Python object_detection.models.ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor() Examples

The following are 27 code examples of object_detection.models.ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module object_detection.models.ssd_mobilenet_v1_feature_extractor , or try the search function .
Example #1
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From BMW-TensorFlow-Training-GUI with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #2
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #3
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From g-tensorflow-models with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #4
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From MAX-Object-Detector with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #5
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, batch_norm_trainable=True):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      batch_norm_trainable: Whether to update batch norm parameters during
        training or not.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm) as sc:
      conv_hyperparams = sc
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams, batch_norm_trainable)
Example #6
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, batch_norm_trainable=True):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      batch_norm_trainable: Whether to update batch norm parameters during
        training or not.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm) as sc:
      conv_hyperparams = sc
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams, batch_norm_trainable)
Example #7
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From Elphas with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, batch_norm_trainable=True):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      batch_norm_trainable: Whether to update batch norm parameters during
        training or not.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm) as sc:
      conv_hyperparams = sc
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams, batch_norm_trainable)
Example #8
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From ros_tensorflow with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #9
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #10
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From Traffic-Rule-Violation-Detection-System with MIT License 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, batch_norm_trainable=True):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      batch_norm_trainable: Whether to update batch norm parameters during
        training or not.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm) as sc:
      conv_hyperparams = sc
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams, batch_norm_trainable)
Example #11
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, batch_norm_trainable=True):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      batch_norm_trainable: Whether to update batch norm parameters during
        training or not.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm) as sc:
      conv_hyperparams = sc
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams, batch_norm_trainable)
Example #12
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #13
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, batch_norm_trainable=True,
                                use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      batch_norm_trainable: Whether to update batch norm parameters during
        training or not.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm) as sc:
      conv_hyperparams = sc
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams, batch_norm_trainable=batch_norm_trainable,
        use_explicit_padding=use_explicit_padding)
Example #14
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From Person-Detection-and-Tracking with MIT License 6 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                is_training=True, use_explicit_padding=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      is_training: whether the network is in training mode.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)
Example #15
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From MBMD with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #16
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From object_detector_app with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #17
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From mtl-ssl with Apache License 2.0 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #18
Source File: ssd_mobilenet_v1_feature_extractor_tf1_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def _create_feature_extractor(self,
                                depth_multiplier,
                                pad_to_multiple,
                                use_explicit_padding=False,
                                num_layers=6,
                                is_training=False,
                                use_keras=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
      num_layers: number of SSD layers.
      is_training: whether the network is in training mode.
      use_keras: if True builds a keras-based feature extractor, if False builds
        a slim-based one.

    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    del use_keras
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        is_training,
        depth_multiplier,
        min_depth,
        pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding,
        num_layers=num_layers)
Example #19
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From garbage-object-detection-tensorflow with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #20
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From HereIsWally with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #21
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From Hands-On-Machine-Learning-with-OpenCV-4 with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #22
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #23
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From hands-detection with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #24
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From moveo_ros with MIT License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #25
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #26
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From tensorflow with BSD 2-Clause "Simplified" License 5 votes vote down vote up 
def _create_feature_extractor(self, depth_multiplier):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    conv_hyperparams = {}
    return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
        depth_multiplier, min_depth, conv_hyperparams)
Example #27
Source File: ssd_mobilenet_v1_feature_extractor_test.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 4 votes vote down vote up 
def _create_feature_extractor(self,
                                depth_multiplier,
                                pad_to_multiple,
                                use_explicit_padding=False,
                                num_layers=6,
                                is_training=False,
                                use_keras=False):
    """Constructs a new feature extractor.

    Args:
      depth_multiplier: float depth multiplier for feature extractor
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
      num_layers: number of SSD layers.
      is_training: whether the network is in training mode.
      use_keras: if True builds a keras-based feature extractor, if False builds
        a slim-based one.

    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    if use_keras:
      return (ssd_mobilenet_v1_keras_feature_extractor
              .SSDMobileNetV1KerasFeatureExtractor(
                  is_training=is_training,
                  depth_multiplier=depth_multiplier,
                  min_depth=min_depth,
                  pad_to_multiple=pad_to_multiple,
                  conv_hyperparams=self._build_conv_hyperparams(
                      add_batch_norm=False),
                  freeze_batchnorm=False,
                  inplace_batchnorm_update=False,
                  use_explicit_padding=use_explicit_padding,
                  num_layers=num_layers,
                  name='MobilenetV1'))
    else:
      return ssd_mobilenet_v1_feature_extractor.SSDMobileNetV1FeatureExtractor(
          is_training,
          depth_multiplier,
          min_depth,
          pad_to_multiple,
          self.conv_hyperparams_fn,
          use_explicit_padding=use_explicit_padding,
          num_layers=num_layers)