本文整理匯總了Python中object_detection.models.ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor方法的典型用法代碼示例。如果您正苦於以下問題：Python ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor方法的具體用法？Python ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor怎麽用？Python ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor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_inception_v3_feature_extractor的用法示例。
在下文中一共展示了ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor方法的3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_inception_v3_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_inception_v3_feature_extractor import SSDInceptionV3FeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
is_training=True):
"""Constructs a SsdInceptionV3FeatureExtractor.
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_v3_feature_extractor.SsdInceptionV3FeatureExtractor.
"""
min_depth = 32
return ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
self.conv_hyperparams_fn,
override_base_feature_extractor_hyperparams=True) 開發者ID:ahmetozlu，項目名稱:vehicle_counting_tensorflow，代碼行數:20，代碼來源:ssd_inception_v3_feature_extractor_test.py
示例2: _create_feature_extractor
# 需要導入模塊: from object_detection.models import ssd_inception_v3_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_inception_v3_feature_extractor import SSDInceptionV3FeatureExtractor [as 別名]
def _create_feature_extractor(self, depth_multiplier, pad_to_multiple,
is_training=True, batch_norm_trainable=True):
"""Constructs a SsdInceptionV3FeatureExtractor.
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_v3_feature_extractor.SsdInceptionV3FeatureExtractor.
"""
min_depth = 32
conv_hyperparams = {}
return ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
conv_hyperparams, batch_norm_trainable) 開發者ID:cagbal，項目名稱:ros_people_object_detection_tensorflow，代碼行數:21，代碼來源:ssd_inception_v3_feature_extractor_test.py
示例3: _create_feature_extractor
# 需要導入模塊: from object_detection.models import ssd_inception_v3_feature_extractor [as 別名]
# 或者: from object_detection.models.ssd_inception_v3_feature_extractor import SSDInceptionV3FeatureExtractor [as 別名]
def _create_feature_extractor(self,
depth_multiplier,
pad_to_multiple,
use_explicit_padding=False,
num_layers=6,
is_training=True):
"""Constructs a SsdInceptionV3FeatureExtractor.
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_v3_feature_extractor.SsdInceptionV3FeatureExtractor.
"""
min_depth = 32
return ssd_inception_v3_feature_extractor.SSDInceptionV3FeatureExtractor(
is_training,
depth_multiplier,
min_depth,
pad_to_multiple,
self.conv_hyperparams_fn,
num_layers=num_layers,
override_base_feature_extractor_hyperparams=True) 開發者ID:ShivangShekhar，項目名稱:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代碼行數:32，代碼來源:ssd_inception_v3_feature_extractor_test.py