/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

10 votes356 views1 answer
Django new static files directory
Python Django
0 vote335 views1 answer
Remove a columns in pandas
Python
11 votes293 views3 answers
Python random choice int
Python
-1 vote304 views1 answer
Traduce query model
Python
7 votes310 views1 answer
Coinflip
Python
4 votes367 views1 answer
Python django shell command
Python Django
0 vote349 views2 answers
Flask abort
Python Flask
0 vote359 views1 answer
Draw box with mouse on image in canvas tkinter
Python
0 vote311 views1 answer
Get unique words from pandas dataframe
Python
0 vote314 views1 answer
Take the fibonnocci numbers into a list in python
Python