python: 深度学习-误差反向传播法

class Relu:
    def __init__(self):
        self.mask=None
        
    def forword(self,x):
        self.mask=(x<0)     #变量mask是由True/False构成的Numpy数组
        out=x.copy()
        out[self.mask]=0
        
        return out
        
    def backward(self,dout):
        dout[self.mask]=0
        dx=dout
        
        return dx

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

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)

        return dx

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）

    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

import sys, os
sys.path.append(os.pardir)
import numpy as np
from common.layers import *
from common.gradient import numerical_gradient
from collections import OrderedDict

class TwoLayerNet:

    def __init__(self, input_size, hidden_size, output_size,
                 weight_init_std=0.01):
        # 初始化权重
        self.params = {}
        self.params[‘W1‘] = weight_init_std *                             np.random.randn(input_size, hidden_size)
        self.params[‘b1‘] = np.zeros(hidden_size)
        self.params[‘W2‘] = weight_init_std *                             np.random.randn(hidden_size, output_size)
        self.params[‘b2‘] = np.zeros(output_size)

        # 生成层
        self.layers = OrderedDict()   # OrderedDict是有序字典
        self.layers[‘Affine1‘] =             Affine(self.params[‘W1‘], self.params[‘b1‘])
        self.layers[‘Relu1‘] = Relu()
        self.layers[‘Affine2‘] =             Affine(self.params[‘W2‘], self.params[‘b2‘])

        self.lastLayer = SoftmaxWithLoss()

    def predict(self, x):
        for layer in self.layers.values():
            x = layer.forward(x)

        return x

    # x:输入数据, t:监督数据
    def loss(self, x, t):
        y = self.predict(x)
        return self.lastLayer.forward(y, t)

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        if t.ndim != 1 : t = np.argmax(t, axis=1)
        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy

    # x:输入数据, t:监督数据
    def numerical_gradient(self, x, t):
        loss_W = lambda W: self.loss(x, t)

        grads = {}
        grads[‘W1‘] = numerical_gradient(loss_W, self.params[‘W1‘])
        grads[‘b1‘] = numerical_gradient(loss_W, self.params[‘b1‘])
        grads[‘W2‘] = numerical_gradient(loss_W, self.params[‘W2‘])
        grads[‘b2‘] = numerical_gradient(loss_W, self.params[‘b2‘])

        return grads

    def gradient(self, x, t):
        # forward
        self.loss(x, t)

        # backward
        dout = 1
        dout = self.lastLayer.backward(dout)

        layers = list(self.layers.values())
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        # 设定
        grads = {}
        grads[‘W1‘] = self.layers[‘Affine1‘].dW
        grads[‘b1‘] = self.layers[‘Affine1‘].db
        grads[‘W2‘] = self.layers[‘Affine2‘].dW
        grads[‘b2‘] = self.layers[‘Affine2‘].db

        return grads