pytorch 在向后（）中崩溃并冻结屏幕，你能帮帮我吗？

Question

import torch

def forward(x):
    return x * w

def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) ** 2

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = torch.Tensor([1.0])
w.requires_grad = True

print("predict (before training)", 4, forward(4).item())

for epoch in range(100):
    for x, y in zip(x_data, y_data):
        l = loss(x, y)
        l.backward()
        print('\tgrad:', x, y, w.grad.item())
        w.data = w.data - 0.01 * w.grad.data
        w.grad.data.zero_()
        print("progress:", epoch, l.item())
print("predict (after training)", 4, forward(4).item())

Linux 发行版是 Ubuntu 18.04

GPU：GeForce RTX 2080 SUPER

GPU 驱动程序：NVIDIA UNIX x86_64 内核模块 450.80.02

CUDA：Cuda 编译工具，11.0 版，V11.0.194

cudNN：8.0.3

pytorch：1.7.0，py3.6_cuda11.0.221_cudnn8.0.3_0

蟒蛇：3.6

代码很简单，但运行时会冻结整个计算机

屏幕、键盘、鼠标，完全没有反应

Answer 1

重新安装Nvidia驱动即可解决问题