MNIST数据集识别
1.MNIST数据集：
提供6W张2828像素点的0~9手写数字图片和标签，用于训练。
提供1W张2828像素点的0~9手写数字图片和标签，用于测试。
黑底白字，黑底用0表示，白字用0~1之间的浮点数表示，越接近于1，越白。
每张图片784个像素点组成长度为784的一维数组，作为输入特征。
图片标签以一维数组的形式给出，每个元素表示对应分类出现的概率。
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("F:/learn/data/imputdata.csv", one_hot = True)
mnist
print("train data size:",mnist.train.num_examples)
print("validation data size:",mnist.validation.num_examples)
print("test data size:",mnist.test.num_examples)
mnist.train.labels[0]
mnist.train.images[0]
BATCH_SIZE = 200
xs, ys = mnist.train.next_batch(BATCH_SIZE)
print("xs shape:", xs.shape)
print("ys shape:", ys.shape)
tf.get_collection("") #从集合中取全部变量，生成一个列表。
tf.add_n([]) #列表内对应元素相加
tf.cast(x,dtype) #把x转为dtype类型
tf.argmax(x,axis) #返回最大值所在索引号
os.path.join("home","name") #返回home/name
字符串.split()
with tf.Graph().as_default() as g: #其内定义的节点在计算图g中
# 保存模型
saver = tf.train.Saver()
with tf.Session() as sess:
for i in range(STEPS):
if i % 轮数 == 0:
saver.save(sess,os.path.join(MODEL_SAVE_PATH,MODEL_NAME),global_step = global_step)
#加载模型
with tf.Sessionn() as sess:
ckpt = tf.train.get_checkpoint_state(存储路径)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path) #加载到当前会话中
# 实例化可还原滑动平均值的saver
ema = tf.trian.ExponentialMovingAverage(滑动平均基数)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
#准确率计算方法
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
模块化搭建神经网络
mnist_forward.py
import tensorflow as tf
INPUT_NODE = 784 #输入节点是784个，因为输入的是图片的像素值，每张素片784个像素点，每个像素点是0~1之间的浮点数
OUTPUT_NODE = 10 #输出10个数，每个数表示对应的索引号出现的概率
LAYER1_NODE = 500 #隐藏层的节点个数
def get_weight(shape, regularizer):
w = tf.Variable(tf.truncated_normal(shape,stddev=0.1)) #随机生成w
if regularizer != None: tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w)) #正则化
return w
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
def forward(x, regularizer):
#第一层
w1 = get_weight([INPUT_NODE, LAYER1_NODE], regularizer)
b1 = get_bias([LAYER1_NODE])
y1 = tf.nn.relu(tf.matmul(x, w1) + b1)
#第二层
w2 = get_weight([LAYER1_NODE, OUTPUT_NODE], regularizer)
b2 = get_bias([OUTPUT_NODE])
y = tf.matmul(y1, w2) + b2 #要对输出使用softmax函数，所以不过relu函数
return y
mnist_backward.py
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import os
BATCH_SIZE = 200 #每轮喂入神经网络200张图片
LEARNING_RATE_BASE = 0.1 #学习率是0.1
LEARNING_RATE_DECAY = 0.99 #学习率衰减率是0.99
REGULARIZER = 0.0001 #正则化系数
STEPS = 50000 #共训练50000轮
MOVING_AVERAGE_DECAY = 0.99 #滑动平均衰减率
MODEL_SAVE_PATH="./model/" #模型保存路径
MODEL_NAME="mnist_model" #模型保存文件名
def backward(mnist):
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)
global_step = tf.Variable(0, trainable=False) #赋初值，设定为不可训练
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')) #包含正则化的损失函数
定义指数衰减学习率
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step) #定义训练过程
#定义滑动平均
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() #实例化saver
with tf.Session() as sess:
init_op = tf.global_variables_initializer() #初始化所有变量
sess.run(init_op)
for i in range(STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
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)
def main():
mnist = input_data.read_data_sets("./data/", one_hot=True)
backward(mnist)
if __name__ == '__main__':
main()
mnist_test.py
#coding:utf-8
import time #为了延迟
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_forward
import mnist_backward
TEST_INTERVAL_SECS = 5 #定义循环间隔时间为5秒
def test(mnist):
with tf.Graph().as_default() as g: #复现计算图
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)
ema = tf.train.ExponentialMovingAverage(mnist_backward.MOVING_AVERAGE_DECAY)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore) #实例化带滑动平均的saver对象，这样所有参数在会话中，被加载时，会被赋值为各自的滑动平均值。
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 step(s), test accuracy = %g" % (global_step, accuracy_score))
else:
print('No checkpoint file found')
return
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist = input_data.read_data_sets("./data/", one_hot=True)
test(mnist)
if __name__ == '__main__':
main()
