def testTrainableTrueIsTrainingFalse(self):
embeddings = image_embedding.inception_resnet_v2(self._images,
trainable=True,
is_training=False)
self.assertEqual([self._batch_size, 2048],
embeddings.get_shape().as_list())
self._verifyParameterCounts()
self._assertCollectionSize(376, tf.GraphKeys.GLOBAL_VARIABLES)
self._assertCollectionSize(188, tf.GraphKeys.TRAINABLE_VARIABLES)
self._assertCollectionSize(0, tf.GraphKeys.UPDATE_OPS)
self._assertCollectionSize(94, tf.GraphKeys.REGULARIZATION_LOSSES)
self._assertCollectionSize(0, tf.GraphKeys.LOSSES)
self._assertCollectionSize(23, tf.GraphKeys.SUMMARIES)
def build_image_embeddings(self):
"""Builds the image model subgraph and generates image embeddings.
Inputs:
self.images
Outputs:
self.image_embeddings
"""
if self.config.cnn_model == "InceptionV4":
inception_output = image_embedding.inception_v4(
self.images,
trainable=self.train_inception,
is_training=self.is_training())
self.inception_variables = tf.get_collection(
tf.GraphKeys.GLOBAL_VARIABLES, scope="InceptionV4")
elif self.config.cnn_model == "InceptionResnetV2":
inception_output = image_embedding.inception_resnet_v2(
self.images,
trainable=self.train_inception,
is_training=self.is_training())
self.inception_variables = tf.get_collection(
tf.GraphKeys.GLOBAL_VARIABLES, scope="InceptionResnetV2")
else:
inception_output = image_embedding.inception_v3(
self.images,
trainable=self.train_inception,
is_training=self.is_training())
self.inception_variables = tf.get_collection(
tf.GraphKeys.GLOBAL_VARIABLES, scope="InceptionV3")
# Map inception output into embedding space.
with tf.variable_scope("image_embedding") as scope:
image_embeddings = tf.contrib.layers.fully_connected(
inputs=inception_output,
num_outputs=self.config.embedding_size,
activation_fn=None,
weights_initializer=self.initializer,
biases_initializer=None,
scope=scope)
# Save the embedding size in the graph.
tf.constant(self.config.embedding_size, name="embedding_size")
self.image_embeddings = image_embeddings