本文整理汇总了Python中object_detection.models.feature_map_generators.multi_resolution_feature_maps方法的典型用法代码示例。如果您正苦于以下问题:Python feature_map_generators.multi_resolution_feature_maps方法的具体用法?Python feature_map_generators.multi_resolution_feature_maps怎么用?Python feature_map_generators.multi_resolution_feature_maps使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类object_detection.models.feature_map_generators
的用法示例。
在下文中一共展示了feature_map_generators.multi_resolution_feature_maps方法的12个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _build_feature_map_generator
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
def _build_feature_map_generator(self, feature_map_layout, use_keras,
pool_residual=False):
if use_keras:
return feature_map_generators.KerasMultiResolutionFeatureMaps(
feature_map_layout=feature_map_layout,
depth_multiplier=1,
min_depth=32,
insert_1x1_conv=True,
freeze_batchnorm=False,
is_training=True,
conv_hyperparams=self._build_conv_hyperparams(),
name='FeatureMaps'
)
else:
def feature_map_generator(image_features):
return feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=feature_map_layout,
depth_multiplier=1,
min_depth=32,
insert_1x1_conv=True,
image_features=image_features,
pool_residual=pool_residual)
return feature_map_generator
示例2: test_get_expected_feature_map_shapes_with_inception_v2
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
def test_get_expected_feature_map_shapes_with_inception_v2(self):
image_features = {
'Mixed_3c': tf.random_uniform([4, 28, 28, 256], dtype=tf.float32),
'Mixed_4c': tf.random_uniform([4, 14, 14, 576], dtype=tf.float32),
'Mixed_5c': tf.random_uniform([4, 7, 7, 1024], dtype=tf.float32)
}
feature_maps = feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=INCEPTION_V2_LAYOUT,
depth_multiplier=1,
min_depth=32,
insert_1x1_conv=True,
image_features=image_features)
expected_feature_map_shapes = {
'Mixed_3c': (4, 28, 28, 256),
'Mixed_4c': (4, 14, 14, 576),
'Mixed_5c': (4, 7, 7, 1024),
'Mixed_5c_2_Conv2d_3_3x3_s2_512': (4, 4, 4, 512),
'Mixed_5c_2_Conv2d_4_3x3_s2_256': (4, 2, 2, 256),
'Mixed_5c_2_Conv2d_5_3x3_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)
示例3: test_get_expected_feature_map_shapes_with_inception_v3
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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)
示例4: extract_features
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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': ['Conv2d_11_pointwise', 'Conv2d_13_pointwise', '', '',
'', ''],
'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('MobilenetV1',
reuse=self._reuse_weights) as scope:
_, image_features = mobilenet_v1.mobilenet_v1_base(
preprocessed_inputs,
final_endpoint='Conv2d_13_pointwise',
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()
示例5: extract_features
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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(
preprocessed_inputs,
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()
示例6: test_get_expected_feature_map_shapes_with_inception_v2
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
def test_get_expected_feature_map_shapes_with_inception_v2(self):
image_features = {
'Mixed_3c': tf.random_uniform([4, 28, 28, 256], dtype=tf.float32),
'Mixed_4c': tf.random_uniform([4, 14, 14, 576], dtype=tf.float32),
'Mixed_5c': tf.random_uniform([4, 7, 7, 1024], dtype=tf.float32)
}
feature_maps = feature_map_generators.multi_resolution_feature_maps(
feature_map_layout=INCEPTION_V2_LAYOUT,
depth_multiplier=1,
min_depth=32,
insert_1x1_conv=True,
image_features=image_features)
expected_feature_map_shapes = {
'Mixed_3c': (4, 28, 28, 256),
'Mixed_4c': (4, 14, 14, 576),
'Mixed_5c': (4, 7, 7, 1024),
'Mixed_5c_2_Conv2d_3_3x3_s2_512': (4, 4, 4, 512),
'Mixed_5c_2_Conv2d_4_3x3_s2_256': (4, 2, 2, 256),
'Mixed_5c_2_Conv2d_5_3x3_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.iteritems())
self.assertDictEqual(out_feature_map_shapes, expected_feature_map_shapes)
示例7: test_get_expected_feature_map_shapes_with_inception_v3
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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.iteritems())
self.assertDictEqual(out_feature_map_shapes, expected_feature_map_shapes)
示例8: extract_features
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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()
示例9: test_get_expected_feature_map_shapes_with_embedded_ssd_mobilenet_v1
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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)
开发者ID:cagbal,项目名称:ros_people_object_detection_tensorflow,代码行数:32,代码来源:feature_map_generators_test.py
示例10: extract_features
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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):
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()
开发者ID:cagbal,项目名称:ros_people_object_detection_tensorflow,代码行数:40,代码来源:ssd_inception_v2_feature_extractor.py
示例11: extract_features
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''],
'layer_depth': [-1, -1, -1, 512, 256, 128],
'use_explicit_padding': self._use_explicit_padding,
'use_depthwise': self._use_depthwise,
}
with slim.arg_scope(self._conv_hyperparams):
with tf.variable_scope('InceptionV3', reuse=self._reuse_weights) as scope:
_, image_features = inception_v3.inception_v3_base(
ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
final_endpoint='Mixed_7c',
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()
开发者ID:cagbal,项目名称:ros_people_object_detection_tensorflow,代码行数:39,代码来源:ssd_inception_v3_feature_extractor.py
示例12: extract_features
# 需要导入模块: from object_detection.models import feature_map_generators [as 别名]
# 或者: from object_detection.models.feature_map_generators import multi_resolution_feature_maps [as 别名]
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_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''],
'layer_depth': [-1, -1, -1, 512, 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('InceptionV3', reuse=self._reuse_weights) as scope:
_, image_features = inception_v3.inception_v3_base(
ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
final_endpoint='Mixed_7c',
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()
开发者ID:ambakick,项目名称:Person-Detection-and-Tracking,代码行数:39,代码来源:ssd_inception_v3_feature_extractor.py