本文整理汇总了Python中object_detection.models.ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor方法的典型用法代码示例。如果您正苦于以下问题：Python ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor方法的具体用法？Python ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor怎么用？Python ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor使用的例子？那么恭喜您, 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.ssd_inception_v2_feature_extractor的用法示例。
在下文中一共展示了ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor方法的4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: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_inception_v2_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_inception_v2_feature_extractor import SSDInceptionV2FeatureExtractor [as 别名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
is_training=True):
"""Constructs a SsdInceptionV2FeatureExtractor.
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.
Returns:
an ssd_inception_v2_feature_extractor.SsdInceptionV2FeatureExtractor.
"""
min_depth = 32
return ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
self.conv_hyperparams_fn,
override_base_feature_extractor_hyperparams=True) 开发者ID:ahmetozlu，项目名称:vehicle_counting_tensorflow，代码行数:20，代码来源:ssd_inception_v2_feature_extractor_test.py
示例2: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_inception_v2_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_inception_v2_feature_extractor import SSDInceptionV2FeatureExtractor [as 别名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
is_training=True, batch_norm_trainable=True):
"""Constructs a SsdInceptionV2FeatureExtractor.
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_inception_v2_feature_extractor.SsdInceptionV2FeatureExtractor.
"""
min_depth = 32
conv_hyperparams = {}
return ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
conv_hyperparams, batch_norm_trainable) 开发者ID:cagbal，项目名称:ros_people_object_detection_tensorflow，代码行数:21，代码来源:ssd_inception_v2_feature_extractor_test.py
示例3: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_inception_v2_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_inception_v2_feature_extractor import SSDInceptionV2FeatureExtractor [as 别名]
def _create_feature_extractor(self, depth_multiplier):
"""Constructs a SsdInceptionV2FeatureExtractor.
Args:
depth_multiplier: float depth multiplier for feature extractor
Returns:
an ssd_inception_v2_feature_extractor.SsdInceptionV2FeatureExtractor.
"""
min_depth = 32
conv_hyperparams = {}
return ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor(
depth_multiplier, min_depth, conv_hyperparams) 示例4: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_inception_v2_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_inception_v2_feature_extractor import SSDInceptionV2FeatureExtractor [as 别名]
def _create_feature_extractor(self,
depth_multiplier,
pad_to_multiple,
use_explicit_padding=False,
num_layers=6,
is_training=True):
"""Constructs a SsdInceptionV2FeatureExtractor.
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.
Returns:
an ssd_inception_v2_feature_extractor.SsdInceptionV2FeatureExtractor.
"""
min_depth = 32
return ssd_inception_v2_feature_extractor.SSDInceptionV2FeatureExtractor(
is_training,
depth_multiplier,
min_depth,
pad_to_multiple,
self.conv_hyperparams_fn,
num_layers=num_layers,
override_base_feature_extractor_hyperparams=True) 开发者ID:ShivangShekhar，项目名称:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代码行数:32，代码来源:ssd_inception_v2_feature_extractor_test.py