刘老师《PyTorch深度学习实践》完结合集（三）梯度下降算法代码

原视频链接：《PyTorch深度学习实践》完结合集_哔哩哔哩_bilibili

import matplotlib.pyplot as plt

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

w = 1.0
def forward(x):
    return x * w

def cost(xs, ys):
    cost = 0
    for x, y in zip(xs, ys):
        cost += (forward(x) - y) ** 2
    return cost / len(xs)

def gradient(xs, ys):
    grad = 0
    for x, y in zip(xs, ys):
        grad += 2 * x * (x * w - y)
    return grad / len(xs)

print('Predict (Before training)', 4, forward(4))
cost_list = []
for epoch in range(50):
    cost_val = cost(x_data, y_data)
    grad_val = gradient(x_data, y_data)
    w -= round(0.01 * grad_val, 5)
    cost_list.append(cost_val)
    print('Epoch:', epoch, 'w=', w, 'loss', cost_val)
print('Predict (after training)', 4, forward(4))

# 将训练过程产生的数据保存到文件中，若不想保存可省略这部分
outfile = open('dataofGradient.txt', "w")
for i in range(len(cost_list)):
    outfile.write(str(round(cost_list[i], 5)) + " ")
outfile.close()

# 绘制训练过程的图像
plt.plot([x for x in range(50)],cost_list)
plt.ylabel('cost')
plt.xlabel('epoch')
plt.show()

生成的图像如下：