【TensorFlow】使用TensorFlow執行K-Means
阿新 • • 發佈:2019-02-04
import numpy as np
import tensorflow as tf
from tensorflow.contrib.factorization import KMeans
載入資料
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
Extracting /tmp/data/train-images-idx3-ubyte.gz Extracting /tmp/data/train-labels-idx1-ubyte.gz Extracting /tmp/data/t10k-images-idx3-ubyte.gz Extracting /tmp/data/t10k-labels-idx1-ubyte.gz
引數
num_features = 784 # 圖片尺寸為28*28=784
num_classes = 10 # 0~9共10個數字
k = 25
num_steps = 50 # 訓練執行的次數
batch_size = 1024
構建模型
X = tf.placeholder(tf.float32,shape=[None,num_features])
Y = tf.placeholder(tf.float32,shape=[None,num_classes])
kmeans = KMeans(inputs=X,num_clusters=k,distance_metric='cosine',use_mini_batch= True)
(all_scores, cluster_idx, scores, cluster_centers_initialized,
init_op,training_op) = kmeans.training_graph()
cluster_idx = cluster_idx[0]
avg_distance = tf.reduce_mean(scores)
init_vars = tf.global_variables_initializer()
訓練
sess = tf.Session()
sess.run(init_vars, feed_dict={X: full_data_x} )
sess.run(init_op, feed_dict={X: full_data_x})
for i in range(1,num_steps+1):
_,d,idx = sess.run([training_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))
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
評估
# k個簇中,各個型別的個數
# 例如counts[i][j]是第2個簇中第j個類別樣本的數量
counts = np.zeros(shape=(k,num_classes))
for i in range(len(idx)):
# idx是所有樣本所屬簇的id
counts[idx[i]] += mnist.train.labels[i]
# labels_map是一個len為25的list
# labels_map[i]表示第i簇中樣本應該屬於的類別
labels_map = [np.argmax(c) for c in counts]
labels_map = tf.convert_to_tensor(labels_map)
# 給定一個cluster_idx,返回這個cluster在樣本中對應的labels
cluster_label = tf.nn.embedding_lookup(labels_map, cluster_idx)
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))
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}))
Test Accuracy: 0.7127