Python ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor方法代碼示例

本文整理匯總了Python中object_detection.models.ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor方法的典型用法代碼示例。如果您正苦於以下問題：Python ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor方法的具體用法？Python ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor怎麽用？Python ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類object_detection.models.ssd_mobilenet_v2_feature_extractor的用法示例。

在下文中一共展示了ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor方法的5個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_mobilenet_v2_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_mobilenet_v2_feature_extractor import SSDMobileNetV2FeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                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.
      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_v2_feature_extractor.SSDMobileNetV2FeatureExtractor(
        False,
        depth_multiplier,
        min_depth,
        pad_to_multiple,
        conv_hyperparams,
        use_explicit_padding=use_explicit_padding)

開發者ID:cagbal，項目名稱:ros_people_object_detection_tensorflow，代碼行數:26，代碼來源:ssd_mobilenet_v2_feature_extractor_test.py

示例2: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_mobilenet_v2_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_mobilenet_v2_feature_extractor import SSDMobileNetV2FeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                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.
      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_v2_feature_extractor.SSDMobileNetV2FeatureExtractor(
        False,
        depth_multiplier,
        min_depth,
        pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding)

開發者ID:ambakick，項目名稱:Person-Detection-and-Tracking，代碼行數:24，代碼來源:ssd_mobilenet_v2_feature_extractor_test.py

示例3: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_mobilenet_v2_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_mobilenet_v2_feature_extractor import SSDMobileNetV2FeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                use_explicit_padding=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.
      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_v2_keras_feature_extractor.
              SSDMobileNetV2KerasFeatureExtractor(
                  is_training=False,
                  depth_multiplier=depth_multiplier,
                  min_depth=min_depth,
                  pad_to_multiple=pad_to_multiple,
                  conv_hyperparams=self._build_conv_hyperparams(),
                  freeze_batchnorm=False,
                  inplace_batchnorm_update=False,
                  use_explicit_padding=use_explicit_padding,
                  name='MobilenetV2'))
    else:
      return ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor(
          False,
          depth_multiplier,
          min_depth,
          pad_to_multiple,
          self.conv_hyperparams_fn,
          use_explicit_padding=use_explicit_padding)

開發者ID:ahmetozlu，項目名稱:vehicle_counting_tensorflow，代碼行數:39，代碼來源:ssd_mobilenet_v2_feature_extractor_test.py

示例4: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_mobilenet_v2_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_mobilenet_v2_feature_extractor import SSDMobileNetV2FeatureExtractor [as 別名]
def _create_feature_extractor(self,
                                depth_multiplier,
                                pad_to_multiple,
                                use_explicit_padding=False,
                                num_layers=6):
    """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.
    Returns:
      an ssd_meta_arch.SSDFeatureExtractor object.
    """
    min_depth = 32
    return ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor(
        False,
        depth_multiplier,
        min_depth,
        pad_to_multiple,
        self.conv_hyperparams_fn,
        use_explicit_padding=use_explicit_padding,
        num_layers=num_layers)

開發者ID:tensorflow，項目名稱:models，代碼行數:29，代碼來源:ssd_mobilenet_v2_feature_extractor_tf1_test.py

示例5: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_mobilenet_v2_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_mobilenet_v2_feature_extractor import SSDMobileNetV2FeatureExtractor [as 別名]
def _create_feature_extractor(self,
                                depth_multiplier,
                                pad_to_multiple,
                                use_explicit_padding=False,
                                num_layers=6,
                                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.
      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_v2_keras_feature_extractor.
              SSDMobileNetV2KerasFeatureExtractor(
                  is_training=False,
                  depth_multiplier=depth_multiplier,
                  min_depth=min_depth,
                  pad_to_multiple=pad_to_multiple,
                  conv_hyperparams=self._build_conv_hyperparams(),
                  freeze_batchnorm=False,
                  inplace_batchnorm_update=False,
                  use_explicit_padding=use_explicit_padding,
                  num_layers=num_layers,
                  name='MobilenetV2'))
    else:
      return ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor(
          False,
          depth_multiplier,
          min_depth,
          pad_to_multiple,
          self.conv_hyperparams_fn,
          use_explicit_padding=use_explicit_padding,
          num_layers=num_layers)

開發者ID:ShivangShekhar，項目名稱:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代碼行數:46，代碼來源:ssd_mobilenet_v2_feature_extractor_test.py

注：本文中的object_detection.models.ssd_mobilenet_v2_feature_extractor.SSDMobileNetV2FeatureExtractor方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。