import matplotlib.pyplot as plt
# prepare the training set
x_data = [1.0, 2.0, 3.0] \\x,y两个数据集
y_data = [2.0, 4.0, 6.0]
# initial guess of weight
w = 1.0 \\设定一个初始权重猜测值
# define the model linear model y = w*x
def forward(x):
return x*w
#define the cost function MSE
def cost(xs, ys):
cost = 0
for x, y in zip(xs,ys):
y_pred = forward(x) \\算y-hat
cost += (y_pred - y)**2 \\(y-hat - y)平方
return cost / len(xs) \\求均值
# define the gradient function gd
def gradient(xs,ys): \\求梯度 贪心算法
grad = 0
for x, y in zip(xs,ys):
grad += 2*x*(x*w - y) \\梯度求和
return grad / len(xs) \\取平均值
epoch_list = []
cost_list = []
print('predict (before training)', 4, forward(4))
for epoch in range(100): \\ 一个epoch , 表示: 所有的数据送入网络中, 完成了一次前向计算 + 反向传播的过程。
cost_val = cost(x_data, y_data)
grad_val = gradient(x_data, y_data)
w-= 0.01 * grad_val \\更新权重
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.ylabel('cost')
plt.xlabel('epoch')
plt.show()
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
# calculate loss function
def loss(x, y):
y_pred = forward(x)
return (y_pred - y)**2
# define the gradient function sgd
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 = w - 0.01*grad # update weight by every grad of sample of training set
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.ylabel('loss')
plt.xlabel('epoch')
plt.show()
总结: