def _init_clusters(self):
"""Initialization of clusters.
Returns:
Tuple with following elements:
cluster_centers: a Tensor for storing cluster centers
cluster_counts: a Tensor for storing counts of points assigned to this
cluster. This is used by mini-batch training.
"""
init = self._initial_clusters
if init == RANDOM_INIT:
clusters_init = self._init_clusters_random()
elif init == KMEANS_PLUS_PLUS_INIT:
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
clusters_init = gen_clustering_ops.kmeans_plus_plus_initialization(
self._inputs[0], self._num_clusters, self._random_seed,
self._kmeans_plus_plus_num_retries)
elif callable(init):
clusters_init = init(self._inputs, self._num_clusters)
elif not isinstance(init, str):
clusters_init = init
else:
assert False, 'Unsupported init passed to Kmeans %s' % str(init)
if self._distance_metric == COSINE_DISTANCE and clusters_init is not None:
clusters_init = nn_impl.l2_normalize(clusters_init, dim=1)
clusters_init = clusters_init if clusters_init is not None else []
cluster_centers = variables.Variable(
clusters_init, name='clusters', validate_shape=False)
cluster_counts = (variables.Variable(
array_ops.ones(
[self._num_clusters], dtype=dtypes.int64)) if self._use_mini_batch
else None)
return cluster_centers, cluster_counts
def _init_clusters(self):
"""Initialization of clusters.
Returns:
Tuple with following elements:
cluster_centers: a Tensor for storing cluster centers
cluster_counts: a Tensor for storing counts of points assigned to this
cluster. This is used by mini-batch training.
"""
init = self._initial_clusters
if init == RANDOM_INIT:
clusters_init = self._init_clusters_random()
elif init == KMEANS_PLUS_PLUS_INIT:
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
clusters_init = gen_clustering_ops.kmeans_plus_plus_initialization(
self._inputs[0], self._num_clusters, self._random_seed,
self._kmeans_plus_plus_num_retries)
elif callable(init):
clusters_init = init(self._inputs, self._num_clusters)
elif not isinstance(init, str):
clusters_init = init
else:
assert False, 'Unsupported init passed to Kmeans %s' % str(init)
if self._distance_metric == COSINE_DISTANCE and clusters_init is not None:
clusters_init = tf.nn.l2_normalize(clusters_init, dim=1)
clusters_init = clusters_init if clusters_init is not None else []
cluster_centers = tf.Variable(clusters_init,
name='clusters',
validate_shape=False)
cluster_counts = (tf.Variable(
tf.zeros([self._num_clusters], dtype=tf.int64))
if self._use_mini_batch else None)
return cluster_centers, cluster_counts
def _kmeans_plus_plus(self):
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
inp = self._inputs[0]
if self._distance_metric == COSINE_DISTANCE:
inp = nn_impl.l2_normalize(inp, dim=1)
return gen_clustering_ops.kmeans_plus_plus_initialization(
inp, math_ops.to_int64(self._num_remaining), self._random_seed,
self._kmeans_plus_plus_num_retries)
def _init_clusters(self):
"""Initialization of clusters.
Returns:
Tuple with following elements:
cluster_centers: a Tensor for storing cluster centers
cluster_counts: a Tensor for storing counts of points assigned to this
cluster. This is used by mini-batch training.
"""
init = self._initial_clusters
if init == RANDOM_INIT:
clusters_init = self._init_clusters_random()
elif init == KMEANS_PLUS_PLUS_INIT:
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
inp = self._inputs[0]
if self._distance_metric == COSINE_DISTANCE:
inp = nn_impl.l2_normalize(inp, dim=1)
clusters_init = gen_clustering_ops.kmeans_plus_plus_initialization(
inp, self._num_clusters, self._random_seed,
self._kmeans_plus_plus_num_retries)
elif callable(init):
clusters_init = init(self._inputs, self._num_clusters)
elif not isinstance(init, str):
clusters_init = init
else:
assert False, 'Unsupported init passed to Kmeans %s' % str(init)
if self._distance_metric == COSINE_DISTANCE and clusters_init is not None:
clusters_init = nn_impl.l2_normalize(clusters_init, dim=1)
clusters_init = clusters_init if clusters_init is not None else []
# TODO(agarwal): Locally cache cluster_centers on the worker to avoid
# copying them each step.
cluster_centers = variables.Variable(clusters_init,
name='clusters',
validate_shape=False)
if self._use_mini_batch and self._mini_batch_steps_per_iteration > 1:
# Copy of cluster centers actively updated each step according to
# mini-batch update rule.
cluster_centers_updated = variables.Variable(
clusters_init, name='clusters_updated', validate_shape=False)
# How many steps till we copy the updated clusters to cluster_centers.
update_in_steps = variables.Variable(
self._mini_batch_steps_per_iteration,
dtype=dtypes.int64,
name='update_in_steps')
# Count of points assigned to cluster_centers_updated.
cluster_counts = variables.Variable(
array_ops.zeros([self._num_clusters], dtype=dtypes.int64))
else:
cluster_centers_updated = cluster_centers
update_in_steps = None
cluster_counts = (variables.Variable(
array_ops.ones([self._num_clusters], dtype=dtypes.int64))
if self._use_mini_batch else None)
return (cluster_centers, cluster_counts, cluster_centers_updated,
update_in_steps)
def _init_clusters(self):
"""Initialization of clusters.
Returns:
Tuple with following elements:
cluster_centers: a Tensor for storing cluster centers
cluster_counts: a Tensor for storing counts of points assigned to this
cluster. This is used by mini-batch training.
"""
init = self._initial_clusters
if init == RANDOM_INIT:
clusters_init = self._init_clusters_random()
elif init == KMEANS_PLUS_PLUS_INIT:
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
inp = self._inputs[0]
if self._distance_metric == COSINE_DISTANCE:
inp = nn_impl.l2_normalize(inp, dim=1)
clusters_init = gen_clustering_ops.kmeans_plus_plus_initialization(
inp, self._num_clusters, self._random_seed,
self._kmeans_plus_plus_num_retries)
elif callable(init):
clusters_init = init(self._inputs, self._num_clusters)
elif not isinstance(init, str):
clusters_init = init
else:
assert False, 'Unsupported init passed to Kmeans %s' % str(init)
if self._distance_metric == COSINE_DISTANCE and clusters_init is not None:
clusters_init = nn_impl.l2_normalize(clusters_init, dim=1)
clusters_init = clusters_init if clusters_init is not None else []
# TODO(agarwal): Locally cache cluster_centers on the worker to avoid
# copying them each step.
cluster_centers = variables.Variable(clusters_init,
name='clusters',
validate_shape=False)
if self._use_mini_batch and self._mini_batch_steps_per_iteration > 1:
# Copy of cluster centers actively updated each step according to
# mini-batch update rule.
cluster_centers_updated = variables.Variable(clusters_init,
name='clusters_updated',
validate_shape=False)
# How many steps till we copy the updated clusters to cluster_centers.
update_in_steps = variables.Variable(self._mini_batch_steps_per_iteration,
dtype=dtypes.int64,
name='update_in_steps')
# Count of points assigned to cluster_centers_updated.
cluster_counts = variables.Variable(array_ops.zeros([self._num_clusters],
dtype=dtypes.int64))
else:
cluster_centers_updated = cluster_centers
update_in_steps = None
cluster_counts = (variables.Variable(array_ops.ones([self._num_clusters],
dtype=dtypes.int64))
if self._use_mini_batch else None)
return (cluster_centers, cluster_counts,
cluster_centers_updated, update_in_steps)
def _kmeans_plus_plus(self):
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
inp = self._inputs[0]
if self._distance_metric == COSINE_DISTANCE:
inp = nn_impl.l2_normalize(inp, dim=1)
return gen_clustering_ops.kmeans_plus_plus_initialization(
inp,
math_ops.to_int64(self._num_remaining), self._random_seed,
self._kmeans_plus_plus_num_retries)
def _initialize_clusters(self, cluster_centers,
cluster_centers_initialized,
cluster_centers_updated):
"""Returns an op to initialize the cluster centers."""
init = self._initial_clusters
if init == RANDOM_INIT:
clusters_init = self._init_clusters_random()
elif init == KMEANS_PLUS_PLUS_INIT:
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
inp = self._inputs[0]
if self._distance_metric == COSINE_DISTANCE:
inp = nn_impl.l2_normalize(inp, dim=1)
clusters_init = gen_clustering_ops.kmeans_plus_plus_initialization(
inp, self._num_clusters, self._random_seed,
self._kmeans_plus_plus_num_retries)
elif callable(init):
clusters_init = init(self._inputs, self._num_clusters)
elif not isinstance(init, str):
clusters_init = init
else:
assert False, 'Unsupported init passed to Kmeans %s' % str(init)
if self._distance_metric == COSINE_DISTANCE and clusters_init is not None:
clusters_init = nn_impl.l2_normalize(clusters_init, dim=1)
with ops.colocate_with(cluster_centers_initialized):
initialized = control_flow_ops.with_dependencies(
[clusters_init],
array_ops.identity(cluster_centers_initialized))
with ops.colocate_with(cluster_centers):
assign_centers = state_ops.assign(cluster_centers,
clusters_init,
validate_shape=False)
if cluster_centers_updated != cluster_centers:
assign_centers = control_flow_ops.group(
assign_centers,
state_ops.assign(cluster_centers_updated,
clusters_init,
validate_shape=False))
assign_centers = control_flow_ops.with_dependencies(
[assign_centers],
state_ops.assign(cluster_centers_initialized, True))
return control_flow_ops.cond(initialized, control_flow_ops.no_op,
lambda: assign_centers).op
def _initialize_clusters(self,
cluster_centers,
cluster_centers_initialized,
cluster_centers_updated):
"""Returns an op to initialize the cluster centers."""
init = self._initial_clusters
if init == RANDOM_INIT:
clusters_init = self._init_clusters_random()
elif init == KMEANS_PLUS_PLUS_INIT:
# Points from only the first shard are used for initializing centers.
# TODO(ands): Use all points.
inp = self._inputs[0]
if self._distance_metric == COSINE_DISTANCE:
inp = nn_impl.l2_normalize(inp, dim=1)
clusters_init = gen_clustering_ops.kmeans_plus_plus_initialization(
inp, self._num_clusters, self._random_seed,
self._kmeans_plus_plus_num_retries)
elif callable(init):
clusters_init = init(self._inputs, self._num_clusters)
elif not isinstance(init, str):
clusters_init = init
else:
assert False, 'Unsupported init passed to Kmeans %s' % str(init)
if self._distance_metric == COSINE_DISTANCE and clusters_init is not None:
clusters_init = nn_impl.l2_normalize(clusters_init, dim=1)
with ops.colocate_with(cluster_centers_initialized):
initialized = control_flow_ops.with_dependencies(
[clusters_init],
array_ops.identity(cluster_centers_initialized))
with ops.colocate_with(cluster_centers):
assign_centers = state_ops.assign(cluster_centers, clusters_init,
validate_shape=False)
if cluster_centers_updated != cluster_centers:
assign_centers = control_flow_ops.group(
assign_centers,
state_ops.assign(cluster_centers_updated, clusters_init,
validate_shape=False))
assign_centers = control_flow_ops.with_dependencies(
[assign_centers],
state_ops.assign(cluster_centers_initialized, True))
return control_flow_ops.cond(initialized,
control_flow_ops.no_op,
lambda: assign_centers).op
