def main(unused_argv):
# Model definition.
g = ops.Graph()
with g.as_default():
images = array_ops.placeholder(
dtypes.float32, shape=(1, None, None, 3), name='input_image')
inception.inception_resnet_v2_base(images)
graph_io.write_graph(g.as_graph_def(), cmd_args.graph_dir,
cmd_args.graph_filename)
def testBuildAndCheckAllEndPointsUptoPreAuxLogitsWithOutputStrideEight(
self):
batch_size = 5
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_resnet_v2_base(
inputs, final_endpoint='PreAuxLogits', output_stride=8)
endpoints_shapes = {
'Conv2d_1a_3x3': [5, 149, 149, 32],
'Conv2d_2a_3x3': [5, 147, 147, 32],
'Conv2d_2b_3x3': [5, 147, 147, 64],
'MaxPool_3a_3x3': [5, 73, 73, 64],
'Conv2d_3b_1x1': [5, 73, 73, 80],
'Conv2d_4a_3x3': [5, 71, 71, 192],
'MaxPool_5a_3x3': [5, 35, 35, 192],
'Mixed_5b': [5, 35, 35, 320],
'Mixed_6a': [5, 33, 33, 1088],
'PreAuxLogits': [5, 33, 33, 1088]
}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(
end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def testBuildAndCheckAllEndPointsUptoPreAuxLogitsWithAlignedFeatureMaps(
self):
batch_size = 5
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_resnet_v2_base(
inputs, final_endpoint='PreAuxLogits', align_feature_maps=True)
endpoints_shapes = {
'Conv2d_1a_3x3': [5, 150, 150, 32],
'Conv2d_2a_3x3': [5, 150, 150, 32],
'Conv2d_2b_3x3': [5, 150, 150, 64],
'MaxPool_3a_3x3': [5, 75, 75, 64],
'Conv2d_3b_1x1': [5, 75, 75, 80],
'Conv2d_4a_3x3': [5, 75, 75, 192],
'MaxPool_5a_3x3': [5, 38, 38, 192],
'Mixed_5b': [5, 38, 38, 320],
'Mixed_6a': [5, 19, 19, 1088],
'PreAuxLogits': [5, 19, 19, 1088]
}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(
end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def testBuildAndCheckAllEndPointsUptoPreAuxLogitsWithOutputStrideEight(self):
batch_size = 5
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_resnet_v2_base(
inputs, final_endpoint='PreAuxLogits', output_stride=8)
endpoints_shapes = {'Conv2d_1a_3x3': [5, 149, 149, 32],
'Conv2d_2a_3x3': [5, 147, 147, 32],
'Conv2d_2b_3x3': [5, 147, 147, 64],
'MaxPool_3a_3x3': [5, 73, 73, 64],
'Conv2d_3b_1x1': [5, 73, 73, 80],
'Conv2d_4a_3x3': [5, 71, 71, 192],
'MaxPool_5a_3x3': [5, 35, 35, 192],
'Mixed_5b': [5, 35, 35, 320],
'Mixed_6a': [5, 33, 33, 1088],
'PreAuxLogits': [5, 33, 33, 1088]
}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def testBuildAndCheckAllEndPointsUptoPreAuxLogitsWithAlignedFeatureMaps(self):
batch_size = 5
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_resnet_v2_base(
inputs, final_endpoint='PreAuxLogits', align_feature_maps=True)
endpoints_shapes = {'Conv2d_1a_3x3': [5, 150, 150, 32],
'Conv2d_2a_3x3': [5, 150, 150, 32],
'Conv2d_2b_3x3': [5, 150, 150, 64],
'MaxPool_3a_3x3': [5, 75, 75, 64],
'Conv2d_3b_1x1': [5, 75, 75, 80],
'Conv2d_4a_3x3': [5, 75, 75, 192],
'MaxPool_5a_3x3': [5, 38, 38, 192],
'Mixed_5b': [5, 38, 38, 320],
'Mixed_6a': [5, 19, 19, 1088],
'PreAuxLogits': [5, 19, 19, 1088]
}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def __call__(self, image_input, training=False, keep_prob=1.0):
"""
Runs the CNN producing the embeddings and the gradients.
:param image_input: Image input to produce embeddings for. [batch_size, image_size, image_size, 1]
:param training: A flag indicating training or evaluation
:param keep_prob: A tf placeholder of type tf.float32 indicating the amount of dropout applied
:return: Embeddings of size [batch_size, 2048]
"""
weight_decay = FLAGS.weight_decay
activation_fn = tf.nn.relu
end_points = {}
with slim.arg_scope(
inception.inception_resnet_v2_arg_scope(
weight_decay=FLAGS.weight_decay)):
with tf.variable_scope("", reuse=self.reuse):
with tf.variable_scope(None, 'InceptionResnetV2',
[image_input]) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=training):
net, end_points = inception.inception_resnet_v2_base(
image_input,
scope=scope,
activation_fn=activation_fn)
feature_map = end_points['PreAuxLogits']
self.reuse = True
return feature_map
def testBuildBaseNetwork(self):
batch_size = 5
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = inception.inception_resnet_v2_base(inputs)
self.assertTrue(net.op.name.startswith('InceptionResnetV2/Conv2d_7b_1x1'))
self.assertListEqual(net.get_shape().as_list(),
[batch_size, 8, 8, 1536])
expected_endpoints = ['Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3',
'MaxPool_5a_3x3', 'Mixed_5b', 'Mixed_6a',
'PreAuxLogits', 'Mixed_7a', 'Conv2d_7b_1x1']
self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildOnlyUptoFinalEndpoint(self):
batch_size = 5
height, width = 299, 299
endpoints = ['Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3',
'MaxPool_5a_3x3', 'Mixed_5b', 'Mixed_6a',
'PreAuxLogits', 'Mixed_7a', 'Conv2d_7b_1x1']
for index, endpoint in enumerate(endpoints):
with tf.Graph().as_default():
inputs = tf.random_uniform((batch_size, height, width, 3))
out_tensor, end_points = inception.inception_resnet_v2_base(
inputs, final_endpoint=endpoint)
if endpoint != 'PreAuxLogits':
self.assertTrue(out_tensor.op.name.startswith(
'InceptionResnetV2/' + endpoint))
self.assertItemsEqual(endpoints[:index+1], end_points.keys())
def _construct_model(model_type='resnet_v1_50'):
"""Constructs model for the desired type of CNN.
Args:
model_type: Type of model to be used.
Returns:
end_points: A dictionary from components of the network to the corresponding
activations.
Raises:
ValueError: If the model_type is not supported.
"""
# Placeholder input.
images = array_ops.placeholder(
dtypes.float32, shape=(1, None, None, 3), name=_INPUT_NODE)
# Construct model.
if model_type == 'inception_resnet_v2':
_, end_points = inception.inception_resnet_v2_base(images)
elif model_type == 'inception_resnet_v2-same':
_, end_points = inception.inception_resnet_v2_base(
images, align_feature_maps=True)
elif model_type == 'inception_v2':
_, end_points = inception.inception_v2_base(images)
elif model_type == 'inception_v2-no-separable-conv':
_, end_points = inception.inception_v2_base(
images, use_separable_conv=False)
elif model_type == 'inception_v3':
_, end_points = inception.inception_v3_base(images)
elif model_type == 'inception_v4':
_, end_points = inception.inception_v4_base(images)
elif model_type == 'alexnet_v2':
_, end_points = alexnet.alexnet_v2(images)
elif model_type == 'vgg_a':
_, end_points = vgg.vgg_a(images)
elif model_type == 'vgg_16':
_, end_points = vgg.vgg_16(images)
elif model_type == 'mobilenet_v1':
_, end_points = mobilenet_v1.mobilenet_v1_base(images)
elif model_type == 'mobilenet_v1_075':
_, end_points = mobilenet_v1.mobilenet_v1_base(
images, depth_multiplier=0.75)
elif model_type == 'resnet_v1_50':
_, end_points = resnet_v1.resnet_v1_50(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v1_101':
_, end_points = resnet_v1.resnet_v1_101(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v1_152':
_, end_points = resnet_v1.resnet_v1_152(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v1_200':
_, end_points = resnet_v1.resnet_v1_200(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v2_50':
_, end_points = resnet_v2.resnet_v2_50(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v2_101':
_, end_points = resnet_v2.resnet_v2_101(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v2_152':
_, end_points = resnet_v2.resnet_v2_152(
images, num_classes=None, is_training=False, global_pool=False)
elif model_type == 'resnet_v2_200':
_, end_points = resnet_v2.resnet_v2_200(
images, num_classes=None, is_training=False, global_pool=False)
else:
raise ValueError('Unsupported model_type %s.' % model_type)
return end_points
def _construct_model(model_type='resnet_v1_50'):
"""Constructs model for the desired type of CNN.
Args:
model_type: Type of model to be used.
Returns:
end_points: A dictionary from components of the network to the corresponding
activations.
Raises:
ValueError: If the model_type is not supported.
"""
# Placeholder input.
images = array_ops.placeholder(dtypes.float32,
shape=(1, None, None, 3),
name=_INPUT_NODE)
# Construct model.
if model_type == 'inception_resnet_v2':
_, end_points = inception.inception_resnet_v2_base(images)
elif model_type == 'inception_resnet_v2-same':
_, end_points = inception.inception_resnet_v2_base(
images, align_feature_maps=True)
elif model_type == 'inception_v2':
_, end_points = inception.inception_v2_base(images)
elif model_type == 'inception_v2-no-separable-conv':
_, end_points = inception.inception_v2_base(images,
use_separable_conv=False)
elif model_type == 'inception_v3':
_, end_points = inception.inception_v3_base(images)
elif model_type == 'inception_v4':
_, end_points = inception.inception_v4_base(images)
elif model_type == 'alexnet_v2':
_, end_points = alexnet.alexnet_v2(images)
elif model_type == 'vgg_a':
_, end_points = vgg.vgg_a(images)
elif model_type == 'vgg_16':
_, end_points = vgg.vgg_16(images)
elif model_type == 'mobilenet_v1':
_, end_points = mobilenet_v1.mobilenet_v1_base(images)
elif model_type == 'mobilenet_v1_075':
_, end_points = mobilenet_v1.mobilenet_v1_base(images,
depth_multiplier=0.75)
elif model_type == 'resnet_v1_50':
_, end_points = resnet_v1.resnet_v1_50(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v1_101':
_, end_points = resnet_v1.resnet_v1_101(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v1_152':
_, end_points = resnet_v1.resnet_v1_152(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v1_200':
_, end_points = resnet_v1.resnet_v1_200(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v2_50':
_, end_points = resnet_v2.resnet_v2_50(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v2_101':
_, end_points = resnet_v2.resnet_v2_101(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v2_152':
_, end_points = resnet_v2.resnet_v2_152(images,
num_classes=None,
is_training=False,
global_pool=False)
elif model_type == 'resnet_v2_200':
_, end_points = resnet_v2.resnet_v2_200(images,
num_classes=None,
is_training=False,
global_pool=False)
else:
raise ValueError('Unsupported model_type %s.' % model_type)
return end_points
else:
with slim.arg_scope(arg_scope):
slim_args = [slim.batch_norm, slim.dropout]
with slim.arg_scope(slim_args, is_training=False):
with tf.variable_scope(base_network, reuse=None) as scope:
if base_network == 'InceptionV3':
net, _ = inception.inception_v3_base(
images, final_endpoint=endpoint, scope=scope)
elif base_network == 'InceptionV3SE':
net, _ = inception.inception_v3_se_base(
images, final_endpoint=endpoint, scope=scope)
elif base_network == 'InceptionV4':
net, _ = inception.inception_v4_base(
images, final_endpoint=endpoint, scope=scope)
elif base_network == 'InceptionResnetV2':
net, _ = inception.inception_resnet_v2_base(
images, final_endpoint=endpoint, scope=scope)
elif base_network == 'InceptionResnetV2SE':
net, _ = inception.inception_resnet_v2_se_base(
images, final_endpoint=endpoint, scope=scope)
net = tf.reduce_mean(net, [0,1,2])
variable_averages = tf.train.ExponentialMovingAverage(
moving_average_decay, tf_global_step)
variables_to_restore = variable_averages.variables_to_restore()
init_fn = slim.assign_from_checkpoint_fn(
checkpoints_path, variables_to_restore)
config_sess = tf.ConfigProto(allow_soft_placement=True)
config_sess.gpu_options.allow_growth = True
with tf.Session(config=config_sess) as sess:
init_fn(sess)