bemoredev
(Smetana Moldau)
September 14, 2017, 3:33am
1
Hi, All.
This is my simple GPU code in PyTorch.
How can I change this in CPU code?
filename=r’/Users/dti/Desktop/PyTorch4testAccuracy/hymenoptera_data/test/bees/1.jpg’
img = skimage.io.imread(filename)
x = V(centre_crop(img).unsqueeze(0), volatile=True).cuda()
model = models.dict ’resnet18’
model = torch.nn.DataParallel(model).cuda()
model = torch.load(‘model5.pth’)
logit = model(x)
print(logit)
Thanks in advance .
An example:
use_cuda = torch.cuda.is_available()
if use_cuda:
X_tensor = Variable(torch.from_numpy(x_data_np).cuda()) # Note the conversion for pytorch
else:
X_tensor = Variable(torch.from_numpy(x_data_np)) # Note the conversion for pytorch
1 Like
iacolippo
(Iacopo Poli)
September 14, 2017, 8:47am
3
remove the .cuda()
and the torch.nn.DataParallel
filename=r’/Users/dti/Desktop/PyTorch4testAccuracy/hymenoptera_data/test/bees/1.jpg’
img = skimage.io.imread(filename)
x = V(centre_crop(img).unsqueeze(0), volatile=True)
model = models.dict['resnet18']
model = torch.load('model5.pth')
logit = model(x)
print(logit)
1 Like