tenserflow实例之最近邻算法

下面是利用MNIST data做的一个最近邻分类

'''
A nearest neighbor learning algorithm example using TensorFlow library.
This example is using the MNIST database of handwritten digits
(http://yann.lecun.com/exdb/mnist/)
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''

from __future__ import print_function

import numpy as np
import tensorflow as tf

# 导入 MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./MNIST_data/", one_hot=True)

# 这里我们训练集选取5000,测试集选取200
Xtr, Ytr = mnist.train.next_batch(5000) #5000 for training (nn candidates)
Xte, Yte = mnist.test.next_batch(200) #200 for testing

# tf设置占位符
xtr = tf.placeholder("float", [None, 784])
xte = tf.placeholder("float", [784])

# 利用L1距离进行最近邻
# 计算 L1距离
distance = tf.reduce_sum(tf.abs(tf.add(xtr, tf.negative(xte))), reduction_indices=1)
# 预测: 取得距离最小的图片的指针
pred = tf.arg_min(distance, 0)

accuracy = 0.

# 初始化所有变量
init = tf.global_variables_initializer()

# 创建对话
with tf.Session() as sess:
    sess.run(init)

    # 循环测试数据
    for i in range(len(Xte)):
        # 得到最近邻
        nn_index = sess.run(pred, feed_dict={xtr: Xtr, xte: Xte[i, :]})
        # 读取最近邻的标签，比较与真实值是否一致
        print("Test", i, "Prediction:", np.argmax(Ytr[nn_index]), 
            "True Class:", np.argmax(Yte[i]))
        # 计算精确度
        if np.argmax(Ytr[nn_index]) == np.argmax(Yte[i]):
            accuracy += 1./len(Xte)
    print("Done!")
    print("Accuracy:", accuracy)

最后

以上就是单纯啤酒为你收集整理的tenserflow实例之最近邻算法的全部内容，希望文章能够帮你解决tenserflow实例之最近邻算法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。