Python tf.compat.v1.estimator.experimental.KMeans用法及代码示例

K-Means 聚类的估计器。

警告：不建议将估算器用于新代码。估算器运行 v1.Session 风格的代码，这更难以正确编写，并且可能会出现意外行为，尤其是与 TF 2 代码结合使用时。估算器确实属于我们的 compatibility guarantees ，但除了安全漏洞之外不会收到任何修复。有关详细信息，请参阅migration guide。

继承自： Estimator

用法

tf.compat.v1.estimator.experimental.KMeans(
    num_clusters, model_dir=None, initial_clusters=RANDOM_INIT,
    distance_metric=SQUARED_EUCLIDEAN_DISTANCE, seed=None, use_mini_batch=True,
    mini_batch_steps_per_iteration=1, kmeans_plus_plus_num_retries=2,
    relative_tolerance=None, config=None, feature_columns=None
)

例子：

import numpy as np
import tensorflow as tf

num_points = 100
dimensions = 2
points = np.random.uniform(0, 1000, [num_points, dimensions])

def input_fn():
  return tf.compat.v1.train.limit_epochs(
      tf.convert_to_tensor(points, dtype=tf.float32), num_epochs=1)

num_clusters = 5
kmeans = tf.compat.v1.estimator.experimental.KMeans(
    num_clusters=num_clusters, use_mini_batch=False)

# train
num_iterations = 10
previous_centers = None
for _ in xrange(num_iterations):
  kmeans.train(input_fn)
  cluster_centers = kmeans.cluster_centers()
  if previous_centers is not None:
    print 'delta:', cluster_centers - previous_centers
  previous_centers = cluster_centers
  print 'score:', kmeans.score(input_fn)
print 'cluster centers:', cluster_centers

# map the input points to their clusters
cluster_indices = list(kmeans.predict_cluster_index(input_fn))
for i, point in enumerate(points):
  cluster_index = cluster_indices[i]
  center = cluster_centers[cluster_index]
  print 'point:', point, 'is in cluster', cluster_index, 'centered at', center

export_saved_model方法保存的SavedModel不包括聚类中心。但是，可以通过训练期间保存的最新检查点来检索聚类中心。具体来说，

kmeans.cluster_centers()

相当于

tf.train.load_variable(
    kmeans.model_dir, KMeansClustering.CLUSTER_CENTERS_VAR_NAME)