Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

[andriilitvynchuk]

Hi there! Thanks for your great repo, but i faced with some difficulties while trying to inference on device ('cuda:0'). My code:
device = torch.device('cuda:0')
tfms = transforms.Compose([transforms.Resize(224), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),])
img = tfms(Image.open('img.png')).unsqueeze(0)
img.to(device)
model.to(device)
model.eval()
with torch.no_grad(): outputs = model(img)
And thrown error:
RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

[cardoso-neto]

I'm pretty sure Tensor.to(device) is not an in-place operation and you're discarding the cuda tensor using it as such.

[andriilitvynchuk]

So it's impossibile to run on GPU or i missed something?

[cardoso-neto]

Are you serious?
Your tensor's the problem.

Did you even try img = img.to(device) as I've told you?

[andriilitvynchuk]

Sorry, i didn't understand your answer. Thank you very much,,

[HoiM]

The problem is that you didn't convert the type of the input data correctly. You can try something like this:
batch = torch.from_numpy(image_batch).type(torch.cuda.FloatTensor)
batch_features = model.extract_features(batch)

[P-DX]

hi, do you solve this problem?
could you share the solution with me?

[andriilitvynchuk]

I just wrote

img = img.to(device)

As wrote before, sending tensor to device is not inplace operation and it returns new tensor.