卷积神经网络实例代码学习

目录

• 代码实例
• 最后结果
• 模型草图

代码实例

import numpy as np
import tensorflow.compat.v1 as tf
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data
tf.compat.v1.disable_eager_execution()
tf.disable_v2_behavior()
#加载数据集
mnist      = input_data.read_data_sets("C:/Users/chenqi/Desktop/data/mnist", one_hot=True)
trainimg   = mnist.train.images
trainlabel = mnist.train.labels
testimg    = mnist.test.images
testlabel  = mnist.test.labels
print ("MNIST ready")
#定义函数需要的参数（权重和偏置）
n_input  = 784
n_output = 10
#wc1 wc2是两个卷积层的过滤器filter，根据下面tf.nn.conv2d函数中对filter参数的要求[filter_height, filter_width, in_channels, out_channels]
#[过滤器的高、过滤器的宽、输入的特征图数量(隐含的表示过滤器的深度)、想要得出的特征图数量]
weights  = {
        '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)),
        '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   = {
        '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))
    }
    
#实现卷积神经网络的函数
def conv_basic(_input, _w, _b, _keepratio):
        # INPUT 同理根据tf.nn.conv2d函数中对input要求[batch, in_height, in_width, in_channels]
        _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
        # CONV LAYER 1
        _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
        #_mean, _var = tf.nn.moments(_conv1, [0, 1, 2])
        #_conv1 = tf.nn.batch_normalization(_conv1, _mean, _var, 0, 1, 0.0001)
        _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
        _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
        _pool_dr1 = tf.nn.dropout(_pool1, _keepratio)
        # CONV LAYER 2
        _conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
        #_mean, _var = tf.nn.moments(_conv2, [0, 1, 2])
        #_conv2 = tf.nn.batch_normalization(_conv2, _mean, _var, 0, 1, 0.0001)
        _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)
        # VECTORIZE
        _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
        # FULLY CONNECTED LAYER 1
        _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
        _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
        # FULLY CONNECTED LAYER 2
        _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])
        # RETURN
        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")
a = tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1))
print (a)
a = tf.Print(a, [a], "a: ")
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
#sess.run(a)
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)

# FUNCTIONS

_pred = conv_basic(x, weights, biases, keepratio)['out']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=_pred, labels=y))
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
_corr = tf.equal(tf.argmax(_pred,1), tf.argmax(y,1)) 
accr = tf.reduce_mean(tf.cast(_corr, tf.float32)) 
init = tf.global_variables_initializer()
    
# SAVER
print ("GRAPH READY")
sess = tf.Session()
sess.run(init)

training_epochs = 15
batch_size      = 100
display_step    = 1
for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = int(mnist.train.num_examples/batch_size)
    #total_batch = 10
    # Loop over all batches
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        # Fit training using batch data
        sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio:0.7})
        # Compute average loss
        avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})/total_batch

    # Display logs per epoch step
    if epoch % display_step == 0: 
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
        train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})
        print (" Training accuracy: %.3f" % (train_acc))
        test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
        print (" Test accuracy: %.3f" % (test_acc))

print ("OPTIMIZATION FINISHED")

最后结果

模型草图

1. 基本结构

   输入→卷积→ReLU→池化→卷积→ReLU→池化→全连接→ReLU→全连接→输出

2. 具体模型

3. 过滤器：因为在我们这里的图片是只有黑白的28x28的灰度图，所以第一层卷积选用过滤器f1=3x3x1，设置要产生64张特征图，那就需要64个f1。第一层卷积的输出也就是第二层卷积的输入是14x14x64，所以选用过滤器f2=3x3x64，设置需要产生128张特征图，那就需要128个f2，输出是7x7x128。

4. 池化：选用了2x2的Max pooling，所以每张特征图经过池化后长、宽都缩小为二分之一，即由28x28x64 → 14x14x64 和 14x14x128 → 7x7x128