Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor方法代碼示例

本文整理匯總了Python中object_detection.models.ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor方法的典型用法代碼示例。如果您正苦於以下問題：Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor方法的具體用法？Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor怎麽用？Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor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_resnet_v1_fpn_feature_extractor的用法示例。

在下文中一共展示了ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor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_resnet_v1_fpn_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet152V1FpnFeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                use_explicit_padding=False, min_depth=32,
                                use_keras=False):
    is_training = True
    if use_keras:
      return (ssd_resnet_v1_fpn_keras_feature_extractor.
              SSDResNet152V1FpnKerasFeatureExtractor(
                  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,
                  name='ResNet152V1_FPN'))
    else:
      return (
          ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor(
              is_training, depth_multiplier, min_depth, pad_to_multiple,
              self.conv_hyperparams_fn,
              use_explicit_padding=use_explicit_padding))

開發者ID:ShivangShekhar，項目名稱:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代碼行數:24，代碼來源:ssd_resnet_v1_fpn_feature_extractor_test.py

示例2: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet152V1FpnFeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                use_explicit_padding=False):
    min_depth = 32
    is_training = True
    return (
        ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor(
            is_training,
            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:14，代碼來源:ssd_resnet_v1_fpn_feature_extractor_test.py

示例3: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet152V1FpnFeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                use_explicit_padding=False):
    min_depth = 32
    conv_hyperparams = {}
    batch_norm_trainable = True
    is_training = True
    return (
        ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor(
            is_training, depth_multiplier, min_depth, pad_to_multiple,
            conv_hyperparams, batch_norm_trainable,
            use_explicit_padding=use_explicit_padding))

開發者ID:cagbal，項目名稱:ros_people_object_detection_tensorflow，代碼行數:13，代碼來源:ssd_resnet_v1_fpn_feature_extractor_test.py

示例4: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet152V1FpnFeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple):
    min_depth = 32
    conv_hyperparams = {}
    batch_norm_trainable = True
    is_training = True
    return (
        ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor(
            is_training, depth_multiplier, min_depth, pad_to_multiple,
            conv_hyperparams, batch_norm_trainable))

開發者ID:ShreyAmbesh，項目名稱:Traffic-Rule-Violation-Detection-System，代碼行數:11，代碼來源:ssd_resnet_v1_fpn_feature_extractor_test.py

示例5: _create_feature_extractor

# 需要導入模塊: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet152V1FpnFeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
                                use_explicit_padding=False, min_depth=32,
                                use_keras=False):
    is_training = True
    return (
        ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor(
            is_training, depth_multiplier, min_depth, pad_to_multiple,
            self.conv_hyperparams_fn,
            use_explicit_padding=use_explicit_padding))

開發者ID:tensorflow，項目名稱:models，代碼行數:11，代碼來源:ssd_resnet_v1_fpn_feature_extractor_tf1_test.py

注：本文中的object_detection.models.ssd_resnet_v1_fpn_feature_extractor.SSDResnet152V1FpnFeatureExtractor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。