TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

代碼

# -*- coding: utf-8 -*-
"""
Created on Sat Feb 19 13:19:30 2022

@author: koneko
"""

from matplotlib  import pyplot as plt
import torch 
import math

dtype = torch.float
device = torch.device("cuda:0")

# Create random input and output data
x = torch.linspace(-math.pi, math.pi, 2000, device=device, dtype=dtype)
y = torch.sin(x)

# Randomly initialize weights
a = torch.randn((), device=device, dtype=dtype)
b = torch.randn((), device=device, dtype=dtype)
c = torch.randn((), device=device, dtype=dtype)
d = torch.randn((), device=device, dtype=dtype)

lr = 1e-6

for t in range(2000):
    # Forward pass: compute predicted y
    y_pred = a + b * x + c * x ** 2 + d * x ** 3

    # Compute and print loss
    loss = (y_pred - y).pow(2).sum().item()
    if t % 100 == 99:
        print(t, loss)

    # Backprop to compute gradients of a, b, c, d with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_a = grad_y_pred.sum()
    grad_b = (grad_y_pred * x).sum()
    grad_c = (grad_y_pred * x ** 2).sum()
    grad_d = (grad_y_pred * x ** 3).sum()

    # Update weights using gradient descent
    a -= lr * grad_a
    b -= lr * grad_b
    c -= lr * grad_c
    d -= lr * grad_d


print(f'Result: y = {a.item()} + {b.item()} x + {c.item()} x^2 + {d.item()} x^3')

x = x.numpy()
y_pred = y_pred.numpy()

plt.plot(x,y_pred)

報錯信息

TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

原因

看信息應該是說數據在顯存里plt不能直接調用？所以要先復制到宿主內存里面

解決方法

倒數第二三行修改為：

x = x.cpu().numpy()
y_pred = y_pred.cpu().numpy()