深度的卷积神经网络CNN（MNIST数据集示例）_以minst数据集为例进行深度神经网络的应用

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上C C++开发知识点，真正体系化！

由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新

如果你需要这些资料，可以戳这里获取

import numpy as np
import pickle
from collections import OrderedDict
from common.layers import *

class DeepConvNet:
    '''深度的卷积网络层（3x3的滤波器）
    结构层（6个卷积层+3个池化层，全连接层后面用dropout）：
      conv-relu-conv-relu-pool-       [16个滤波器]
      conv-relu-conv-relu-pool-       [32个滤波器]
      conv-relu-conv-relu-pool-       [64个滤波器]
      affine-relu-dropout-affine-dropout-softmax
    '''
    def __init__(self, input_dim=(1, 28, 28),
                 conv1={'filterNum':16,'filterSize':3,'pad':1,'stride':1},
                 conv2={'filterNum':16,'filterSize':3,'pad':1,'stride':1},
                 conv3={'filterNum':32,'filterSize':3,'pad':1,'stride':1},
                 conv4={'filterNum':32,'filterSize':3,'pad':2,'stride':1},
                 conv5={'filterNum':64,'filterSize':3,'pad':1,'stride':1},
                 conv6={'filterNum':64,'filterSize':3,'pad':1,'stride':1},
                 hiddenSize=50, outputSize=10):
        #上一层的神经元数量
        pre_n=np.array([1*3*3,16*3*3,16*3*3,32*3*3,32*3*3,64*3*3,64*4*4,hiddenSize])
        #权重初始值使用He，因为激活函数是ReLU
        weight_inits=np.sqrt(2.0/pre_n)

        self.params={}
        pre_channel_n=input_dim[0]#通道数，每经过一个卷积层更新
        for i,conv in enumerate([conv1,conv2,conv3,conv4,conv5,conv6]):
            self.params['W'+str(i+1)]=weight_inits[i]*np.random.randn(conv['filterNum'],pre_channel_n,conv['filterSize'],conv['filterSize'])
            self.params['b'+str(i+1)]=np.zeros(conv['filterNum'])
            pre_channel_n=conv['filterNum']#更新通道数
        self.params['W7']=weight_inits[6]*np.random.randn(64*4*4,hiddenSize)
        self.params['b7']=np.zeros(hiddenSize)
        self.params['W8']=weight_inits[7]*np.random.randn(hiddenSize,outputSize)
        self.params['b8']=np.zeros(outputSize)

        #生成各层(21层)
        self.layers=[]
        self.layers.append(Convolution(self.params['W1'],self.params['b1'],conv1['stride'],conv1['pad']))
        self.layers.append(Relu())
        self.layers.append(Convolution(self.params['W2'],self.params['b2'],conv2['stride'],conv2['pad']))
        self.layers.append(Relu())
        self.layers.append(Pooling(pool_h=2,pool_w=2,stride=2))
        self.layers.append(Convolution(self.params['W3'],self.params['b3'],conv3['stride'],conv3['pad']))
        self.layers.append(Relu())
        self.layers.append(Convolution(self.params['W4'],self.params['b4'],conv4['stride'],conv4['pad']))
        self.layers.append(Relu())
        self.layers.append(Pooling(pool_h=2,pool_w=2,stride=2))
        self.layers.append(Convolution(self.params['W5'],self.params['b5'],conv5['stride'],conv5['pad']))
        self.layers.append(Relu())
        self.layers.append(Convolution(self.params['W6'],self.params['b6'],conv6['stride'],conv6['pad']))
        self.layers.append(Relu())
        self.layers.append(Pooling(pool_h=2,pool_w=2,stride=2))
        self.layers.append(Affine(self.params['W7'],self.params['b7']))
        self.layers.append(Relu())
        self.layers.append(Dropout(0.5))
        self.layers.append(Affine(self.params['W8'],self.params['b8']))
        self.layers.append(Dropout(0.5))

        self.last_layer=SoftmaxWithLoss()

    def predict(self,x,train_flg=False):
        for layer in self.layers:
            if isinstance(layer,Dropout):#判断层是不是Dropout类型
                x=layer.forward(x,train_flg)
            else:
                x=layer.forward(x)
        return x

    def loss(self,x,t):
        y=self.predict(x,train_flg=True)
        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,train_flg=False)
            y=np.argmax(y,axis=1)
            acc+=np.sum(y==tt)
        return acc/x.shape[0]

    def gradient(self,x,t):
        #forward
        self.loss(x,t)
        #backward
        dout=1
        dout=self.last_layer.backward(dout)
        tmp_layers=self.layers.copy()
        tmp_layers.reverse()
        for layer in tmp_layers:
            dout=layer.backward(dout)
        grads={}#遍历包含权重偏置的层
        for i,layer_i in enumerate((0,2,5,7,10,12,15,18)):
            grads['W'+str(i+1)]=self.layers[layer_i].dW
            grads['b'+str(i+1)]=self.layers[layer_i].db
        return grads

    def save_params(self,fname='params.pkl'):
        params={}
        for k,v in self.params.items():
            params[k]=v
        with open(fname,'wb') as f:
            pickle.dump(params,f)

    def load_params(self,fname='params.pkl'):
        with open(fname,'rb') as f:
            params=pickle.load(f)
        for k,v in params.items():
            self.params[k]=v
        for i,layer_i in enumerate((0,2,5,7,10,12,15,18)):
            self.layers[layer_i].W=self.params['W'+str(i+1)]
            self.layers[layer_i].b=self.params['b'+str(i+1)]

测试精度并保存学习后的参数，代码如下：

import numpy as np
from dataset.mnist import load_mnist
from deepconv import DeepConvNet
from common.trainer import Trainer

#加载MNIST数据集
(x_train,t_train),(x_test,t_test)=load_mnist(flatten=False)

#深度学习CNN
network=DeepConvNet()
trainer=Trainer(network,x_train,t_train,x_test,t_test,epochs=20,mini_batch_size=100,optimizer='Adam',optimizer_param={'lr':0.001},evaluate_sample_num_per_epoch=1000)
trainer.train()

#保存学习的权重偏置参数，方便后续调用
network.save_params('DeepCNN_Params.pkl')
print('保存参数成功！')

上面代码的训练大概花费了6~7个小时（本人配置一般的电脑），接下来我们直接来加载深度学习完保存的权重偏置参数的pkl文件，看下这个深度CNN的精度能达到多少，以及查看20个没有被正确识别的数字图片有什么特征。

![img](https://img-blog.csdnimg.cn/img_convert/8fd72d65c2243ec83a89e16dccdb6f53.png)
![img](https://img-blog.csdnimg.cn/img_convert/add19a3994e4cfd3d67d500d39593e85.png)

**既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，涵盖了95%以上C C++开发知识点，真正体系化！**

**由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新**

**[如果你需要这些资料，可以戳这里获取](https://bbs.csdn.net/topics/618668825)**

课程，涵盖了95%以上C C++开发知识点，真正体系化！**

**由于文件比较多，这里只是将部分目录截图出来，全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频，并且后续会持续更新**

**[如果你需要这些资料，可以戳这里获取](https://bbs.csdn.net/topics/618668825)**