全连接:每个神经元与前后相邻层的每一个神经元都有连接关系,输入是
特征,输出为预测的结果
前先向传播
定义输入、参数和输出。
# mnist_forward.py
import tensorflow as tf
INPUT_NODE = 28 * 28
OUTPUT_NODE = 10
LAYER1_NODE = 500
def get_weight(shape, regularizer):
w = tf.Variable(tf.truncated_normal(shape, stddev=0.1))
if regularizer != None:
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
def forward(x, regularizer):
w1 = get_weight([INPUT_NODE, LAYER1_NODE], regularizer)
b1 = get_bias([LAYER1_NODE])
y1 = tf.nn.relu(tf.matmul(x, w1) + b1)
w2 = get_weight([LAYER1_NODE, OUTPUT_NODE], regularizer)
b2 = get_bias([OUTPUT_NODE])
y = tf.matmul(y1, w2) + b2
return y
反向传播
反向传播过程完成网络参数的训练
# coding:utf-8
# mnist_backward.py
# 反向传播过程实现利用训练数据集对神经网络模型训练,通过降低损失函数值,
# 实现网络模型参数的优化,从而得到准确率高且泛化能力强的神经网络模型
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import os
import mnist_generateds
BATCH_SIZE = 200
LEARNING_RATE_BASE = 0.1
LEARNING_RATE_DECAY = 0.99
REGULARIZER = 0.0001
STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = './model/'
MODEL_NAME = 'mnist_model'
train_num_examples = 60000
#def backward(mnist):
def backward():
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32, [None, mnist_forward.OUTPUT_NODE])
y = mnist_forward.forward(x, REGULARIZER) #前向传播函数
global_step = tf.Variable(0, trainable=False)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cem = tf.reduce_mean(ce)
loss = cem + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
train_num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step, ema_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
img_batch, label_batch = mnist_generateds.get_tfrecord(BATCH_SIZE, isTrain=True)
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord=coord)
for i in range(STEPS):
#xs, ys = mnist.train.next_batch(BATCH_SIZE)
xs, ys = sess.run([img_batch, label_batch])
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 == 0:
print("After %s training steps, loss on training batch is %s." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
coord.request_stop()
coord.join(threads)
def main():
#mnist = input_data.read_data_sets("./data/", one_hot=True)
#backward(mnist)
backward()
if __name__ == '__main__':
main()
预测
# coding:utf-8
# mnist_test.py
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_backward
import mnist_forward
TEST_INTERVAL_SECS = 5
def test(mnist):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE])
y_ = tf.placeholder(tf.float32, [None, mnist_forward.OUTPUT_NODE])
y = mnist_forward.forward(x, None)
# 实例化带滑动平均的saver对象
ema = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
accuracy_score = sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})
print("After %s training steps, test accuracy = %s" % (global_step, accuracy_score))
else:
print("No checkpoint file found\n")
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist = input_data.read_data_sets("./data/test/", one_hot=True)
test(mnist)
if __name__ == '__main__':
main()
输入真实图片预测结果
网络输入:一维数组(784 个像素点)
像素点:0-1 之间的浮点数(接近 0 越黑,接近 1 越白)
网络输出:一维数组(十个可能性概率),数组中最大的那个元素所对应的索引号就是预测的结果
def application():
testNum = input("input the number of test pictures:")
for i in range(testNum):
testPic = raw_input("the path of test picture:")
testPicArr = pre_pic(testPic)
preValue = restore_model(testPicArr)
print "The prediction number is:", preValue
注解:
任务分成两个函数完成
1)testPicArr = pre_pic(testPic)对手写数字图片做预处理
2)preValue = restore_model(testPicArr) 将符合神经网络输入要求的图片喂
给复现的神经网络模型,输出预测值
制作数据集,实现特定应用
数据集生成读取文件
tfrecords 文件
1)tfrecords:是一种二进制文件,可先将图片和标签制作成该格式的文件。使用 tfrecords 进行数据读取,会提高内存利用率。
2)tf.train.Example: 用来存储训练数据。训练数据的特征用键值对的形式表示。
如:‘ img_raw ’ :值 ‘ label ’ :值 值是 Byteslist/FloatList/Int64List
3)SerializeToString( ):把数据序列化成字符串存储。
生成 tfrecords 文件
#coding:utf-8
import tensorflow as tf
import numpy as np
from PIL import Image
import os
image_train_path = './mnist_data_jpg/mnist_train_jpg_60000/'
label_train_path = './mnist_data_jpg/mnist_train_jpg_60000.txt'
tfRecord_train = './data/mnist_train.tfrecords'
image_test_path = './mnist_data_jpg/mnist_test_jpg_10000/'
label_test_path = './mnist_data_jpg/mnist_test_jpg_10000.txt'
tfRecord_test = './data/mnist_test.tfrecords'
data_path = './data'
resize_height = 28
resize_width = 28
def read_tfRecord(tfRecord_path):
filename_queue = tf.train.string_input_producer([tfRecord_path])
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(serialized_example,
features={
'label': tf.FixedLenFeature([10], tf.int64),
'img_raw': tf.FixedLenFeature([], tf.string)
})
img = tf.decode_raw(features['img_raw'], tf.uint8)
img.set_shape([28 * 28])
img = tf.cast(img, tf.float32) * (1. / 255)
label = tf.cast(features['label'], tf.float32)
return img, label
def write_tfRecord(tfRecordNmae, image_path, label_path):
writer = tf.python_io.TFRecordWriter(tfRecordNmae)
num_pic = 0
f = open(label_path, 'r')
contents = f.readlines()
f.close()
for content in contents:
value = content.split()
img_path = image_path + value[0]
img = Image.open(img_path)
img_raw = img.tobytes()
labels = [0] * 10
labels[int(value[1])] = 1
example = tf.train.Example(features=tf.train.Features(feature={
'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw])),
'label': tf.train.Feature(int64_list=tf.train.Int64List(value=labels))
}))
writer.write(example.SerializeToString())
num_pic += 1
print "The number of picture:", num_pic
writer.close()
print "write tfrecord successfull"
def generate_tfRecord():
isExists = os.path.exists(data_path)
if not isExists:
os.mkdir(data_path)
print 'The directory was created successfully'
else:
print 'directory already exists'
write_tfRecord(tfRecord_train, image_train_path, label_train_path)
write_tfRecord(tfRecord_test, image_test_path, label_test_path)
def get_tfrecord(num, isTrain=True):
if isTrain:
tfRecord_path = tfRecord_train
else:
tfRecord_path = tfRecord_test
img, label = read_tfRecord(tfRecord_path)
img_batch, label_batch = tf.train.shuffle_batch([img, label],
batch_size=num,
num_threads=2,
capacity=1000,
min_after_dequeue=700)
return img_batch, label_batch
def main():
generate_tfRecord()
if __name__ == '__main__':
main()