Module `dimdrop.layers`

Source code

from .clustering_layer import ClusteringLayer

__all__ = [
    'ClusteringLayer'
]

Sub-modules

dimdrop.layers.clustering_layer: Clustering layer implementation by Chengwei Zhang: https://www.dlology.com/blog/how-to-do-unsupervised-clustering-with-keras/ …

Classes

class ClusteringLayer (n_clusters, weights=None, alpha=1.0, **kwargs)

Clustering layer converts input sample (feature) to soft label, i.e. a vector that represents the probability of the sample belonging to each cluster. The probability is calculated with student's t-distribution.

Example

    model.add(ClusteringLayer(n_clusters=10))

Parameters

n_clusters : int: number of clusters.
weights : list of Numpy array, shape (n_clusters,n_features), optional: Represents the initial cluster centers.
alpha : float, optional: degrees of freedom parameter in Student's t-distribution. Default to 1.0.

Input shape

2D tensor with shape: `(n_samples, n_features)`.

Output shape

2D tensor with shape: `(n_samples, n_clusters)`.

Source code

class ClusteringLayer(Layer):
    """
    Clustering layer converts input sample (feature) to soft label, i.e. a
    vector that represents the probability of the sample belonging to each
    cluster. The probability is calculated with student's t-distribution.

    Example
    -------
    ```
        model.add(ClusteringLayer(n_clusters=10))
    ```
    Parameters
    ----------
    n_clusters: int
        number of clusters.
    weights: list of Numpy array, shape `(n_clusters, n_features)`, optional
        Represents the initial cluster centers.
    alpha: float, optional
        degrees of freedom parameter in Student's t-distribution.
        Default to 1.0.

    Input shape
    -----------
        2D tensor with shape: `(n_samples, n_features)`.

    Output shape
    ------------
        2D tensor with shape: `(n_samples, n_clusters)`.
    """

    def __init__(self, n_clusters, weights=None, alpha=1.0, **kwargs):
        if 'input_shape' not in kwargs and 'input_dim' in kwargs:
            kwargs['input_shape'] = (kwargs.pop('input_dim'),)
        super(ClusteringLayer, self).__init__(**kwargs)
        self.n_clusters = n_clusters
        self.alpha = alpha
        self.initial_weights = weights
        self.input_spec = InputSpec(ndim=2)

    def build(self, input_shape):
        assert len(input_shape) == 2
        input_dim = input_shape[1]
        self.input_spec = InputSpec(dtype=K.floatx(), shape=(None, input_dim))
        self.clusters = self.add_weight(name='clusters', shape=(
            self.n_clusters, input_dim), initializer='glorot_uniform', )
        if self.initial_weights is not None:
            self.set_weights(self.initial_weights)
            del self.initial_weights
        self.built = True

    def call(self, inputs, **kwargs):
        """ student t-distribution, as same as used in t-SNE algorithm.
         Measure the similarity between embedded point z_i and centroid µ_j.
                 q_ij = 1/(1+dist(x_i, µ_j)^2), then normalize it.
                 q_ij can be interpreted as the probability of assigning
                 sample i to cluster j. (i.e., a soft assignment)

        Parameters
        -----------
        inputs: tensor of shape `(n_samples, n_features)`
            the variable containing data

        Returns
        -------
        q: tensor of shape `(n_samples, n_clusters)`
            student's t-distribution, or soft labels for each sample.
        """
        q = 1.0 / (1.0 + (K.sum(K.square(
            K.expand_dims(inputs, axis=1) - self.clusters
        ), axis=2) / self.alpha))
        q **= (self.alpha + 1.0) / 2.0
        # Make sure each sample's 10 values add up to 1.
        q = K.transpose(K.transpose(q) / K.sum(q, axis=1))
        return q

    def compute_output_shape(self, input_shape):
        assert input_shape and len(input_shape) == 2
        return input_shape[0], self.n_clusters

    def get_config(self):
        config = {'n_clusters': self.n_clusters}
        base_config = super(ClusteringLayer, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

Ancestors

keras.engine.base_layer.Layer

Methods

def build(self, input_shape)

Creates the layer weights.

Must be implemented on all layers that have weights.

Arguments

input_shape: Keras tensor (future input to layer)
    or list/tuple of Keras tensors to reference
    for weight shape computations.

Source code

def build(self, input_shape):
    assert len(input_shape) == 2
    input_dim = input_shape[1]
    self.input_spec = InputSpec(dtype=K.floatx(), shape=(None, input_dim))
    self.clusters = self.add_weight(name='clusters', shape=(
        self.n_clusters, input_dim), initializer='glorot_uniform', )
    if self.initial_weights is not None:
        self.set_weights(self.initial_weights)
        del self.initial_weights
    self.built = True

def call(self, inputs, **kwargs)

student t-distribution, as same as used in t-SNE algorithm. Measure the similarity between embedded point z_i and centroid µ_j. q_ij = 1/(1+dist(x_i, µ_j)^2), then normalize it. q_ij can be interpreted as the probability of assigning sample i to cluster j. (i.e., a soft assignment)

Parameters

inputs : tensor of shape (n_samples,n_features): the variable containing data

Returns

q : tensor of shape (n_samples,n_clusters): student's t-distribution, or soft labels for each sample.

Source code

def call(self, inputs, **kwargs):
    """ student t-distribution, as same as used in t-SNE algorithm.
     Measure the similarity between embedded point z_i and centroid µ_j.
             q_ij = 1/(1+dist(x_i, µ_j)^2), then normalize it.
             q_ij can be interpreted as the probability of assigning
             sample i to cluster j. (i.e., a soft assignment)

    Parameters
    -----------
    inputs: tensor of shape `(n_samples, n_features)`
        the variable containing data

    Returns
    -------
    q: tensor of shape `(n_samples, n_clusters)`
        student's t-distribution, or soft labels for each sample.
    """
    q = 1.0 / (1.0 + (K.sum(K.square(
        K.expand_dims(inputs, axis=1) - self.clusters
    ), axis=2) / self.alpha))
    q **= (self.alpha + 1.0) / 2.0
    # Make sure each sample's 10 values add up to 1.
    q = K.transpose(K.transpose(q) / K.sum(q, axis=1))
    return q

def compute_output_shape(self, input_shape)

Computes the output shape of the layer.

Assumes that the layer will be built to match that input shape provided.

Arguments

input_shape: Shape tuple (tuple of integers)
    or list of shape tuples (one per output tensor of the layer).
    Shape tuples can include None for free dimensions,
    instead of an integer.

Returns

An input shape tuple.

Source code

def compute_output_shape(self, input_shape):
    assert input_shape and len(input_shape) == 2
    return input_shape[0], self.n_clusters

def get_config(self)

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Returns

Python dictionary.

Source code

def get_config(self):
    config = {'n_clusters': self.n_clusters}
    base_config = super(ClusteringLayer, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))