Tensorflow学习笔记(一):手写数字识别
mnist_forward.py
#!/usr/bin/env python2.7
#coding: utf-8
import tensorflow as tf
INPUT_NODE = 784 #喂入数据的大小
OUTPUT_NODE = 10 #输出数据的大小
LAYER1_NODE = 500 #第一层隐藏层的大小
def get_weight(shape, regularizer): #生成形状为shape,正则化率为regularizer的w
w = tf.Variable(tf.truncated_normal(shape, stddev = 0.1)) #定义w为形状为shape,标准差为0.1的截断的随机值
if regularizer != None: tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w)) :#将w以L2正则化的结果添加到集合losses中
return w
def get_bias(shape): #生成形状为shape的b
b = tf.Variable(tf.zeros(shape)) #以0填充的shape
return b
def forward(x, regularizer): #正向传播
#输入层到隐藏层
w1 = get_weight([INPUT_NODE, LAYER1_NODE], regularizer)
b1 = get_bias([LAYER1_NODE])
y1 = tf.nn.relu(tf.matmul(x, w1) + b1) #对矩阵乘法的计算结果进行激活,即mat=max(mat, 0)
#隐藏层到输出层
w2 = get_weight([LAYER1_NODE, OUTPUT_NODE], regularizer)
b2 = get_bias([OUTPUT_NODE])
y = tf.matmul(y1, w2) + b2
return y
mnist_backward.py
#!/usr/bin/env python2.7
#coding: utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data #导入mnist数据集
import mnist_forward
import os
BATCH_SIZE = 200 #每次喂入的数据组数
LEARNING_RATE_BASE = 0.1 #学习率基数
LEARNING_RATE_DECAY = 0.99 #学习率衰减率
REGULARIZER = 0.0001 #正则化率
STEPS = 50000 #训练次数
MOVING_AVERAGE_DECAY = 0.99 #滑动平均衰减率
MODEL_SAVE_PATH = './model/' #模型的保存位置
MODEL_NAME = 'mnist_model' #模型的名称
def backward(mnist): #反向传播
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE]) #待喂入数据,占位
y_ = tf.placeholder(tf.float32, [None, mnist_forward.OUTPUT_NODE]) #计算所得数据,占位
y = mnist_forward.forward(x, REGULARIZER) #正向传播,得到计算图
global_step = tf.Variable(0, trainable = False) #不可训练的变量,作为计步器
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = y , labels = tf.argmax(y_, 1))
#用交叉熵归一化指数函数计算y和y_的差距
cem = tf.reduce_mean(ce)
#求平均
loss = cem + tf.add_n(tf.get_collection('losses'))
#总损失为交叉熵+正则化(从losses集合中取出并求和)
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY, staircase = True)
#指数衰减学习率,呈阶梯下降
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step = global_step)
#定义线性下降的优化器作为训练步骤
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
#求滑动平均
ema_op = ema.apply(tf.trainable_variables())
#把滑动平均应用到所有可训练变量
with tf.control_dependencies([train_step, ema_op]): #将训练步骤和滑动平均操作绑定
train_op = tf.no_op(name = 'train') #什么也不做
saver = tf.train.Saver() #初始化保存器
with tf.Session() as sess:
sess.run(tf.global_variables_initializer()) #初始化所有全局变量
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH) #检查模型目录是否已有模型,获取其状态
if ckpt and ckpt.model_checkpoint_path: #如果存在且能获得模型路径
saver.restore(sess, ckpt.model_checkpoint_path) #重现模型到当前会话
for i in range(STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE) #从mnist中去下一撮数据
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict = {x: xs, y_: ys}) #训练,并得到损失和总步数
if i % 1000 == 0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step = global_step) #暂存当前会话
def main():
mnist = input_data.read_data_sets('./data/', one_hot = True) #读取数据集,如果没有会自动下载
backward(mnist) #反向传播
if __name__ == '__main__':
main()
mnist_app.py
#!/usr/bin/env python2.7
#coding: utf-8
import tensorflow as tf
import numpy as np
from PIL import Image
import mnist_forward
import mnist_backward
def restore_model(testPicArr): #传入图像像素值的列表,恢复模型,喂入图像,得到结果
with tf.Graph().as_default() as tg: #打开默认图
x = tf.placeholder(tf.float32, [None, mnist_forward.INPUT_NODE]) #要喂入的数据,占位
y = mnist_forward.forward(x, None) #前向传播,得到计算图,y为输出
preValue = tf.argmax(y, 1) #去y中最大元素的下表
variable_averages = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
#求滑动平均
variables_to_restore = variable_averages.variables_to_restore()
#获取所有可恢复的变量
saver = tf.train.Saver(variables_to_restore)
#初始化保存器
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_backward.MODEL_SAVE_PATH) #检查模型状态
if ckpt and ckpt.model_checkpoint_path: #存在
saver.restore(sess, ckpt.model_checkpoint_path) #恢复模型到当前会话
preValue = sess.run(preValue, feed_dict = {x: testPicArr}) #喂入数据,得到结果
return preValue
else:
print("No checkpoint file found")
return -1
def pre_pic(picName): #传入图片路径,进行预处理
img = Image.open(picName) #打开图片文件
reIm = img.resize((28, 28), Image.ANTIALIAS) #抗锯齿地将图片重置到28×28
im_arr = np.array(reIm.convert('L')) #将图像灰度化并存为列表
threshold = 50 #阈值,超过则为白,没超过则为黑
for i in range(28):
for j in range(28):
im_arr[i][j] = 255 - im_arr[i][j] #由于mnist存的是黑0白1,所以要反过来
if im_arr[i][j] < threshold:
im_arr[i][j] = 0
else:
im_arr[i][j] = 255
nm_arr = im_arr.reshape([1, 784]) #将图像像素列表重新定型
nm_arr = nm_arr.astype(np.float32) #将列表转换到float32类型
img_ready = np.multiply(nm_arr, 1.0 / 255.0) #列表各元素除255
return img_ready
def application():
testNum = input("Inpt 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
def main():
application()
if __name__ == '__main__':
main()