深度学习笔记：深度学习CNN python程序实现

加深网络

深度学习相对于一般的神经网络区别就在于使用多层隐藏层。在该例中我们构造一个基于CNN的深度学习网络，其训练完成后对于mnist数据集失败准确率可以超过99%

该网络隐藏层结构：
卷积层—ReLU—卷积层—ReLU—池化层—卷积层—ReLU—卷积层—ReLU—池化层—卷积层—ReLU—卷积层—ReLU—池化层—affine—ReLU—dropout—affine—dropout—softmax

先放上完整代码：

# coding: utf-8
import sys, os
sys.path.append("D:\AI learning source code")  # 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 *


class DeepConvNet:
    """识别率为99%以上的高精度的ConvNet

    网络结构如下所示
        conv - relu - conv- relu - pool -
        conv - relu - conv- relu - pool -
        conv - relu - conv- relu - pool -
        affine - relu - dropout - affine - dropout - softmax
    """
    def __init__(self, input_dim=(1, 28, 28),
                 conv_param_1 = {
   'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_2 = {
   'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_3 = {
   'filter_num':32, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_4 = {
   'filter_num':32, 'filter_size':3, 'pad':2, 'stride':1},
                 conv_param_5 = {
   'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_6 = {
   'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
                 hidden_size=50, output_size=10):
        # 初始化权重===========
        # 各层的神经元平均与前一层的几个神经元有连接（TODO:自动计算）
        pre_node_nums = np.array([1*3*3, 16*3*3, 16*3*3, 32*3*3, 32*3*3, 64*3*3, 64*4*4, hidden_size])
        wight_init_scales = np.sqrt(2.0 / pre_node_nums)  # 使用ReLU的情况下推荐的初始值
        
        self.params = {
   }
        pre_channel_num = input_dim[0]
        for idx, conv_param in enumerate([conv_param_1, conv_param_2, conv_param_3, conv_param_4, conv_param_5, conv_param_6]):
            self.params['W' + str(idx+1)] = wight_init_scales[idx] * np.random.randn(conv_param['filter_num'], pre_channel_num, conv_param['filter_size'], conv_param['filter_size'])
            self.params['b' + str(idx+1)] = np.zeros(conv_param['filter_num'])
            pre_channel_num = conv_param['filter_num']
        self.params['W7'] = wight_init_scales[6] * np.random.randn(64*4*4, hidden_size)
        self.params['b7'] = np.zeros(hidden_size)
        self.params['W8'] = wight_init_scales[7] * np.random.randn(hidden_size, output_size)
        self.params['b8'] = np.zeros(output_size)

        # 生成层===========
        self.layers = []
        self.layers.append(Convolution(self.params['W1'], self.params['b1'], 
                           conv_param_1['stride'], conv_param_1['pad'])