TypeError: can‘t convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory fi

大家好，又见面了，我是你们的朋友全栈君。如果您正在找激活码,请点击查看最新教程,关注关注公众号 “全栈程序员社区” 获取激活教程,可能之前旧版本教程已经失效.最新Idea2022.1教程亲测有效,一键激活。

Jetbrains全系列IDE稳定放心使用

运行程序如下：

import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
import matplotlib.pyplot as plt


class LinearRegression(nn.Module):
    def __init__(self):
        super(LinearRegression,self).__init__()
        self.linear = nn.Linear(1,1)
    def forward(self, x):
        out = self.linear(x)
        return out
x_train = np.array([[3.3],[4.4],[5.5],[6.710],[6.93],[4.168],[9.779],[6.182],[7.59],[2.167],[7.042],[10.791],[5.313],[7.997],[3.1]],dtype=np.float32)
y_train = np.array([[1.7],[2.76],[2.09],[3.19],[1.694],[1.573],[3.366],[2.596],[2.53],[1.221],[2.827],[3.465],[1.65],[2.904],[1.3]],dtype=np.float32)
x_train = torch.from_numpy(x_train)
y_train = torch.from_numpy(y_train)
num_epochs = 1000
if torch.cuda.is_available():
    print("GPU1")
    model = LinearRegression().cuda()
else:
    print("CPU1")
    model = LinearRegression()

criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(),lr=1e-3)


for epoch in  range(num_epochs):
    if torch.cuda.is_available():
        print('GPU2')
        inputs = Variable(x_train).cuda()
        target = Variable(y_train).cuda()
    else:
        print("CPU2")
        inputs = Variable(x_train)
        target = Variable(y_train)
    # forward
    out = model(inputs)
    loss = criterion(out,target)
    # backward
    optimizer.zero_grad()  # 梯度归零
    loss.backward()   # 反向传播
    optimizer.step()  # 更新参数
    # if (epoch+1) % 20 ==0:
    #     print('Epoch[{}/{}], loss:{:,6f}'.format(epoch+1,num_epochs,loss.data[0]))


model.eval()

predict = model(Variable(x_train.cuda()))  
predict = predict.data.numpy()
plt.plot(x_train.numpy(),y_train.numpy(),'ro',label='Original data')
plt.plot(x_train.numpy(),predict,label='Fitting Line')
plt.show()

这行报错：predict = predict.data.numpy()

TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

意思是:如果想把CUDA tensor格式的数据改成numpy时，需要先将其转换成cpu float-tensor随后再转到numpy格式。 numpy不能读取CUDA tensor 需要将它转化为 CPU tensor
将predict.data.numpy() 改为predict.data.cpu().numpy()即可