311

You can try following ways

1. torch.Tensor().numpy()
2. torch.Tensor().cpu().data.numpy()
3. torch.Tensor().cpu().detach().numpy()

Upvotes: 11

Marius Johan
Marius Johan

Reputation: 392

Sometimes if there's "applied" gradient, you'll first have to put .detach() function before the .numpy() function. 

loss = loss_fn(preds, labels)
print(loss.detach().numpy())

Upvotes: 1

Wasi Ahmad
Wasi Ahmad

Reputation: 37761

You may find the following two functions useful.

  1. torch.Tensor.numpy()
  2. torch.from_numpy()

Upvotes: 1

Related Questions