tensorflow学习（五）基于卷积神经网络mnist数据集分类

import numpy as np
import tensorflow as tf
import input_data
mnist = input_data.read_data_sets('data/',one_hot=True)

train_img = mnist.train.images
train_label = mnist.train.labels
test_img = mnist.test.images
test_label = mnist.test.labels

#设置输出输出层数
n_input = 784
n_output = 10
w = {
    'wc1': tf.Variable(tf.random_normal([3,3,1,64],stddev=0.1)), #[w,n,in_channel,out_channel]
    '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)), #[输入，输出]
    'wd2': tf.Variable(tf.random_normal([1024,n_output],stddev=0.1))

}

b = {
    '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)),

}

def conv_basic(_input, _w, _b, _kratio):
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
    #转化为一个四维数据 [n_batch_size, h, w, channel] -1 自动判断输入的batch_size
    _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1,1,1,1], padding='SAME')
    #strides [batch_size,  h, w, channel] same 补零 valide 去除末尾的数据
    _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')
    #ksize [batch_siez,w, h, channel] strides = [batch_size, w, h, channel]
    _pool1_dr1 = tf.nn.dropout(_pool1,_kratio)
    # conv2
    _conv2 = tf.nn.conv2d(_pool1_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
    # strides [batch_size,  h, w, channel] same 补零 valide 去除末尾的数据
    _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')
    # ksize [batch_siez,w, h, channel] strides = [batch_size, w, h, channel]
    _pool_dr2 = tf.nn.dropout(_pool2, _kratio)
    #vectorize
    _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
    #full1
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
    _fc_dr1 = tf.nn.dropout(_fc1, _kratio)
    #full2
    _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])


    out = { 'input_r':_input_r, 'conv1':_conv1, 'pool1':_pool1,
            'pool1_dr1':_pool1_dr1, 'conv2':_conv2, 'pool2':_pool2,
            'pool_dir2':_pool_dr2, 'densel':_dense1, 'fc1':_fc1,
            'fc1_dr1': _fc_dr1, 'out':_out

    }
    return out


x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
kratio = tf.placeholder(tf.float32)
#对于设置的所有placeholder都需要通过字典赋值

_pred = conv_basic(x, w, b, kratio)['out']

#计算损失 需要输入labels 和logits
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=_pred))

optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
_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()

with tf.Session() as sess:
    sess.run(init)
    batch_size = 16
    for epoch in range(15):
        avg_loss =0
        total_batch = 10
        for i in range(10):
            batch_xs, batch_ys = mnist.train.next_batch(16)
            sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, kratio: 0.7})
            avg_loss += sess.run(loss, feed_dict={x:batch_xs, y:batch_ys, kratio:1.} )/10

        print('epoch: %03d/%03d cost: %.9f' % (epoch,15, avg_loss ))
        train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, kratio : 1.})
        print('accuracy %.3f'% (train_acc))

添加保存神经网络和读取神经网络参数。当do_train为1时训练保存神经网络当do_train为0是读取神经网络

import numpy as np
import tensorflow as tf
import input_data
mnist = input_data.read_data_sets('data/',one_hot=True)

train_img = mnist.train.images
train_label = mnist.train.labels
test_img = mnist.test.images
test_label = mnist.test.labels

#设置输出输出层数
n_input = 784
n_output = 10
w = {
    'wc1': tf.Variable(tf.random_normal([3,3,1,64],stddev=0.1)), #[w,n,in_channel,out_channel]
    '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)), #[输入，输出]
    'wd2': tf.Variable(tf.random_normal([1024,n_output],stddev=0.1))

}

b = {
    '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)),

}

def conv_basic(_input, _w, _b, _kratio):
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
    #转化为一个四维数据 [n_batch_size, h, w, channel] -1 自动判断输入的batch_size
    _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1,1,1,1], padding='SAME')
    #strides [batch_size,  h, w, channel] same 补零 valide 去除末尾的数据
    _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')
    #ksize [batch_siez,w, h, channel] strides = [batch_size, w, h, channel]
    _pool1_dr1 = tf.nn.dropout(_pool1,_kratio)
    # conv2
    _conv2 = tf.nn.conv2d(_pool1_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
    # strides [batch_size,  h, w, channel] same 补零 valide 去除末尾的数据
    _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')
    # ksize [batch_siez,w, h, channel] strides = [batch_size, w, h, channel]
    _pool_dr2 = tf.nn.dropout(_pool2, _kratio)
    #vectorize
    _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
    #full1
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
    _fc_dr1 = tf.nn.dropout(_fc1, _kratio)
    #full2
    _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])


    out = { 'input_r':_input_r, 'conv1':_conv1, 'pool1':_pool1,
            'pool1_dr1':_pool1_dr1, 'conv2':_conv2, 'pool2':_pool2,
            'pool_dir2':_pool_dr2, 'densel':_dense1, 'fc1':_fc1,
            'fc1_dr1': _fc_dr1, 'out':_out

    }
    return out


x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
kratio = tf.placeholder(tf.float32)
#对于设置的所有placeholder都需要通过字典赋值

_pred = conv_basic(x, w, b, kratio)['out']

#计算损失 需要输入labels 和logits
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=_pred))

optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
_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()

save_step = 1
saver = tf.train.Saver(max_to_keep=3)

do_train = 0




with tf.Session() as sess:
    sess.run(init)
    batch_size = 16

    if do_train ==1:
        for epoch in range(15):
            avg_loss =0
            total_batch = 10
            for i in range(10):
                batch_xs, batch_ys = mnist.train.next_batch(16)
                sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, kratio: 0.7})
                avg_loss += sess.run(loss, feed_dict={x:batch_xs, y:batch_ys, kratio:1.} )/10

            print('epoch: %03d/%03d cost: %.9f' % (epoch,15, avg_loss ))
            train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, kratio : 1.})
            print('accuracy %.3f'% (train_acc))
            saver.save(sess, 'saver/nets/cnn_minist.ckpt-' + str(epoch) )
    if do_train ==0:
        epoch = 15 -1
        saver.restore(sess, 'saver/nets/cnn_minist.ckpt-' + str(epoch) )
        test_acc = sess.run(accr,feed_dict={x: test_img, y:test_label, kratio:1.})
        print('testing accuray %.3f' % (test_acc))