/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

27 votes261 views6 answers
Create a empty dataframe
Python
0 vote250 views1 answer
Get hwid python
Python
0 vote211 views2 answers
Python del list
Python
1 vote246 views1 answer
Python program to print ASCII characters in lowercase
Python
0 vote287 views1 answer
Django default template location
Python Django
0 vote250 views1 answer
Change orientatin of dict read pandas
Python
7 votes273 views3 answers
Numpy array equal
Python
2 votes261 views1 answer
How to check if how much time is your code taking to run in python
Python
1 vote245 views1 answer
How to set the location on a pygame window
Python
0 vote218 views1 answer
Divide array into equal parts/slices python
Python