def testModelHasExpectedNumberOfParameters(self):
batch_size = 5
height, width = 224, 224
inputs = random_ops.random_uniform((batch_size, height, width, 3))
with arg_scope(inception_v2.inception_v2_arg_scope()):
inception_v2.inception_v2_base(inputs)
total_params, _ = model_analyzer.analyze_vars(
variables_lib.get_model_variables())
self.assertAlmostEqual(10173112, total_params)
def testBuildAndCheckAllEndPointsUptoMixed5c(self):
batch_size = 5
height, width = 224, 224
inputs = random_ops.random_uniform((batch_size, height, width, 3))
_, end_points = inception_v2.inception_v2_base(
inputs, final_endpoint='Mixed_5c')
endpoints_shapes = {
'Mixed_3b': [batch_size, 28, 28, 256],
'Mixed_3c': [batch_size, 28, 28, 320],
'Mixed_4a': [batch_size, 14, 14, 576],
'Mixed_4b': [batch_size, 14, 14, 576],
'Mixed_4c': [batch_size, 14, 14, 576],
'Mixed_4d': [batch_size, 14, 14, 576],
'Mixed_4e': [batch_size, 14, 14, 576],
'Mixed_5a': [batch_size, 7, 7, 1024],
'Mixed_5b': [batch_size, 7, 7, 1024],
'Mixed_5c': [batch_size, 7, 7, 1024],
'Conv2d_1a_7x7': [batch_size, 112, 112, 64],
'MaxPool_2a_3x3': [batch_size, 56, 56, 64],
'Conv2d_2b_1x1': [batch_size, 56, 56, 64],
'Conv2d_2c_3x3': [batch_size, 56, 56, 192],
'MaxPool_3a_3x3': [batch_size, 28, 28, 192]
}
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 testBuildBaseNetwork(self):
batch_size = 5
height, width = 224, 224
inputs = random_ops.random_uniform((batch_size, height, width, 3))
mixed_5c, end_points = inception_v2.inception_v2_base(inputs)
self.assertTrue(mixed_5c.op.name.startswith('InceptionV2/Mixed_5c'))
self.assertListEqual(mixed_5c.get_shape().as_list(),
[batch_size, 7, 7, 1024])
expected_endpoints = [
'Mixed_3b', 'Mixed_3c', 'Mixed_4a', 'Mixed_4b', 'Mixed_4c',
'Mixed_4d', 'Mixed_4e', 'Mixed_5a', 'Mixed_5b', 'Mixed_5c',
'Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3'
]
self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildOnlyUptoFinalEndpoint(self):
batch_size = 5
height, width = 224, 224
endpoints = [
'Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
'Mixed_4a', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e',
'Mixed_5a', 'Mixed_5b', 'Mixed_5c'
]
for index, endpoint in enumerate(endpoints):
with ops.Graph().as_default():
inputs = random_ops.random_uniform(
(batch_size, height, width, 3))
out_tensor, end_points = inception_v2.inception_v2_base(
inputs, final_endpoint=endpoint)
self.assertTrue(
out_tensor.op.name.startswith('InceptionV2/' + endpoint))
self.assertItemsEqual(endpoints[:index + 1], end_points)
def extract_features(self, preprocessed_inputs):
"""Extract features from preprocessed inputs.
Args:
preprocessed_inputs: a [batch, height, width, channels] float tensor
representing a batch of images.
Returns:
feature_maps: a list of tensors where the ith tensor has shape
[batch, height_i, width_i, depth_i]
"""
preprocessed_inputs.get_shape().assert_has_rank(4)
shape_assert = tf.Assert(
tf.logical_and(
tf.greater_equal(tf.shape(preprocessed_inputs)[1], 33),
tf.greater_equal(tf.shape(preprocessed_inputs)[2], 33)),
['image size must at least be 33 in both height and width.'])
feature_map_layout = {
'from_layer': ['Mixed_4c', 'Mixed_5c', '', '', '', ''],
'layer_depth': [-1, -1, 512, 256, 256, 128],
}
with tf.control_dependencies([shape_assert]):
with slim.arg_scope(self._conv_hyperparams):
with tf.variable_scope('InceptionV2',
reuse=self._reuse_weights) as scope:
_, image_features = inception_v2.inception_v2_base(
ops.pad_to_multiple(preprocessed_inputs,
self._pad_to_multiple),
final_endpoint='Mixed_5c',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
scope=scope)
feature_maps = feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=feature_map_layout,
depth_multiplier=self._depth_multiplier,
min_depth=self._min_depth,
insert_1x1_conv=True,
image_features=image_features)
return feature_maps.values()
def _CNN(inputs):
'''
The second part of the network (CNN) and the group module, are used to extract
the final view descriptors together with the discrimination scores, separately.
'''
final_view_descriptors = []
n_views = inputs.get_shape().as_list()[1]
# transpose views: (NxVxHxWxC) -> (VxNxHxWxC)
views = tf.transpose(inputs, perm=[1, 0, 2, 3, 4])
for i in range(n_views):
batch_view = tf.gather(views, i) # N x H x W x C
net, end_points = \
inception_v2.inception_v2_base(batch_view, scope=None)
final_view_descriptors.append(net)
return final_view_descriptors
def _extract_proposal_features(self, preprocessed_inputs, scope):
"""Extracts first stage RPN features.
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]
activations: A dictionary mapping feature extractor tensor names to
tensors
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.
"""
preprocessed_inputs.get_shape().assert_has_rank(4)
shape_assert = tf.Assert(
tf.logical_and(
tf.greater_equal(tf.shape(preprocessed_inputs)[1], 33),
tf.greater_equal(tf.shape(preprocessed_inputs)[2], 33)),
['image size must at least be 33 in both height and width.'])
with tf.control_dependencies([shape_assert]):
with tf.variable_scope('InceptionV2',
reuse=self._reuse_weights) as scope:
with _batch_norm_arg_scope(
[slim.conv2d, slim.separable_conv2d],
batch_norm_scale=True,
train_batch_norm=self._train_batch_norm):
_, activations = inception_v2.inception_v2_base(
preprocessed_inputs,
final_endpoint='Mixed_4e',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
scope=scope)
return activations['Mixed_4e'], activations
def extract_features(self, preprocessed_inputs):
"""Extract features from preprocessed inputs.
Args:
preprocessed_inputs: a [batch, height, width, channels] float tensor
representing a batch of images.
Returns:
feature_maps: a list of tensors where the ith tensor has shape
[batch, height_i, width_i, depth_i]
"""
preprocessed_inputs = shape_utils.check_min_image_dim(
33, preprocessed_inputs)
feature_map_layout = {
'from_layer': ['Mixed_4c', 'Mixed_5c', '', '', '', ''],
'layer_depth': [-1, -1, 512, 256, 256, 128],
'use_explicit_padding': self._use_explicit_padding,
'use_depthwise': self._use_depthwise,
}
with slim.arg_scope(self._conv_hyperparams_fn()):
with tf.variable_scope('InceptionV2',
reuse=self._reuse_weights) as scope:
_, image_features = inception_v2.inception_v2_base(
ops.pad_to_multiple(preprocessed_inputs,
self._pad_to_multiple),
final_endpoint='Mixed_5c',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
scope=scope)
feature_maps = feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=feature_map_layout,
depth_multiplier=self._depth_multiplier,
min_depth=self._min_depth,
insert_1x1_conv=True,
image_features=image_features)
return feature_maps.values()
