TensorFlow——全连接神经网络识别手写数字（一）

1、MINIST

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

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

x = tf.placeholder(tf.float32, [None, 784])
y_actual = tf.placeholder(tf.float32, [None, 10])

# 初始化权值W
W = tf.Variable(tf.zeros([784, 10]))
# 初始化偏置项b
b = tf.Variable(tf.zeros([10]))
# 加权变换并进行softmax回归，得到预测概率
y_predict = tf.nn.softmax(tf.matmul(x, W) + b)

# 求交叉熵
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=y_actual, logits=y_predict)
# 用梯度下降法使得残差最小
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

# 在测试阶段，测试准确度计算
correct_prediction = tf.equal(tf.argmax(y_predict, 1), tf.argmax(y_actual, 1))
# 多个批次的准确度均值
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)
    for i in range(10000):
        batch_xs, batch_ys = mnist.train.next_batch(100)
        sess.run(train_step, feed_dict={x: batch_xs, y_actual: batch_ys})
        if i % 100 == 0:
            print("test_accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images, y_actual: mnist.test.labels}))

2、softmax

import tensorflow as tf

x = [[3., 1., -3.], [3., 1., -3.]]
y = tf.nn.softmax(x)
y2 = tf.nn.softmax(x, axis=0)
with tf.Session() as sess:
    print(x)
    print(sess.run(y))
    print(sess.run(y2))

最后

以上就是怕孤独音响为你收集整理的TensorFlow——全连接神经网络识别手写数字（一）的全部内容，希望文章能够帮你解决TensorFlow——全连接神经网络识别手写数字（一）所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。