def _extract_proposal_features(self, preprocessed_inputs, scope):
"""Extracts first stage RPN features.
Extracts features using the first half of the Inception Resnet v2 network.
We construct the network in `align_feature_maps=True` mode, which means
that all VALID paddings in the network are changed to SAME padding so that
the feature maps are aligned.
Args:
preprocessed_inputs: A [batch, height, width, channels] float32 tensor
representing a batch of images.
scope: A scope name.
Returns:
rpn_feature_map: A tensor with shape [batch, height, width, depth]
Raises:
InvalidArgumentError: If the spatial size of `preprocessed_inputs`
(height or width) is less than 33.
ValueError: If the created network is missing the required activation.
"""
if len(preprocessed_inputs.get_shape().as_list()) != 4:
raise ValueError('`preprocessed_inputs` must be 4 dimensional, got a '
'tensor of shape %s' % preprocessed_inputs.get_shape())
with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope(
weight_decay=self._weight_decay)):
# Forces is_training to False to disable batch norm update.
with slim.arg_scope([slim.batch_norm],
is_training=self._train_batch_norm):
with tf.variable_scope('InceptionResnetV2',
reuse=self._reuse_weights) as scope:
return inception_resnet_v2.inception_resnet_v2_base(
preprocessed_inputs, final_endpoint='PreAuxLogits',
scope=scope, output_stride=self._first_stage_features_stride,
align_feature_maps=True)
def _extract_proposal_features(self, preprocessed_inputs, scope):
"""Extracts first stage RPN features.
Extracts features using the first half of the Inception Resnet v2 network.
We construct the network in `align_feature_maps=True` mode, which means
that all VALID paddings in the network are changed to SAME padding so that
the feature maps are aligned.
Args:
preprocessed_inputs: A [batch, height, width, channels] float32 tensor
representing a batch of images.
scope: A scope name.
Returns:
rpn_feature_map: A tensor with shape [batch, height, width, depth]
Raises:
InvalidArgumentError: If the spatial size of `preprocessed_inputs`
(height or width) is less than 33.
ValueError: If the created network is missing the required activation.
"""
if len(preprocessed_inputs.get_shape().as_list()) != 4:
raise ValueError('`preprocessed_inputs` must be 4 dimensional, got a '
'tensor of shape %s' % preprocessed_inputs.get_shape())
with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope(
weight_decay=self._weight_decay)):
# Forces is_training to False to disable batch norm update.
with slim.arg_scope([slim.batch_norm],
is_training=self._train_batch_norm):
with tf.variable_scope('InceptionResnetV2',
reuse=self._reuse_weights) as scope:
return inception_resnet_v2.inception_resnet_v2_base(
preprocessed_inputs, final_endpoint='PreAuxLogits',
scope=scope, output_stride=self._first_stage_features_stride,
align_feature_maps=True)
def inception_v3(images,
trainable=True,
is_training=True,
weight_decay=0.00004,
stddev=0.1,
dropout_keep_prob=0.8,
use_batch_norm=True,
batch_norm_params=None,
add_summaries=True,
scope="InceptionResnetV2"):
"""Builds an Inception V3 subgraph for image embeddings.
Args:
images: A float32 Tensor of shape [batch, height, width, channels].
trainable: Whether the inception submodel should be trainable or not.
is_training: Boolean indicating training mode or not.
weight_decay: Coefficient for weight regularization.
stddev: The standard deviation of the trunctated normal weight initializer.
dropout_keep_prob: Dropout keep probability.
use_batch_norm: Whether to use batch normalization.
batch_norm_params: Parameters for batch normalization. See
tf.contrib.layers.batch_norm for details.
add_summaries: Whether to add activation summaries.
scope: Optional Variable scope.
Returns:
end_points: A dictionary of activations from inception_v3 layers.
"""
# Only consider the inception model to be in training mode if it's trainable.
is_inception_model_training = trainable and is_training
if use_batch_norm:
# Default parameters for batch normalization.
if not batch_norm_params:
batch_norm_params = {
"is_training": is_inception_model_training,
"trainable": trainable,
# Decay for the moving averages.
"decay": 0.9997,
# Epsilon to prevent 0s in variance.
"epsilon": 0.001,
# Collection containing the moving mean and moving variance.
"variables_collections": {
"beta": None,
"gamma": None,
"moving_mean": ["moving_vars"],
"moving_variance": ["moving_vars"],
}
}
else:
batch_norm_params = None
if trainable:
weights_regularizer = tf.contrib.layers.l2_regularizer(weight_decay)
else:
weights_regularizer = None
with tf.variable_scope(scope, "InceptionResnetV2", [images]) as scope:
with slim.arg_scope(
[slim.conv2d, slim.fully_connected],
weights_regularizer=weights_regularizer,
trainable=trainable):
with slim.arg_scope(
[slim.conv2d],
weights_initializer=tf.truncated_normal_initializer(stddev=stddev),
activation_fn=tf.nn.relu,
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params):
net, end_points = inception_resnet_v2.inception_resnet_v2_base(images, scope=scope)
with tf.variable_scope("logits"):
shape = net.get_shape()
net = slim.avg_pool2d(net, shape[1:3], padding="VALID", scope="pool")
net = slim.dropout(
net,
keep_prob=dropout_keep_prob,
is_training=is_inception_model_training,
scope="dropout")
net = slim.flatten(net, scope="flatten")
# Add summaries.
if add_summaries:
for v in end_points.values():
tf.contrib.layers.summaries.summarize_activation(v)
return net
def inception_v3(images,
trainable=True,
is_training=True,
weight_decay=0.00004,
stddev=0.1,
dropout_keep_prob=0.8,
use_batch_norm=True,
batch_norm_params=None,
add_summaries=True,
scope="InceptionResnetV2"):
"""Builds an Inception V3 subgraph for image embeddings.
Args:
images: A float32 Tensor of shape [batch, height, width, channels].
trainable: Whether the inception submodel should be trainable or not.
is_training: Boolean indicating training mode or not.
weight_decay: Coefficient for weight regularization.
stddev: The standard deviation of the trunctated normal weight initializer.
dropout_keep_prob: Dropout keep probability.
use_batch_norm: Whether to use batch normalization.
batch_norm_params: Parameters for batch normalization. See
tf.contrib.layers.batch_norm for details.
add_summaries: Whether to add activation summaries.
scope: Optional Variable scope.
Returns:
end_points: A dictionary of activations from inception_v3 layers.
"""
# Only consider the inception model to be in training mode if it's trainable.
is_inception_model_training = trainable and is_training
if use_batch_norm:
# Default parameters for batch normalization.
if not batch_norm_params:
batch_norm_params = {
"is_training": is_inception_model_training,
"trainable": trainable,
# Decay for the moving averages.
"decay": 0.9997,
# Epsilon to prevent 0s in variance.
"epsilon": 0.001,
# Collection containing the moving mean and moving variance.
"variables_collections": {
"beta": None,
"gamma": None,
"moving_mean": ["moving_vars"],
"moving_variance": ["moving_vars"],
}
}
else:
batch_norm_params = None
if trainable:
weights_regularizer = tf.contrib.layers.l2_regularizer(weight_decay)
else:
weights_regularizer = None
with tf.variable_scope(scope, "InceptionResnetV2", [images]) as scope:
with slim.arg_scope([slim.conv2d, slim.fully_connected],
weights_regularizer=weights_regularizer,
trainable=trainable):
with slim.arg_scope(
[slim.conv2d],
weights_initializer=tf.truncated_normal_initializer(
stddev=stddev),
activation_fn=tf.nn.relu,
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params):
net, end_points = inception_resnet_v2.inception_resnet_v2_base(
images, scope=scope)
with tf.variable_scope("logits"):
shape = net.get_shape()
net = slim.avg_pool2d(net,
shape[1:3],
padding="VALID",
scope="pool")
net = slim.dropout(net,
keep_prob=dropout_keep_prob,
is_training=is_inception_model_training,
scope="dropout")
net = slim.flatten(net, scope="flatten")
# Add summaries.
if add_summaries:
for v in end_points.values():
tf.contrib.layers.summaries.summarize_activation(v)
return net
