梯度下降(GD)
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 = [i for i in range(1, 101)]
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 -= 0.01 * grad_val
cost_list.append(cost_val)
print('Epoch:', epoch, 'w=', w, 'loss=', cost_val)
print('Predict (after training)', 4, forward(4))
plt.plot(epoch_list, cost_list)
plt.ylabel('cost')
plt.xlabel('epoch')
plt.show()
随机梯度下降(SGD)
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 = [i for i in range(1, 101)]
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
print("\tgrad: ", x, y, grad)
l = loss(x, y)
loss_list.append(l)
print("progress:", epoch, "w=", w, "loss=", l)
print('Predict (after training)', 4, forward(4))
plt.plot(epoch_list, loss_list)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.show()
用GD和SGD对比
GD适用于并行计算,计算快;SGD计算慢,但是效果好
所以深度学习的实际使用中常常折中,也就是使用小批量梯度下降
这里的矛盾其实就是batch_size取舍的问题,这在深度学习中是一个难点