当前位置: 首页>>代码示例>>Python>>正文


Python inception_v3.inception_v3_base方法代码示例

本文整理汇总了Python中nets.inception_v3.inception_v3_base方法的典型用法代码示例。如果您正苦于以下问题:Python inception_v3.inception_v3_base方法的具体用法?Python inception_v3.inception_v3_base怎么用?Python inception_v3.inception_v3_base使用的例子?那么, 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nets.inception_v3的用法示例。


在下文中一共展示了inception_v3.inception_v3_base方法的5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: extract_features

# 需要导入模块: from nets import inception_v3 [as 别名]
# 或者: from nets.inception_v3 import inception_v3_base [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['Mixed_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''],
        'layer_depth': [-1, -1, -1, 512, 256, 128],
        'use_explicit_padding': self._use_explicit_padding,
        'use_depthwise': self._use_depthwise,
    }

    with slim.arg_scope(self._conv_hyperparams_fn()):
      with tf.variable_scope('InceptionV3', reuse=self._reuse_weights) as scope:
        _, image_features = inception_v3.inception_v3_base(
            ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
            final_endpoint='Mixed_7c',
            min_depth=self._min_depth,
            depth_multiplier=self._depth_multiplier,
            scope=scope)
        feature_maps = feature_map_generators.multi_resolution_feature_maps(
            feature_map_layout=feature_map_layout,
            depth_multiplier=self._depth_multiplier,
            min_depth=self._min_depth,
            insert_1x1_conv=True,
            image_features=image_features)

    return feature_maps.values() 
开发者ID:ahmetozlu,项目名称:vehicle_counting_tensorflow,代码行数:39,代码来源:ssd_inception_v3_feature_extractor.py

示例2: extract_features

# 需要导入模块: from nets import inception_v3 [as 别名]
# 或者: from nets.inception_v3 import inception_v3_base [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['Mixed_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''],
        'layer_depth': [-1, -1, -1, 512, 256, 128],
        'use_explicit_padding': self._use_explicit_padding,
        'use_depthwise': self._use_depthwise,
    }

    with slim.arg_scope(self._conv_hyperparams):
      with tf.variable_scope('InceptionV3', reuse=self._reuse_weights) as scope:
        _, image_features = inception_v3.inception_v3_base(
            ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
            final_endpoint='Mixed_7c',
            min_depth=self._min_depth,
            depth_multiplier=self._depth_multiplier,
            scope=scope)
        feature_maps = feature_map_generators.multi_resolution_feature_maps(
            feature_map_layout=feature_map_layout,
            depth_multiplier=self._depth_multiplier,
            min_depth=self._min_depth,
            insert_1x1_conv=True,
            image_features=image_features)

    return feature_maps.values() 
开发者ID:cagbal,项目名称:ros_people_object_detection_tensorflow,代码行数:39,代码来源:ssd_inception_v3_feature_extractor.py

示例3: extract_features

# 需要导入模块: from nets import inception_v3 [as 别名]
# 或者: from nets.inception_v3 import inception_v3_base [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs.get_shape().assert_has_rank(4)
    shape_assert = tf.Assert(
        tf.logical_and(tf.greater_equal(tf.shape(preprocessed_inputs)[1], 33),
                       tf.greater_equal(tf.shape(preprocessed_inputs)[2], 33)),
        ['image size must at least be 33 in both height and width.'])

    feature_map_layout = {
        'from_layer': ['Mixed_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''],
        'layer_depth': [-1, -1, -1, 512, 256, 128],
    }

    with tf.control_dependencies([shape_assert]):
      with slim.arg_scope(self._conv_hyperparams):
        with tf.variable_scope('InceptionV3',
                               reuse=self._reuse_weights) as scope:
          _, image_features = inception_v3.inception_v3_base(
              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
              final_endpoint='Mixed_7c',
              min_depth=self._min_depth,
              depth_multiplier=self._depth_multiplier,
              scope=scope)
          feature_maps = feature_map_generators.multi_resolution_feature_maps(
              feature_map_layout=feature_map_layout,
              depth_multiplier=self._depth_multiplier,
              min_depth=self._min_depth,
              insert_1x1_conv=True,
              image_features=image_features)

    return feature_maps.values() 
开发者ID:danmacnish,项目名称:cartoonify,代码行数:42,代码来源:ssd_inception_v3_feature_extractor.py

示例4: extract_features

# 需要导入模块: from nets import inception_v3 [as 别名]
# 或者: from nets.inception_v3 import inception_v3_base [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['Mixed_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''
                      ][:self._num_layers],
        'layer_depth': [-1, -1, -1, 512, 256, 128][:self._num_layers],
        'use_explicit_padding': self._use_explicit_padding,
        'use_depthwise': self._use_depthwise,
    }

    with slim.arg_scope(self._conv_hyperparams_fn()):
      with tf.variable_scope('InceptionV3', reuse=self._reuse_weights) as scope:
        _, image_features = inception_v3.inception_v3_base(
            ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
            final_endpoint='Mixed_7c',
            min_depth=self._min_depth,
            depth_multiplier=self._depth_multiplier,
            scope=scope)
        feature_maps = feature_map_generators.multi_resolution_feature_maps(
            feature_map_layout=feature_map_layout,
            depth_multiplier=self._depth_multiplier,
            min_depth=self._min_depth,
            insert_1x1_conv=True,
            image_features=image_features)

    return feature_maps.values() 
开发者ID:ShivangShekhar,项目名称:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV,代码行数:40,代码来源:ssd_inception_v3_feature_extractor.py

示例5: extract_features

# 需要导入模块: from nets import inception_v3 [as 别名]
# 或者: from nets.inception_v3 import inception_v3_base [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['Mixed_5d', 'Mixed_6e', 'Mixed_7c', '', '', ''
                      ][:self._num_layers],
        'layer_depth': [-1, -1, -1, 512, 256, 128][:self._num_layers],
        'use_explicit_padding': self._use_explicit_padding,
        'use_depthwise': self._use_depthwise,
    }

    with slim.arg_scope(self._conv_hyperparams_fn()):
      with tf.variable_scope('InceptionV3', reuse=self._reuse_weights) as scope:
        _, image_features = inception_v3.inception_v3_base(
            ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
            final_endpoint='Mixed_7c',
            min_depth=self._min_depth,
            depth_multiplier=self._depth_multiplier,
            scope=scope)
        feature_maps = feature_map_generators.multi_resolution_feature_maps(
            feature_map_layout=feature_map_layout,
            depth_multiplier=self._depth_multiplier,
            min_depth=self._min_depth,
            insert_1x1_conv=True,
            image_features=image_features)

    return list(feature_maps.values()) 
开发者ID:tensorflow,项目名称:models,代码行数:40,代码来源:ssd_inception_v3_feature_extractor.py


注:本文中的nets.inception_v3.inception_v3_base方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。