tensorflow-神经网络识别手写数字
Posted wyply115
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了tensorflow-神经网络识别手写数字相关的知识,希望对你有一定的参考价值。
- 数据下载连接:http://yann.lecun.com/exdb/mnist/
- 下载t10k-images-idx3-ubyte.gz;t10k-labels-idx1-ubyte.gz;train-images-idx3-ubyte.gz;train-labels-idx1-ubyte.gz
- 简单神经网络识别手写数字
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 数据下载连接:http://yann.lecun.com/exdb/mnist/
# 下载t10k-images-idx3-ubyte.gz;t10k-labels-idx1-ubyte.gz;train-images-idx3-ubyte.gz;train-labels-idx1-ubyte.gz
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_integer("is_train", 1, "指定程序是训练还是预测") # 指定1是训练模型,指定0是进行对测试集预测
def full_connected():
'''
简单神经网络对手写数字图片进行识别
:return: None
'''
# 获取真实的数据
mnist = input_data.read_data_sets("./data/mnist/", one_hot=True)
# 1. 建立数据占位符 x[None, 784] y[None, 10]
with tf.variable_scope("data"):
x = tf.placeholder(tf.float32, [None,784])
y_true = tf.placeholder(tf.int32, [None, 10])
# 2. 建立一个全连接层得神经网络 w[784,10] b[10]
with tf.variable_scope("fc_model"):
# 随机初始化权重和偏置
weight = tf.Variable(tf.random_normal([784,10], mean=0.0, stddev=1.0), name="w")
bias = tf.Variable(tf.constant(0.0, shape=[10]))
# 预测None的输出结果 [None, 784] * [784, 10] + [10] = [None, 10]
y_predict = tf.matmul(x, weight) + bias
# 3. 求出所有样本的损失,然后求平均值
with tf.variable_scope("soft_cross"):
# 求平均交叉熵损失
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_predict))
# 4. 梯度下降求出损失
with tf.variable_scope("optimazer"):
train_op = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
# 5. 计算准确率
with tf.variable_scope("acc"):
equal_list = tf.equal(tf.arg_max(y_true,1), tf.arg_max(y_predict,1))
accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
# 收集变量
tf.summary.scalar("losses", loss)
tf.summary.scalar("acc", accuracy)
# 高纬度变量收集
tf.summary.histogram("weights", weight)
tf.summary.histogram("biases", bias)
# 定义一个合并变量得op
merged = tf.summary.merge_all()
# 创建一个saver保存模型
saver = tf.train.Saver()
# 6.定义一个初始化变量的op
init_op = tf.global_variables_initializer()
# 6. 开启会话进行训练
with tf.Session() as sess:
# 初始化变量
sess.run(init_op)
# 建立events文件,然后写入
filewriter = tf.summary.FileWriter("./summary/", graph=sess.graph)
if FLAGS.is_train == 1:
# 迭代步数训练,更新参数预测
for i in range(2000):
# 取出真是存在得特征值和目标值
mnist_x, mnist_y = mnist.train.next_batch(100)
sess.run(train_op, feed_dict=x: mnist_x, y_true:mnist_y)
# 写入每步训练得值
summary = sess.run(merged, feed_dict=x: mnist_x, y_true:mnist_y)
filewriter.add_summary(summary, i)
print("训练第 %d 步,准确率为:%f " %(i, sess.run(accuracy, feed_dict=x: mnist_x, y_true:mnist_y)))
# 保存模型
saver.save(sess, "./data/ckpt/fc_model")
else:
# 加载模型
saver.restore(sess, "./data/ckpt/fc_model")
# 如果是0,做出预测
for i in range(100):
# 每次测试一张图片
x_test, y_test = mnist.test.next_batch(1)
print("第 %d 张图片,手写数字目标是 %d, 预测结果是:%d" % (
i,
tf.argmax(y_test, 1).eval(),
tf.argmax(sess.run(y_predict, feed_dict=x: x_test, y_true: y_test), 1).eval()
))
return None
if __name__ == '__main__':
full_connected()
- 卷积神经网络识别手写数字
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
def weight_variables(shape):
'''
初始化权重
:param shape:
:return: w 初始化的权重
'''
w = tf.Variable(tf.random_normal(shape=shape, mean=0.0, stddev=1.0))
return w
def bias_variables(shape):
'''
初始化偏置
:param shape:
:return: b 初始化的偏置
'''
b = tf.Variable(tf.constant(0.1, shape=shape))
return b
def model():
'''
自定义卷积模型
一卷积层:32个filter,5*5,strides=1,padding="SAME"; 池化:2*2, strides=2,padding="SAME"
二卷积层:64个filter,5*5,strides=1,padding="SAME";池化:2*2, strides=2
:return: None
'''
# 1. 准备数据占位符 x[None, 784] y_true[None, 10]
with tf.variable_scope("data"):
x = tf.placeholder(tf.float32, [None, 784])
y_true = tf.placeholder(tf.int32, [None, 10])
# 2. 一卷积层, 卷积、激活、池化
with tf.variable_scope("conv1"):
# 随机初始化权重, 偏置
w_conv1 = weight_variables([5,5,1,32])
b_conv1 = bias_variables([32])
# 对x改变形状[None,784] --> [None, 28, 28, 1]
x_reshape = tf.reshape(x, [-1, 28,28,1])
# 卷积+激活 [None, 28, 28, 1] --> [None, 28, 28, 32]
x_relu1 = tf.nn.relu(tf.nn.conv2d(x_reshape, w_conv1, strides=[1,1,1,1], padding="SAME") + b_conv1)
# 池化 2*2 [None, 28, 28, 32] --> [None, 14, 14, 32]
x_pool1 = tf.nn.max_pool(x_relu1, ksize=[1,2,2,1], strides=[1,2,2,1], padding="SAME")
# 3. 二卷积层
with tf.variable_scope("conv2"):
# 随机初始化权重, 偏置
w_conv2 = weight_variables([5, 5, 32, 64])
b_conv2 = bias_variables([64])
# 卷积+激活 [None, 14, 14, 32] --> [None, 14, 14, 64]
x_relu2 = tf.nn.relu(tf.nn.conv2d(x_pool1, w_conv2, strides=[1, 1, 1, 1], padding="SAME") + b_conv2)
# 池化 2*2 [None, 14, 14, 64] --> [None, 7, 7, 64]
x_pool2 = tf.nn.max_pool(x_relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")
# 4. 全连接层 [None,7,7,64] --> [None,7*7*64] * [7*7*64,10] + [10] = [None,10]
with tf.variable_scope("fc"):
# 随机初始化权重, 偏置
w_fc = weight_variables([7*7*64, 10])
b_fc = bias_variables([10])
# 修改x_pool2形状
x_fc_reshape = tf.reshape(x_pool2, [-1, 7*7*64])
# 矩阵运算得出每个样本得10个结果
y_predict = tf.matmul(x_fc_reshape, w_fc) + b_fc
return x, y_true, y_predict
def conv_fc():
# 1. 获取真实数据
mnist = input_data.read_data_sets("./data/mnist/", one_hot=True)
# 2. 定义模型,获得输出
x, y_true, y_predict = model()
# 3. 求出所有样本的损失,然后求平均值
with tf.variable_scope("soft_cross"):
# 求平均交叉熵损失
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_predict))
# 4. 梯度下降求出损失
with tf.variable_scope("optimazer"):
train_op = tf.train.GradientDescentOptimizer(0.0001).minimize(loss)
# 5. 计算准确率
with tf.variable_scope("acc"):
equal_list = tf.equal(tf.arg_max(y_true, 1), tf.arg_max(y_predict, 1))
accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))
# 定义一个初始化变量的op
init_op = tf.global_variables_initializer()
# 开启会话
with tf.Session() as sess:
sess.run(init_op)
# 循环训练
for i in range(3000):
# 取出真实数据中得特征值和目标值
mnist_x, mnist_y = mnist.train.next_batch(50)
sess.run(train_op, feed_dict=x: mnist_x, y_true: mnist_y)
print("训练第 %d 步,准确率为:%f " % (i, sess.run(accuracy, feed_dict=x: mnist_x, y_true: mnist_y)))
if __name__ == '__main__':
conv_fc()
- 一到笔试题
计算过程(通道对输出不影响):
- 经过一层卷积:长,H2 = (200 - 5 + 2*1)/2 +1 = 99.5 (这里不是整数是需要自己分析卷积过程,步长为2,0.5步就是1,因为padding=1,padding是填充的0无需观察,因此结果就是99);长宽一样,因此不在计算宽。
- 经过pooling,H2 = (99 - 3 + 2*0)/1 +1 = 97
- 又经过一层卷积:H2 = (97 - 3 + 2*1)/1 +1 = 97,因此最终图片大小输出为97*97
因此答案是:C. 97
以上是关于tensorflow-神经网络识别手写数字的主要内容,如果未能解决你的问题,请参考以下文章