/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 vote313 views1 answer
Torch split classes stratified
Python
0 vote333 views1 answer
Random.choices without repetition
Python
39 votes342 views5 answers
Csv to python
Python
0 vote308 views1 answer
Pop function second argument in python
Python
0 vote327 views1 answer
Python select from list by boolean list
Python
0 vote274 views1 answer
Get label text tkinter
Python
3 votes344 views4 answers
Python list group by count
Python
2 votes321 views6 answers
How to setup Turtle python
Python
0 vote300 views1 answer
Find Carmichael number sage
Python
0 vote310 views1 answer
Float number field django models
Python