tensorflow基础模型之KMeans算法

tensorflow执行KMeans算法。

代码如下：

from __future__ import print_function

​

# Ignore all GPUs, tf random forest does not benefit from it.

import os

​

import numpy as np

import tensorflow as tf

from tensorflow.contrib.factorization import KMeans

​

os.environ["CUDA_VISIBLE_DEVICES"] = ""

​

# 导入MNIST数据

from tensorflow.examples.tutorials.mnist import input_data

​

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

full_data_x = mnist.train.images

​

# 参数

num_steps = 50 # 总训练步数

batch_size = 1024 # 批处理数量

k = 25 # 集群数

num_classes = 10 # 10类数字

num_features = 784 # 28*28=>784类特征

​

# 图像输入

X = tf.placeholder(tf.float32, shape=[None, num_features])

# 标签(分配一个标签给中心质点、测试)

Y = tf.placeholder(tf.float32, shape=[None, num_classes])

​

# K-Means 参数

kmeans = KMeans(inputs=X, num_clusters=k, distance_metric='cosine',

use_mini_batch=True)

​

# 建立 KMeans 图

training_graph = kmeans.training_graph()

​

if len(training_graph) > 6: # Tensorflow 1.4+

(all_scores, cluster_idx, scores, cluster_centers_initialized,

cluster_centers_var, init_op, train_op) = training_graph

else:

(all_scores, cluster_idx, scores, cluster_centers_initialized,

init_op, train_op) = training_graph

​

cluster_idx = cluster_idx[0] # fix for cluster_idx being a tuple

avg_distance = tf.reduce_mean(scores)

​

# 初始化参数

init_vars = tf.global_variables_initializer()

​

# 开启TensorFlow会话

sess = tf.Session(http://www.my516.com)

​

# 初始化

sess.run(init_vars, feed_dict={X: full_data_x})

sess.run(init_op, feed_dict={X: full_data_x})

​

# 训练

for i in range(1, num_steps + 1):

_, d, idx = sess.run([train_op, avg_distance, cluster_idx],

feed_dict={X: full_data_x})

if i % 10 == 0 or i == 1:

print("Step %i, Avg Distance: %f" % (i, d))

​

# 分配表前给每个质点

# 用每轮训练的到理它们最近的质点标签样本计算每个质点的总标签数('idx')

counts = np.zeros(shape=(k, num_classes))

for i in range(len(idx)):

counts[idx[i]] += mnist.train.labels[i]

# 分配频率最高的标签给质点

labels_map = [np.argmax(c) for c in counts]

labels_map = tf.convert_to_tensor(labels_map)

​

# 评估

# centroid_id -> label

cluster_label = tf.nn.embedding_lookup(labels_map, cluster_idx)

# 计算准确率

correct_prediction = tf.equal(cluster_label, tf.cast(tf.argmax(Y, 1), tf.int32))

accuracy_op = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

​

# 测试模型

test_x, test_y = mnist.test.images, mnist.test.labels

print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: test_x, Y: test_y}))

运行结果：

Step 1, Avg Distance: 0.341471

Step 10, Avg Distance: 0.221609

Step 20, Avg Distance: 0.220328

Step 30, Avg Distance: 0.219776

Step 40, Avg Distance: 0.219419

Step 50, Avg Distance: 0.219154

Test Accuracy: 0.7127

---------------------