利用Tensorflow实现卷积神经网络模型

Posted 2020-09-17

首先看一下卷积神经网络模型，如下图：

卷积神经网络（CNN）由输入层、卷积层、激活函数、池化层、全连接层组成，即INPUT-CONV-RELU-POOL-FC
池化层：为了减少运算量和数据维度而设置的一种层。

 

代码如下：

n_input  = 784        # 28*28的灰度图
n_output = 10         # 完成一个10分类的操作
weights  = {
    #\'权重参数\': tf.Variable(tf.高期([feature的H, feature的W, 当前feature连接的输入的深度, 最终想得到多少个特征图], 标准差=0.1)),
    \'wc1\': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)),
    \'wc2\': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)),
　　 #\'全连接层参数\': tf.Variable(tf.高斯([特征图H*特征图W*深度, 最终想得到多少个特征图], 标准差=0.1)),
    \'wd1\': tf.Variable(tf.random_normal([7*7*128, 1024], stddev=0.1)),
    \'wd2\': tf.Variable(tf.random_normal([1024, n_output], stddev=0.1))
}
biases   = {
　　 #\'偏置参数\': tf.Variable(tf.高斯([第1层有多少个偏置项], 标准差=0.1)),
    \'bc1\': tf.Variable(tf.random_normal([64], stddev=0.1)),
    \'bc2\': tf.Variable(tf.random_normal([128], stddev=0.1)),
    \'bd1\': tf.Variable(tf.random_normal([1024], stddev=0.1)),
    \'bd2\': tf.Variable(tf.random_normal([n_output], stddev=0.1))
}

#卷积神经网络
def conv_basic(_input, _w, _b, _keepratio):
    #将输入数据转化成一个四维的[n, h, w, c]tensorflow格式数据
    #_input_r = tf.将输入数据转化成tensorflow格式(输入, shape=[batch_size大小, H, W, 深度])
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])

    #第1层卷积    
    #_conv1 = tf.nn.卷积(输入, 权重参数, 步长=[batch_size大小, H, W, 深度], padding=\'建议选择SAME\')
    _conv1 = tf.nn.conv2d(_input_r, _w[\'wc1\'], strides=[1, 1, 1, 1], padding=\'SAME\')
    #_conv1 = tf.nn.非线性激活函数(tf.nn.加法(_conv1, _b[\'bc1\']))
    _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b[\'bc1\']))
    #第1层池化
    #_pool1 = tf.nn.池化函数(_conv1, 指定池化窗口的大小=[batch_size大小, H, W, 深度], strides=[1, 2, 2, 1], padding=\'SAME\')
    _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding=\'SAME\')
    #随机杀死一些节点，不让所有神经元都加入到训练中
    #_pool_dr1 = tf.nn.dropout(_pool1, 保留比例)
    _pool_dr1 = tf.nn.dropout(_pool1, _keepratio)
    
    #第2层卷积
    _conv2 = tf.nn.conv2d(_pool_dr1, _w[\'wc2\'], strides=[1, 1, 1, 1], padding=\'SAME\')
    _conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b[\'bc2\']))
    _pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding=\'SAME\')
    _pool_dr2 = tf.nn.dropout(_pool2, _keepratio)
    
    #全连接层
    #转化成tensorflow格式
    _dense1 = tf.reshape(_pool_dr2, [-1, _w[\'wd1\'].get_shape().as_list()[0]])
    #第1层全连接层
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w[\'wd1\']), _b[\'bd1\']))
    _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
    #第2层全连接层
    _out = tf.add(tf.matmul(_fc_dr1, _w[\'wd2\']), _b[\'bd2\'])
    #返回值
    out = { \'input_r\': _input_r, \'conv1\': _conv1, \'pool1\': _pool1, \'pool1_dr1\': _pool_dr1,
        \'conv2\': _conv2, \'pool2\': _pool2, \'pool_dr2\': _pool_dr2, \'dense1\': _dense1,
        \'fc1\': _fc1, \'fc_dr1\': _fc_dr1, \'out\': _out
    }
    return out
print ("CNN READY")

#设置损失函数&优化器（代码说明：略 请看前面文档）
learning_rate = 0.001
x      = tf.placeholder("float", [None, nsteps, diminput])
y      = tf.placeholder("float", [None, dimoutput])
myrnn  = _RNN(x, weights, biases, nsteps, \'basic\')
pred   = myrnn[\'O\']
cost   = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) 
optm   = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) # Adam Optimizer
accr   = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(pred,1), tf.argmax(y,1)), tf.float32))
init   = tf.global_variables_initializer()
print ("Network Ready!")

#训练（代码说明：略 请看前面文档）
training_epochs = 5
batch_size      = 16
display_step    = 1
sess = tf.Session()
sess.run(init)
print ("Start optimization")
for epoch in range(training_epochs):
    avg_cost = 0.
    #total_batch = int(mnist.train.num_examples/batch_size)
    total_batch = 100
    # Loop over all batches
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        batch_xs = batch_xs.reshape((batch_size, nsteps, diminput))
        # Fit training using batch data
        feeds = {x: batch_xs, y: batch_ys}
        sess.run(optm, feed_dict=feeds)
        # Compute average loss
        avg_cost += sess.run(cost, feed_dict=feeds)/total_batch
    # Display logs per epoch step
    if epoch % display_step == 0: 
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
        feeds = {x: batch_xs, y: batch_ys}
        train_acc = sess.run(accr, feed_dict=feeds)
        print (" Training accuracy: %.3f" % (train_acc))
        testimgs = testimgs.reshape((ntest, nsteps, diminput))
        feeds = {x: testimgs, y: testlabels, istate: np.zeros((ntest, 2*dimhidden))}
        test_acc = sess.run(accr, feed_dict=feeds)
        print (" Test accuracy: %.3f" % (test_acc))
print ("Optimization Finished.")