def test_get_expected_feature_map_shapes_with_embedded_ssd_mobilenet_v1(
self):
image_features = {
'Conv2d_11_pointwise': tf.random_uniform([4, 16, 16, 512],
dtype=tf.float32),
'Conv2d_13_pointwise': tf.random_uniform([4, 8, 8, 1024],
dtype=tf.float32),
}
feature_maps = feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=EMBEDDED_SSD_MOBILENET_V1_LAYOUT,
depth_multiplier=1,
min_depth=32,
insert_1x1_conv=True,
image_features=image_features)
expected_feature_map_shapes = {
'Conv2d_11_pointwise': (4, 16, 16, 512),
'Conv2d_13_pointwise': (4, 8, 8, 1024),
'Conv2d_13_pointwise_2_Conv2d_2_3x3_s2_512': (4, 4, 4, 512),
'Conv2d_13_pointwise_2_Conv2d_3_3x3_s2_256': (4, 2, 2, 256),
'Conv2d_13_pointwise_2_Conv2d_4_2x2_s2_256': (4, 1, 1, 256)}
init_op = tf.global_variables_initializer()
with self.test_session() as sess:
sess.run(init_op)
out_feature_maps = sess.run(feature_maps)
out_feature_map_shapes = dict(
(key, value.shape) for key, value in out_feature_maps.items())
self.assertDictEqual(out_feature_map_shapes, expected_feature_map_shapes)
def test_get_expected_feature_map_shapes_with_inception_v3(self):
image_features = {
'Mixed_5d': tf.random_uniform([4, 35, 35, 256], dtype=tf.float32),
'Mixed_6e': tf.random_uniform([4, 17, 17, 576], dtype=tf.float32),
'Mixed_7c': tf.random_uniform([4, 8, 8, 1024], dtype=tf.float32)
}
feature_maps = feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=INCEPTION_V3_LAYOUT,
depth_multiplier=1,
min_depth=32,
insert_1x1_conv=True,
image_features=image_features)
expected_feature_map_shapes = {
'Mixed_5d': (4, 35, 35, 256),
'Mixed_6e': (4, 17, 17, 576),
'Mixed_7c': (4, 8, 8, 1024),
'Mixed_7c_2_Conv2d_3_3x3_s2_512': (4, 4, 4, 512),
'Mixed_7c_2_Conv2d_4_3x3_s2_256': (4, 2, 2, 256),
'Mixed_7c_2_Conv2d_5_3x3_s2_128': (4, 1, 1, 128)}
init_op = tf.global_variables_initializer()
with self.test_session() as sess:
sess.run(init_op)
out_feature_maps = sess.run(feature_maps)
out_feature_map_shapes = dict(
(key, value.shape) for key, value in out_feature_maps.items())
self.assertDictEqual(out_feature_map_shapes, expected_feature_map_shapes)
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':
['layer_15/expansion_output', 'layer_19', '', '', '', ''],
'layer_depth': [-1, -1, 512, 256, 256, 128],
'use_depthwise': self._use_depthwise,
'use_explicit_padding': self._use_explicit_padding,
}
with tf.variable_scope('MobilenetV2',
reuse=self._reuse_weights) as scope:
with slim.arg_scope(
mobilenet_v2.training_scope(is_training=None, bn_decay=0.9997)), \
slim.arg_scope(
[mobilenet.depth_multiplier], min_depth=self._min_depth):
with (slim.arg_scope(self._conv_hyperparams_fn())
if self._override_base_feature_extractor_hyperparams else
context_manager.IdentityContextManager()):
_, image_features = mobilenet_v2.mobilenet_base(
ops.pad_to_multiple(preprocessed_inputs,
self._pad_to_multiple),
final_endpoint='layer_19',
depth_multiplier=self._depth_multiplier,
use_explicit_padding=self._use_explicit_padding,
scope=scope)
with slim.arg_scope(self._conv_hyperparams_fn()):
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 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()
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]
Raises:
ValueError: if image height or width are not 256 pixels.
"""
image_shape = preprocessed_inputs.get_shape()
image_shape.assert_has_rank(4)
image_height = image_shape[1].value
image_width = image_shape[2].value
if image_height is None or image_width is None:
shape_assert = tf.Assert(
tf.logical_and(tf.equal(tf.shape(preprocessed_inputs)[1], 256),
tf.equal(tf.shape(preprocessed_inputs)[2],
256)),
['image size must be 256 in both height and width.'])
with tf.control_dependencies([shape_assert]):
preprocessed_inputs = tf.identity(preprocessed_inputs)
elif image_height != 256 or image_width != 256:
raise ValueError(
'image size must be = 256 in both height and width;'
' image dim = %d,%d' % (image_height, image_width))
feature_map_layout = {
'from_layer':
['Conv2d_11_pointwise', 'Conv2d_13_pointwise', '', '', ''],
'layer_depth': [-1, -1, 512, 256, 256],
'conv_kernel_size': [-1, -1, 3, 3, 2],
'use_explicit_padding':
self._use_explicit_padding,
'use_depthwise':
self._use_depthwise,
}
with tf.variable_scope('MobilenetV1',
reuse=self._reuse_weights) as scope:
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(is_training=None)):
with (slim.arg_scope(self._conv_hyperparams_fn())
if self._override_base_feature_extractor_hyperparams else
context_manager.IdentityContextManager()):
_, image_features = mobilenet_v1.mobilenet_v1_base(
ops.pad_to_multiple(preprocessed_inputs,
self._pad_to_multiple),
final_endpoint='Conv2d_13_pointwise',
min_depth=self._min_depth,
depth_multiplier=self._depth_multiplier,
use_explicit_padding=self._use_explicit_padding,
scope=scope)
with slim.arg_scope(self._conv_hyperparams_fn()):
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()