/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 vote158 views1 answer
How to instal django cities
Python Django
0 vote139 views1 answer
Circular heatmap python
Python
0 vote126 views1 answer
Check for the negative integers and float
Python
0 vote135 views1 answer
Write dict to json file with special characters
Python
2 votes130 views2 answers
Python find smallest value in list
Python
0 vote144 views2 answers
How to format integer to two digit in python
Python
7 votes128 views1 answer
How to set the screen brightness using python
Python
0 vote149 views1 answer
Raspberry pi run python script on boot
Python
0 vote133 views1 answer
How to take long input in python
Python
0 vote148 views1 answer
Como calcular el rango en python
Python