Google I/O is a wrap! Catch up on TensorFlow sessions View sessions

tf.compat.v1.estimator.experimental.KMeans

View source on GitHub

An Estimator for K-Means clustering.

Inherits From: Estimator

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
)

Example:

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

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,

kmeans.cluster_centers()

is equivalent to

tf.train.load_variable(
    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.

    config

    model_dir

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

    Methods

    cluster_centers

    View source

    cluster_centers()

    Returns the cluster centers.

    eval_dir

    View source

    eval_dir(
    name=None
)

    Shows the directory name where evaluation metrics are dumped.

    Args
    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.

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

    evaluate

    View source

    evaluate(
    input_fn, steps=None, hooks=None, checkpoint_path=None, name=None
)

    Evaluates the model given evaluation data input_fn.

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

    Args
    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.

    Returns
    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.

    Raises
    ValueError If steps <= 0.

    experimental_export_all_saved_models

    View source

    experimental_export_all_saved_models(
    export_dir_base, input_receiver_fn_map, assets_extra=None, as_text=False,
    checkpoint_path=None
)

    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 tf.estimator.ModeKeys.PREDICT), such that up to three tf.MetaGraphDefs are saved with a single set of variables in a single SavedModel directory.

    For the variables and tf.MetaGraphDefs, a timestamped export directory below export_dir_base, and writes a SavedModel into it containing the tf.MetaGraphDef for the given mode and its associated signatures.

    For prediction, the exported MetaGraphDef will provide one SignatureDef for each element of the export_outputs dict returned from the model_fn, named using the same keys. One of these keys is always tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY, indicating which signature will be served when a serving request does not specify one. For each signature, the outputs are provided by the corresponding tf.estimator.export.ExportOutputs, and the inputs are always the input receivers provided by the serving_input_receiver_fn.

    For training and evaluation, the train_op is stored in an extra collection, and loss, metrics, and predictions are included in a SignatureDef for the mode in question.

    Extra assets may be written into the SavedModel via the assets_extra argument. This should be a dict, where each key gives a destination path (including the filename) relative to the assets.extra directory. The corresponding value gives the full path of the source file to be copied. For example, the simple case of copying a single file without renaming it is specified as {'my_asset_file.txt': '/path/to/my_asset_file.txt'}.

    Args
    export_dir_base A string containing a directory in which to create timestamped subdirectories containing exported SavedModels.
    input_receiver_fn_map dict of tf.estimator.ModeKeys to input_receiver_fn mappings, where the input_receiver_fn is a function that takes no arguments and returns the appropriate subclass of InputReceiver.
    assets_extra A dict specifying how to populate the assets.extra directory within the exported SavedModel, or None if no extra assets are needed.
    as_text whether to write the SavedModel proto in text format.
    checkpoint_path The checkpoint path to export. If None (the default), the most recent checkpoint found within the model directory is chosen.

    Returns
    The path to the exported directory as a bytes object.

    Raises
    ValueError if any input_receiver_fn is None, no export_outputs are provided, or no checkpoint can be found.

    export_saved_model

    View source

    export_saved_model(
    export_dir_base, serving_input_receiver_fn, assets_extra=None, as_text=False,
    checkpoint_path=None, experimental_mode=ModeKeys.PREDICT
)

    Exports inference graph as a SavedModel into the given dir.

    For a detailed guide, see Using SavedModel with Estimators.

    This method builds a new graph by first calling the serving_input_receiver_fn to obtain feature Tensors, and then calling this Estimator's model_fn to generate the model graph based on those features. It restores the given checkpoint (or, lacking that, the most recent checkpoint) into this graph in a fresh session. Finally it creates a timestamped export directory below the given export_dir_base, and writes a SavedModel into it containing a single tf.MetaGraphDef saved from this session.

    The exported MetaGraphDef will provide one SignatureDef for each element of the export_outputs dict returned from the model_fn, named using the same keys. One of these keys is always