pytorch深度学习实践（刘二大人）课堂代码&作业——梯度下降算法

*学习率是超参数，训练结果没达到要求时大家可以自行调整大小，我这里调成了0.2

一、梯度下降

import numpy as np
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):
        y_pred = forward(x)
        cost += (y_pred - 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)

epoch_list = []
cost_list = []

print('Predict (before training)', 4, forward(4))
for epoch in range(100):
    cost_val = cost(x_data, y_data)
    grad_val = gradient(x_data, y_data)
    w -= 0.2 * grad_val
    print('Epoch:', epoch, 'w=', w, 'loss=', cost_val)
    epoch_list.append(epoch)
    cost_list.append(cost_val)
print('Predict (after training)', 4, forward(4))

plt.plot(epoch_list, cost_list)
plt.grid(True)
plt.xlabel('Epoch')
plt.ylabel('Cost')
plt.show()

二、随机梯度下降

#SGD随机梯度下降,其实应该随机取一个样本来更新权重，但这里直接遍历了每个样本
import numpy as np
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 loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) ** 2

def gradient(x, y):
        return 2 * x * (x * w - y)

epoch_list = []
loss_list = []

print('Predict (before training)', 4, forward(4))
for epoch in range(100):
    for x, y in zip(x_data, y_data):
        grad = gradient(x, y)
        w -= 0.2 * grad
        print("\tgrad: ", x, y, grad)
        l = loss(x, y)
    print("progress:", epoch, "w=", w, "loss=", l)
    epoch_list.append(epoch)
    loss_list.append(l)
print('Predict (after training)', 4, forward(4))

plt.plot(epoch_list, loss_list)
plt.grid(True)
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show()