Python - AttributeError: 'numpy.ndarray' object has no attribute 'to'

Question

I now have the updated code as follows:

    # Hyperparameters
random_seed = 123
learning_rate = 0.01
num_epochs = 10
batch_size = 128

device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")

for epoch in range(num_epochs): model = resnet34.train() for batch_idx, (features, targets) in enumerate(train_generator):

    features = features.to(device)
    targets = targets.to(device)
        
    ### FORWARD AND BACK PROP
    logits = model(features)
    cost = torch.nn.functional.cross_entropy(logits, targets)
    optimizer.zero_grad()
    
    cost.backward()
    
    ### UPDATE MODEL PARAMETERS
    optimizer.step()
    
    ### LOGGING
    if not batch_idx % 50:
        print ('Epoch: %03d/%03d | Batch %03d/%03d | Cost: %.4f' 
               %(epoch+1, num_epochs, batch_idx, 
                 len(datagen)//batch_size, cost))

model = model.eval() # eval mode to prevent upd. batchnorm params during inference
with torch.set_grad_enabled(False): # save memory during inference
    print('Epoch: %03d/%03d training accuracy: %.2f%%' % (
          epoch+1, num_epochs, 
          compute_accuracy(model, train_generator)))

When having only one image, the code runs fine. But, when I add another image or more, I get the following:

features = features.to(device)
targets = targets.to(device)
AttributeError: 'numpy.ndarray' object has no attribute 'to'

Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. — Community
– Community Bot, Commented Jun 9, 2022 at 15:18
obviously it's a numpy array, not a pytorch tensor, but you think it's a pytorch tensor, because you call .to(device) on it, which is not possible with numpy arrays, because they aren't pytorch tensors. I hope that was clear. — Christoph Rackwitz
– Christoph Rackwitz, Commented Jun 9, 2022 at 20:39

dx2-66 · Accepted Answer · 2022-06-10 07:57:41Z

7

It would be nice to see your train_generator code for clarity, but it does not seem to be a torch DataLoader. In this case, you should probably convert your arrays to tensors manually. There are several ways to do so:

torch.from_numpy(numpy_array) - for numpy arrays;
torch.as_tensor(list) - for common lists and tuples;
torch.tensor(array) should also work but the above ways will avoid copying the data when possible.

answered Jun 10, 2022 at 7:57

dx2-66

2,9352 gold badges9 silver badges19 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Python - AttributeError: 'numpy.ndarray' object has no attribute 'to'

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related