神经网络有合适的权重(W)和偏置(b),调整权重和偏置以便拟合训练数据的过程称之为学习。分为下面四个步骤:
步骤1:从训练集中随机选择一部分数据
步骤2:计算损失函数关于各个权重参数(W)的梯度
步骤3:将权重沿梯度方向进行微小的更新
步骤4:重复步骤1、步骤2、步骤3
#乘法层
class MulLayer:
def __init__(self):
self.x = None
self.y = None
def forward(self, x, y):
self.x = x
self.y = y
out = x * y
return out
def backward(self, dout):
dx = dout * self.y
dy = dout * self.x
return dx, dy
#加法层
class AddLayer:
def __init__(self):
pass
def forward(self, x, y):
out = x + y
return out
def backward(self, dout):
dx = dout * 1
dy = dout * 1
return dx, dy
仅使用加法层和乘法层写一个例子,如下:
#应用
apple = 100
apple_num = 2
orange = 150
orange_num = 3
tax = 1.1
#layer
mul_apple_layer = MulLayer()
mul_orange_layer = MulLayer()
add_apple_orange_layer = AddLayer()
mul_tax_layer = MulLayer()
#forward
apple_price = mul_apple_layer.forward(apple, apple_num,)#(1)
orange_price = mul_orange_layer.forward(orange, orange_num)#(2)
all_price = add_apple_orange_layer.forward(apple_price, orange_price)#(3)
price = mul_tax_layer.forward(all_price,tax)#(4)
#backward
dprice = 1
dall_price, dtax = mul_tax_layer.backward(dprice)#(4)
dapple_price, dorange_price = add_apple_orange_layer.backward(dall_price)#(3)
dorange, dorange_num = mul_orange_layer.backward(dorange_price)#(2)
dapple, dapple_num = mul_apple_layer.backward(dapple_price)#(1)
print(price)#715
print(dapple_num, dapple, dorange, dorange_num, dtax)#110, 2.2, 3.3, 165, 650"""
激活函数
#激活函数Relu层
import numpy as np
class Relu:
def __init__(self):
self.mask = None
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
def backward(self, dout):
dout[self.mask] = 0
dx = dout
return dx
激活函数ReLu层应用
#激活函数ReLu层应用
x = np.array([[1.0, -0.5], [-2.0, 3.0]])
print(x)
mask = (x <= 0)#mask在一定范围内的数值转换为true,其它范围为false
print(mask)
#激活函数sigmoid层
import numpy as np
class Sigmoid:
def __init__(self):
self.out = None
def forward(self, x):
out = 1 / (1 + np.exp(-x))
self.out = out
return out
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
#批归一化Affine层
import numpy as np
class Affine:
def __init__(self, W, b):
self.W = W
self.b = b
self.x = None
self.dw = None
self.db = None
def forward(self, x):
self.x = x
out = np.dot(x, self.W) + self.b
return out
def backward(self, dout):
dx = np.dot(dout, self.W.T)
self.dW = np.dot(self.x.T, dout)
self.db = np.sum(dout, axis=0)#axis=0表示是一个一维数据
return dx
Softmax-with-Loss层实现代码:
Cross Entropy Error:交叉熵误差
#Softmax-with-Loss层的实现
import numpy as np
class SoftmaxWithLoss:
def __init__(self):
self.loss = None #损失
self.y = None #softmax的输出
self.t = None #监督数据(one—hot vector)
#################定义一个softmax函数###########
def softmax(self, a):
c = np.max(a)
exp_a = np.exp(a - c)
sum_exp_a = np.sum(exp_a)
y = exp_a / sum_exp_a
return y
###############定义一个交叉熵误差函数###############
def cross_entropy_error(self, y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
batch_size = y.shape[0]
return np.sum(np.log(y[np.arange(batch_size),t] + 1e-7)) / batch_size
def forward(self, x, t):
self.t = t
self.y = softmax(x)
self.loss = cross_entropy_error(self.y, self.t)
return self.loss
def backward(self, dout=1):
batch_size = self.t.shape[0]
dx = (self.y - self.t) / batch_size
return dx