本文整理汇总了Python中object_detection.models.ssd_resnet_v1_fpn_feature_extractor.SSDResnet101V1FpnFeatureExtractor方法的典型用法代码示例。如果您正苦于以下问题：Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet101V1FpnFeatureExtractor方法的具体用法？Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet101V1FpnFeatureExtractor怎么用？Python ssd_resnet_v1_fpn_feature_extractor.SSDResnet101V1FpnFeatureExtractor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_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.SSDResnet101V1FpnFeatureExtractor方法的6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_resnet_v1_fpn_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet101V1FpnFeatureExtractor [as 别名]
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.
SSDResNet101V1FpnKerasFeatureExtractor(
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='ResNet101V1_FPN'))
else:
return (
ssd_resnet_v1_fpn_feature_extractor.SSDResnet101V1FpnFeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
self.conv_hyperparams_fn,
use_explicit_padding=use_explicit_padding)) 开发者ID:ShivangShekhar，项目名称:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代码行数:24，代码来源:ssd_resnet_v1_fpn_feature_extractor_test.py
示例2: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet101V1FpnFeatureExtractor [as 别名]
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.SSDResnet101V1FpnFeatureExtractor(
is_training,
depth_multiplier,
min_depth,
pad_to_multiple,
self.conv_hyperparams_fn,
use_explicit_padding=use_explicit_padding)) 开发者ID:ahmetozlu，项目名称:vehicle_counting_tensorflow，代码行数:14，代码来源:ssd_resnet_v1_fpn_feature_extractor_test.py
示例3: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet101V1FpnFeatureExtractor [as 别名]
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.SSDResnet101V1FpnFeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
conv_hyperparams, batch_norm_trainable,
use_explicit_padding=use_explicit_padding)) 开发者ID:cagbal，项目名称:ros_people_object_detection_tensorflow，代码行数:13，代码来源:ssd_resnet_v1_fpn_feature_extractor_test.py
示例4: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet101V1FpnFeatureExtractor [as 别名]
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.SSDResnet101V1FpnFeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
conv_hyperparams, batch_norm_trainable)) 开发者ID:ShreyAmbesh，项目名称:Traffic-Rule-Violation-Detection-System，代码行数:11，代码来源:ssd_resnet_v1_fpn_feature_extractor_test.py
示例5: test_create_ssd_fpn_model_from_config
# 需要导入模块: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet101V1FpnFeatureExtractor [as 别名]
def test_create_ssd_fpn_model_from_config(self):
model_proto = self.create_default_ssd_model_proto()
model_proto.ssd.feature_extractor.type = 'ssd_resnet101_v1_fpn'
model_proto.ssd.feature_extractor.fpn.min_level = 3
model_proto.ssd.feature_extractor.fpn.max_level = 7
model = model_builder.build(model_proto, is_training=True)
self.assertIsInstance(model._feature_extractor,
ssd_resnet_v1_fpn.SSDResnet101V1FpnFeatureExtractor)
self.assertEqual(model._feature_extractor._fpn_min_level, 3)
self.assertEqual(model._feature_extractor._fpn_max_level, 7) 开发者ID:ShivangShekhar，项目名称:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代码行数:12，代码来源:model_builder_test.py
示例6: _create_feature_extractor
# 需要导入模块: from object_detection.models import ssd_resnet_v1_fpn_feature_extractor [as 别名]
# 或者: from object_detection.models.ssd_resnet_v1_fpn_feature_extractor import SSDResnet101V1FpnFeatureExtractor [as 别名]
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.SSDResnet101V1FpnFeatureExtractor(
is_training, depth_multiplier, min_depth, pad_to_multiple,
self.conv_hyperparams_fn,
use_explicit_padding=use_explicit_padding))