Have a question? Connect with the community at the TensorFlow Forum Visit Forum


An Estimator for K-Means clustering.

Inherits From: Estimator


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):
  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

The SavedModel saved by the export_saved_model method does not include the cluster centers. However, the cluster centers may be retrieved by the latest checkpoint saved during training. Specifically,


is equivalent to

    kmeans.model_dir, KMeansClustering.CLUSTER_CENTERS_VAR_NAME)

num_clusters An integer tensor specifying the number of clusters. This argument is ignored if initial_clusters is a tensor or numpy array.
model_dir The directory to save the model results and log files.
initial_clusters Specifies how the initial cluster centers are chosen. One of the following: * a tensor or numpy array with the initial cluster centers. * a callable f(inputs, k) that selects and returns up to k centers from an input batch. f is free to return any number of centers from 0 to k. It will be invoked on successive input batches as necessary until all num_clusters centers are chosen.

  • KMeansClustering.RANDOM_INIT: Choose centers randomly from an input batch. If the batch size is less than num_clusters then the entire batch is chosen to be initial cluster centers and the remaining centers are chosen from successive input batches.
  • KMeansClustering.KMEANS_PLUS_PLUS_INIT: Use kmeans++ to choose centers from the first input batch. If the batch size is less than num_clusters, a TensorFlow runtime error occurs.
distance_metric The distance metric used for clustering. One of:
  • KMeansClustering.SQUARED_EUCLIDEAN_DISTANCE: Euclidean distance between vectors u and v is defined as \(||u - v||_2\) which is the square root of the sum of the absolute squares of the elements' difference.
  • KMeansClustering.COSINE_DISTANCE: Cosine distance between vectors u and v is defined as \(1 - (u . v) / (||u||_2 ||v||_2)\).
  • seed Python integer. Seed for PRNG used to initialize centers.
    use_mini_batch A boolean specifying whether to use the mini-batch k-means algorithm. See explanation above.
    mini_batch_steps_per_iteration The number of steps after which the updated cluster centers are synced back to a master copy. Used only if use_mini_batch=True. See explanation above.
    kmeans_plus_plus_num_retries For each point that is sampled during kmeans++ initialization, this parameter specifies the number of additional points to draw from the current distribution before selecting the best. If a negative value is specified, a heuristic is used to sample O(log(num_to_sample)) additional points. Used only if initial_clusters=KMeansClustering.KMEANS_PLUS_PLUS_INIT.
    relative_tolerance A relative tolerance of change in the loss between iterations. Stops learning if the loss changes less than this amount. This may not work correctly if use_mini_batch=True.
    config See tf.estimator.Estimator.
    feature_columns An optionable iterable containing all the feature columns used by the model. All items in the set should be feature column instances that can be passed to tf.feature_column.input_layer. If this is None, all features will be used.

    ValueError An invalid argument was passed to initial_clusters or distance_metric.



    model_fn Returns the model_fn which is bound to self.params.



    View source

    Returns the cluster centers.


    View source

    Shows the directory name where evaluation metrics are dumped.

    name Name of the evaluation if user needs to run multiple evaluations on different data sets, such as on training data vs test data. Metrics for different evaluations are saved in separate folders, and appear separately in tensorboard.

    A string which is the path of directory contains evaluation metrics.


    View source

    Evaluates the model given evaluation data input_fn.

    For each step, calls input_fn, which returns one batch of data. Evaluates until:

    input_fn A function that constructs the input data for evaluation. See Premade Estimators for more information. The function should construct and return one of the following:

    • A tf.data.Dataset object: Outputs of Dataset object must be a tuple (features, labels) with same constraints as below.
    • A tuple (features, labels): Where features is a tf.Tensor or a dictionary of string feature name to Tensor and labels is a Tensor or a dictionary of string label name to Tensor. Both features and labels are consumed by model_fn. They should satisfy the expectation of model_fn from inputs.
    steps Number of steps for which to evaluate model. If None, evaluates until input_fn raises an end-of-input exception.
    hooks List of tf.train.SessionRunHook subclass instances. Used for callbacks inside the evaluation call.
    checkpoint_path Path of a specific checkpoint to evaluate. If None, the latest checkpoint in model_dir is used. If there are no checkpoints in model_dir, evaluation is run with newly initialized Variables instead of ones restored from checkpoint.
    name Name of the evaluation if user needs to run multiple evaluations on different data sets, such as on training data vs test data. Metrics for different evaluations are saved in separate folders, and appear separately in tensorboard.

    A dict containing the evaluation metrics specified in model_fn keyed by name, as well as an entry global_step which contains the value of the global step for which this evaluation was performed. For canned estimators, the dict contains the loss (mean loss per mini-batch) and the average_loss (mean loss per sample). Canned classifiers also return the accuracy. Canned regressors also return the label/mean and the prediction/mean.

    ValueError If steps <= 0.


    View source

    Exports a SavedModel with tf.MetaGraphDefs for each requested mode.

    For each mode passed in via the input_receiver_fn_map, this method builds a new graph by calling the input_receiver_fn to obtain feature and label Tensors. Next, this method calls the Estimator's model_fn in the passed mode to generate the model graph based on those features and labels, and restores the given checkpoint (or, lacking that, the most recent checkpoint) into the graph. Only one of the modes is used for saving variables to the SavedModel (order of preference: tf.estimator.ModeKeys.TRAIN, tf.estimator.ModeKeys.EVAL, then