[人工智能]CNN的实现（附代码）

前言

前文已经单独实现了卷积层和池化层，现在来组合这些层，搭建进行手写数字识别的CNN。
这个简单的CNN网络构成如下。

网络的构成是“Convolution - ReLU - Pooling -Affine - ReLU - Affine - Softmax”，我们将它实现为名为SimpleConvNet的类。

该网络的参数
? input_dim―输入数据的维度：（通道，高，长）
? conv_param―卷积层的超参数（字典）。
字典的关键字如下：
filter_num―滤波器的数量
filter_size―滤波器的大小
stride―步幅
pad―填充
? hidden_size―隐藏层（全连接）的神经元数量
? output_size―输出层（全连接）的神经元数量
? weitght_int_std―初始化时权重的标准差

卷积层的超参数通过名为conv_param的字典传入。我们设想它会
像{‘filter_num’:30,‘filter_size’:5, ‘pad’:0, ‘stride’:1}。
这个CNN网络的初始化分为三个部分。

第一部分：取出初始化传入卷积层的超参数，并计算卷积层的输出大小

class SimpleConvNet:
	def __init__(self, input_dim=(1, 28, 28),
						conv_param={'filter_num':30, 'filter_size':5,'pad':0, 'stride':1},
						hidden_size=100, output_size=10, weight_init_std=0.01):
		filter_num = conv_param['filter_num']
		filter_size = conv_param['filter_size']
		filter_pad = conv_param['pad']
		filter_stride = conv_param['stride']
		input_size = input_dim[1]
		conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
		pool_output_size = int(filter_num * (conv_output_size/2) *(conv_output_size/2))

第二部分：权重参数的初始化，包括第一层卷积层和两个全连接层的权重和偏置。分别为W1、b1、w2、b2、w3、b3

# 初始化权重
self.params = {}
self.params['W1'] = weight_init_std * np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
self.params['b1'] = np.zeros(filter_num)
self.params['W2'] = weight_init_std * np.random.randn(pool_output_size, hidden_size)
self.params['b2'] = np.zeros(hidden_size)
self.params['W3'] = weight_init_std * np.random.randn(hidden_size, output_size)
self.params['b3'] = np.zeros(output_size)

第三步：生成对应的层，向有序字典（OrderedDict）的layers中添加层。只有最后的SoftmaxWithLoss层被添加到别的变量lastLayer

# 生成层
self.layers = OrderedDict()
self.layers['Conv1'] = Convolution(self.params['W1'], self.params['b1'],conv_param['stride'], conv_param['pad'])
self.layers['Relu1'] = Relu()
self.layers['Pool1'] = Pooling(pool_h=2, pool_w=2, stride=2)
self.layers['Affine1'] = Affine(self.params['W2'], self.params['b2'])
self.layers['Relu2'] = Relu()
self.layers['Affine2'] = Affine(self.params['W3'], self.params['b3'])

self.last_layer = SoftmaxWithLoss()

以上就是SimpleConvNet的初始化中进行的处理。每一层的单独的具体实现已经在前面文中提到，为构建一个简单的CNN网络，每一层各司其职。

像这样进行初始化后，进行推理的predict方法和求损失函数的loss方法调用如下。

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

        return x

    def loss(self, x, t):
        """求损失函数
        参数x是输入数据、t是教师标签
        """
        y = self.predict(x)
        return self.last_layer.forward(y, t)

predict方法从头开始依次调用已添加的层，并将结果传递给下一层。

接下来是基于误差反向传播求梯度

def gradient(self, x, t):
        """求梯度（误差反向传播法）
        Parameters
        ----------
        x : 输入数据
        t : 教师标签
        Returns
        -------
        具有各层的梯度的字典变量
            grads['W1']、grads['W2']、...是各层的权重
            grads['b1']、grads['b2']、...是各层的偏置
        """
        # forward
        self.loss(x, t)

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

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

        # 设定
        grads = {}
        grads['W1'], grads['b1'] = self.layers['Conv1'].dW, self.layers['Conv1'].db
        grads['W2'], grads['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
        grads['W3'], grads['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].db

        return grads

因为每一层的误差正向传播和反向传播已经在各层实现，也就是forward（）和backward（）方法，只需要依次调用每一层的方法即可，最后将每一层中各个权重参数的梯度保存到grads字典中。

simple_convnet类如下

import sys, os
sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import pickle
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient

class SimpleConvNet:
    """简单的ConvNet

    conv - relu - pool - affine - relu - affine - softmax
    
    Parameters
    ----------
    input_size : 输入大小（MNIST的情况下为784）
    hidden_size_list : 隐藏层的神经元数量的列表（e.g. [100, 100, 100]）
    output_size : 输出大小（MNIST的情况下为10）
    activation : 'relu' or 'sigmoid'
    weight_init_std : 指定权重的标准差（e.g. 0.01）
        指定'relu'或'he'的情况下设定“He的初始值”
        指定'sigmoid'或'xavier'的情况下设定“Xavier的初始值”
    """
    def __init__(self, input_dim=(1, 28, 28), 
                 conv_param={'filter_num':30, 'filter_size':5, 'pad':0, 'stride':1},
                 hidden_size=100, output_size=10, weight_init_std=0.01):
        filter_num = conv_param['filter_num']
        filter_size = conv_param['filter_size']
        filter_pad = conv_param['pad']
        filter_stride = conv_param['stride']
        input_size = input_dim[1]
        conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
        pool_output_size = int(filter_num * (conv_output_size/2) * (conv_output_size/2))

        # 初始化权重
        self.params = {}
        self.params['W1'] = weight_init_std * \
                            np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
        self.params['b1'] = np.zeros(filter_num)
        self.params['W2'] = weight_init_std * \
                            np.random.randn(pool_output_size, hidden_size)
        self.params['b2'] = np.zeros(hidden_size)
        self.params['W3'] = weight_init_std * \
                            np.random.randn(hidden_size, output_size)
        self.params['b3'] = np.zeros(output_size)

        # 生成层
        self.layers = OrderedDict()
        self.layers['Conv1'] = Convolution(self.params['W1'], self.params['b1'],
                                           conv_param['stride'], conv_param['pad'])
        self.layers['Relu1'] = Relu()
        self.layers['Pool1'] = Pooling(pool_h=2, pool_w=2, stride=2)
        self.layers['Affine1'] = Affine(self.params['W2'], self.params['b2'])
        self.layers['Relu2'] = Relu()
        self.layers['Affine2'] = Affine(self.params['W3'], self.params['b3'])

        self.last_layer = SoftmaxWithLoss()

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

        return x

    def loss(self, x, t):
        """求损失函数
        参数x是输入数据、t是教师标签
        """
        y = self.predict(x)
        return self.last_layer.forward(y, t)

    def accuracy(self, x, t, batch_size=100):
        if t.ndim != 1 : t = np.argmax(t, axis=1)
        
        acc = 0.0
        
        for i in range(int(x.shape[0] / batch_size)):
            tx = x[i*batch_size:(i+1)*batch_size]
            tt = t[i*batch_size:(i+1)*batch_size]
            y = self.predict(tx)
            y = np.argmax(y, axis=1)
            acc += np.sum(y == tt) 
        
        return acc / x.shape[0]

    def numerical_gradient(self, x, t):
        """求梯度（数值微分）

        Parameters
        ----------
        x : 输入数据
        t : 教师标签

        Returns
        -------
        具有各层的梯度的字典变量
            grads['W1']、grads['W2']、...是各层的权重
            grads['b1']、grads['b2']、...是各层的偏置
        """
        loss_w = lambda w: self.loss(x, t)

        grads = {}
        for idx in (1, 2, 3):
            grads['W' + str(idx)] = numerical_gradient(loss_w, self.params['W' + str(idx)])
            grads['b' + str(idx)] = numerical_gradient(loss_w, self.params['b' + str(idx)])

        return grads

    def gradient(self, x, t):
        """求梯度（误差反向传播法）

        Parameters
        ----------
        x : 输入数据
        t : 教师标签

        Returns
        -------
        具有各层的梯度的字典变量
            grads['W1']、grads['W2']、...是各层的权重
            grads['b1']、grads['b2']、...是各层的偏置
        """
        # forward
        self.loss(x, t)

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

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

        # 设定
        grads = {}
        grads['W1'], grads['b1'] = self.layers['Conv1'].dW, self.layers['Conv1'].db
        grads['W2'], grads['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
        grads['W3'], grads['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].db

        return grads
        
    def save_params(self, file_name="params.pkl"):
        params = {}
        for key, val in self.params.items():
            params[key] = val
        with open(file_name, 'wb') as f:
            pickle.dump(params, f)

    def load_params(self, file_name="params.pkl"):
        with open(file_name, 'rb') as f:
            params = pickle.load(f)
        for key, val in params.items():
            self.params[key] = val

        for i, key in enumerate(['Conv1', 'Affine1', 'Affine2']):
            self.layers[key].W = self.params['W' + str(i+1)]
            self.layers[key].b = self.params['b' + str(i+1)]

参考

《深度学习入门：基于Python的理论与实现 》斋藤康毅