报错

device:GPU CPU

？1：RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

sol1：用CUDA训练的模型，测试时要指定设备为CUDA

device =  torch.device("cuda" if torch.cuda.is_available() else "cpu")
# img = transform(img)后
img = img.to(device)
# or 
with torch.no_grad():
    output = model(img.to(device))

sol2：调用训练好的模型时，使用CPU

model = torch.load("pretrained_demo_10.pth",map_location=torch.device("cpu"))