快捷導(dǎo)航

使用TensorFlow搭建一個(gè)全連接神經(jīng)網(wǎng)絡(luò)教程

更新時(shí)間：2020年02月06日 10:22:56 作者：techping

今天小編就為大家分享一篇使用TensorFlow搭建一個(gè)全連接神經(jīng)網(wǎng)絡(luò)教程，具有很好的參考價(jià)值，希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧

說(shuō)明

本例子利用TensorFlow搭建一個(gè)全連接神經(jīng)網(wǎng)絡(luò)，實(shí)現(xiàn)對(duì)MNIST手寫數(shù)字的識(shí)別。

先上代碼

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

# prepare data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

xs = tf.placeholder(tf.float32, [None, 784])
ys = tf.placeholder(tf.float32, [None, 10])

# the model of the fully-connected network
weights = tf.Variable(tf.random_normal([784, 10]))
biases = tf.Variable(tf.zeros([1, 10]) + 0.1)
outputs = tf.matmul(xs, weights) + biases
predictions = tf.nn.softmax(outputs)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(predictions),
            reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

# compute the accuracy
correct_predictions = tf.equal(tf.argmax(predictions, 1), tf.argmax(ys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))

with tf.Session() as sess:
 init = tf.global_variables_initializer()
 sess.run(init)
 for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict={
   xs: batch_xs,
   ys: batch_ys
  })
  if i % 50 == 0:
   print(sess.run(accuracy, feed_dict={
    xs: mnist.test.images,
    ys: mnist.test.labels
   }))

代碼解析

1. 讀取MNIST數(shù)據(jù)

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

2. 建立占位符

xs = tf.placeholder(tf.float32, [None, 784])
ys = tf.placeholder(tf.float32, [None, 10])

xs 代表圖片像素?cái)?shù)據(jù), 每張圖片(28×28)被展開(kāi)成(1×784), 有多少圖片還未定, 所以shape為None×784.

ys 代表圖片標(biāo)簽數(shù)據(jù), 0-9十個(gè)數(shù)字被表示成One-hot形式, 即只有對(duì)應(yīng)bit為1, 其余為0.

3. 建立模型

weights = tf.Variable(tf.random_normal([784, 10]))


biases = tf.Variable(tf.zeros([1, 10]) + 0.1)
outputs = tf.matmul(xs, weights) + biases
predictions = tf.nn.softmax(outputs)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(predictions),
            reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

使用Softmax函數(shù)作為激活函數(shù)：

4. 計(jì)算正確率

correct_predictions = tf.equal(tf.argmax(predictions, 1), tf.argmax(ys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))

5. 使用模型

with tf.Session() as sess:
 init = tf.global_variables_initializer()
 sess.run(init)
 for i in range(1000):
  batch_xs, batch_ys = mnist.train.next_batch(100)
  sess.run(train_step, feed_dict={
   xs: batch_xs,
   ys: batch_ys
  })
  if i % 50 == 0:
   print(sess.run(accuracy, feed_dict={
    xs: mnist.test.images,
    ys: mnist.test.labels
   }))

運(yùn)行結(jié)果

訓(xùn)練1000個(gè)循環(huán), 準(zhǔn)確率在87%左右.

Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
0.1041
0.632
0.7357
0.7837
0.7971
0.8147
0.8283
0.8376
0.8423
0.8501
0.8501
0.8533
0.8567
0.8597
0.8552
0.8647
0.8654
0.8701
0.8712
0.8712

以上這篇使用TensorFlow搭建一個(gè)全連接神經(jīng)網(wǎng)絡(luò)教程就是小編分享給大家的全部?jī)?nèi)容了，希望能給大家一個(gè)參考，也希望大家多多支持腳本之家。

您可能感興趣的文章: