（六）Tensorflow學習——卷積神經網絡

深度學習框架-Tensorflow案例實戰視頻課程

導入相關包

import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

加載mnist數據集

print('Download and Extract MNIST dataset')
mnist = input_data.read_data_sets('data/', one_hot=True)
trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels
print('MNIST loaded')

參數初始化

# 參數初始化
n_input = 784
n_output = 10
# 兩個卷積層，兩個全連接層
weights = {
    'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)), # [filter的長、filter的寬、filter的高、feature map數量]
    '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)),
}

前向傳播

# 前向傳播
def conv_basic(_input, _w, _b, _keepratio):
    # INPUT，將輸入數據轉換爲四維
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])  # -1表示自動推斷，1表示通道
    # CONV_LAYER_1
    _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')  # SAME表示用0填充 
    _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)  # 保留比率
    # CONV_LAYER_2
    _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)
    # VECTORIZE FLATTEN操作
    _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.nn.relu(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')

輸入輸出數據格式

placeholder形式創建x、y、keepratio（用於dropout）

x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)

反向傳播求解模型

# 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.GradientDescentOptimizer(learning_rate=0.02).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()

模型保存

# SAVER
save_step = 1 # 每一個epoch都保存模型
saver = tf.train.Saver(max_to_keep=3)  # 最多保留三個模型

門機制控制程序訓練或者測試

do_train = 0  # do_train決定程序是進行訓練（等於1）還是測試（等於0）
sess = tf.Session()
sess.run(init)

模型訓練

training_epochs = 10
batch_size = 100
display_step = 1
if do_train == 1:
    for epoch in range(training_epochs+1):
        avg_cost = 0.
        num_batch = int(mnist.train.num_examples/batch_size)
        for i in range(num_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            feeds = {x: batch_xs, y: batch_ys, keepratio: 0.7}
            sess.run(optm, feed_dict=feeds)
            avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio: 1.0})/num_batch
        if epoch % display_step == 0:
            feeds_train = {x: batch_xs, y: batch_ys, keepratio: 1.0}
            feeds_test = {x: mnist.test.images, y: mnist.test.labels, keepratio: 1.0}
            train_acc = sess.run(accr, feed_dict=feeds_train)
            test_acc = sess.run(accr, feed_dict=feeds_test)
            print("Epoch: %03d/%03d cost: %.9f train_acc: %.3f test_acc: %.3f"
                  % (epoch, training_epochs, avg_cost, train_acc, test_acc))
        # 每一個epoch保存一個模型
        if epoch % save_step == 0:
            saver.save(sess, "save/nets/cnn_mnist_basic.ckpt-" + str(epoch))
    print('Done')

模型測試

if do_train == 0:
    epoch = training_epochs
    saver.restore(sess, "save/nets/cnn_mnist_basic.ckpt-" + str(epoch))
    
    test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio: 1.})
    print("TEST ACCURACY: %.3F" % (test_acc))