/Python/RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument

RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument

# 第二个类型是 torch.cuda.FloatTensor，这意味着它是已经移到 GPU 的张量。
# 它想获得类型为 torch.FloatTensor 的张量，但是没有 .cuda，因此该张量应该在 CPU 上。
# PyTorch 只能对位于相同设备上的张量进行运算，因此必须同时位于 CPU 或 GPU 上。如果你要在 GPU 
# 上运行网络，一定要使用 .to(device) 将模型和所有必要张量移到 GPU 上，其中 device 为 "cuda" 或 "cpu"。

device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = model.to(device) # the same model.cuda()

for images, labels in trainloader:
	images, labels = images.to(device), labels.to(device)

Similar codes

0 vote191 views1 answer
Pythagorean theorem calc: find c, a=n
Python
2 votes197 views1 answer
Matplotlib multiple plots with different size
Python
9 votes207 views2 answers
TypeError: method() takes 1 positional argument but 2 were given
Python
0 vote183 views1 answer
''' python '''
Python
0 vote158 views0 answer
Python
1 vote204 views1 answer
Download from radio javan python
Python
0 vote191 views1 answer
Numpy evenly spaced numbers
Python
0 vote187 views1 answer
Pandas split groupby
Python
12 votes217 views4 answers
Get index of all element in list python
Python
0 vote205 views1 answer
Django filter values with e and operator
Python