def _sample_kmc2_chain():
"""Returns previous centers as well as a new center sampled using k-MC2.
"""
# Extract the subset from the underlying batch.
start = i * self._kmc2_chain_length
end = start + self._kmc2_chain_length
subset = first_shard[start:end]
# Compute the distances from points in the subset to previous centers.
_, distances = gen_clustering_ops.nearest_neighbors(
subset, self._cluster_centers, 1)
# Sample index of new center using k-MC2 Markov chain.
new_center_index = gen_clustering_ops.kmc2_chain_initialization(
array_ops.squeeze(distances), self._random_seed)
# Extract actual new center.
newly_sampled_center = array_ops.reshape(
subset[new_center_index], [1, -1])
# Return concatenation with previously sampled centers.
if self._distance_metric == COSINE_DISTANCE:
newly_sampled_center = nn_impl.l2_normalize(
newly_sampled_center, dim=1)
return array_ops.concat(
[self._cluster_centers, newly_sampled_center], 0)
def _sample_kmc2_chain():
"""Returns previous centers as well as a new center sampled using k-MC2.
"""
# Extract the subset from the underlying batch.
start = i * self._kmc2_chain_length
end = start + self._kmc2_chain_length
subset = first_shard[start:end]
# Compute the distances from points in the subset to previous centers.
_, distances = gen_clustering_ops.nearest_neighbors(
subset, self._cluster_centers, 1)
# Sample index of new center using k-MC2 Markov chain.
new_center_index = gen_clustering_ops.kmc2_chain_initialization(
array_ops.squeeze(distances), self._random_seed)
# Extract actual new center.
newly_sampled_center = array_ops.reshape(subset[new_center_index],
[1, -1])
# Return concatenation with previously sampled centers.
if self._distance_metric == COSINE_DISTANCE:
newly_sampled_center = nn_impl.l2_normalize(
newly_sampled_center, dim=1)
return array_ops.concat([self._cluster_centers, newly_sampled_center],
0)
def _infer_graph(self, inputs, clusters):
"""Maps input to closest cluster and the score.
Args:
inputs: list of input Tensors.
clusters: Tensor of cluster centers.
Returns:
List of tuple, where each value in tuple corresponds to a value in inp.
The tuple has following three elements:
all_scores: distance of each input to each cluster center.
score: distance of each input to closest cluster center.
cluster_idx: index of cluster center closest to the corresponding input.
"""
assert isinstance(inputs, list)
# Pairwise distances are used only by transform(). In all other cases, this
# sub-graph is not evaluated.
scores = self._distance_graph(inputs, clusters, self._distance_metric)
output = []
if (self._distance_metric == COSINE_DISTANCE
and not self._clusters_l2_normalized()):
# The cosine distance between normalized vectors x and y is the same as
# 2 * squared_euclidean_distance. We are using this fact and reusing the
# nearest_neighbors op.
# TODO (ands): Support COSINE distance in nearest_neighbors and remove id:695
# https://github.com/imdone/tensorflow/issues/696
# this.
with ops.colocate_with(clusters, ignore_existing=True):
clusters = nn_impl.l2_normalize(clusters, dim=1)
for inp, score in zip(inputs, scores):
with ops.colocate_with(inp, ignore_existing=True):
(indices, distances) = gen_clustering_ops.nearest_neighbors(
inp, clusters, 1)
if self._distance_metric == COSINE_DISTANCE:
distances *= 0.5
output.append((score, array_ops.squeeze(distances, [-1]),
array_ops.squeeze(indices, [-1])))
return zip(*output)
def _infer_graph(self, inputs, clusters):
"""Maps input to closest cluster and the score.
Args:
inputs: list of input Tensors.
clusters: Tensor of cluster centers.
Returns:
List of tuple, where each value in tuple corresponds to a value in inp.
The tuple has following three elements:
all_scores: distance of each input to each cluster center.
score: distance of each input to closest cluster center.
cluster_idx: index of cluster center closest to the corresponding input.
"""
assert isinstance(inputs, list)
# Pairwise distances are used only by transform(). In all other cases, this
# sub-graph is not evaluated.
scores = self._distance_graph(inputs, clusters, self._distance_metric)
output = []
if (self._distance_metric == COSINE_DISTANCE and
not self._clusters_l2_normalized()):
# The cosine distance between normalized vectors x and y is the same as
# 2 * squared_euclidian_distance. We are using this fact and reusing the
# nearest_neighbors op.
# TODO(ands): Support COSINE distance in nearest_neighbors and remove
# this.
with ops.colocate_with(clusters):
clusters = nn_impl.l2_normalize(clusters, dim=1)
for inp, score in zip(inputs, scores):
with ops.colocate_with(inp):
(indices,
distances) = gen_clustering_ops.nearest_neighbors(inp, clusters, 1)
if self._distance_metric == COSINE_DISTANCE:
distances *= 0.5
output.append(
(score, array_ops.squeeze(distances), array_ops.squeeze(indices)))
return zip(*output)
