深度学习笔记(15. TensorFlow实现CNN)

我会带着你远行 2023-06-30 02:37 23阅读 0赞

### 摘要 ###

本文是学习Ng深度学习课程第四部分——卷积神经网络。看完课程做了一下作业，用TensorFlow实现了一个简单的CNN网络，完成了手势0~5数字识别。基本就是课件代码copy，比较遗憾的是numpy实现的同样结构CNN有问题，损失不下降，还出现梯度爆炸。  
程序地址：[https://github.com/ConstellationBJUT/Coursera-DL-Study-Notes/blob/master/class4\_week1\_cnn/tf\_cnn\_classfier.py][https_github.com_ConstellationBJUT_Coursera-DL-Study-Notes_blob_master_class4_week1_cnn_tf_cnn_classfier.py]

### 网络结构 ###

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2Jqam95MjAwOQ_size_16_color_FFFFFF_t_70]  
图片->conv1->relu->pool1 -> conv2->relu->pool2 -> flatten ->FC->softmax

### 程序结构 ###

1.  数据：两个.h5文件，分别是train,X(1080, 64, 64, 3)，一共1080个样本，每个样本图片是64*64*3，label(1080, 6)。dev，X(120,64,64,3)，label(120, 6)
2.  程序文件：tf\_cnn\_classfier.py，包括CNN网络，分类试验等

### 主程序 ###

用tf主要完成正向传播网络的构建，用框架不用考虑反向传播，还是相当方便的。

def forward_propagation(X, parameters):
        """ Implements the forward propagation for the model: CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED Arguments: X -- input dataset placeholder, of shape (input size, number of examples) parameters -- python dictionary containing your parameters "W1", "W2" the shapes are given in initialize_parameters Returns: Z3 -- the output of the last LINEAR unit """
    
        # Retrieve the parameters from the dictionary "parameters"
        W1 = parameters['W1']
        W2 = parameters['W2']
    
        # CONV2D: stride of 1, padding 'SAME'
        Z1 = tf.nn.conv2d(X, filter=W1, strides=[1, 1, 1, 1], padding='SAME')
        # RELU
        A1 = tf.nn.relu(Z1)
        # MAXPOOL: window 8x8, sride 8, padding 'SAME'
        P1 = tf.nn.max_pool(A1, ksize=[1, 8, 8, 1], strides=[1, 8, 8, 1], padding='SAME')
        # CONV2D: filters W2, stride 1, padding 'SAME'
        Z2 = tf.nn.conv2d(P1, filter=W2, strides=[1, 1, 1, 1], padding='SAME')
        # RELU
        A2 = tf.nn.relu(Z2)
        # MAXPOOL: window 4x4, stride 4, padding 'SAME'
        P2 = tf.nn.max_pool(A2, ksize=[1, 4, 4, 1], strides=[1, 4, 4, 1], padding='SAME')
        # FLATTEN
        P2 = tf.contrib.layers.flatten(P2)
        # FULLY-CONNECTED without non-linear activation function (not not call softmax).
        # 6 neurons in output layer. Hint: one of the arguments should be "activation_fn=None"
        Z3 = tf.contrib.layers.fully_connected(P2, 6, activation_fn=None)
    
        return Z3

### 实验结果 ###

直接copy，代码一样，结果也是一样的，老没意思了  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2Jqam95MjAwOQ_size_16_color_FFFFFF_t_70 1]

### 总结 ###

numpy实现的CNN还在查错误，发现实现这种网络结构真的好难纠错啊。这波课程5部分——DNN、改善神经网络(Adam等优化梯度算法)、结构化机器学习（经验之谈）、CNN、RNN（GRU、LSTM），就算刷完了。有些语音和翻译的实验没做，感觉还不错

[https_github.com_ConstellationBJUT_Coursera-DL-Study-Notes_blob_master_class4_week1_cnn_tf_cnn_classfier.py]: https://github.com/ConstellationBJUT/Coursera-DL-Study-Notes/blob/master/class4_week1_cnn/tf_cnn_classfier.py
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2Jqam95MjAwOQ_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200114145635528.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2Jqam95MjAwOQ==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2Jqam95MjAwOQ_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20200114150735891.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2Jqam95MjAwOQ==,size_16,color_FFFFFF,t_70