Python inception_v3.inception_v3_base方法代碼示例

本文整理匯總了Python中nets.inception_v3.inception_v3_base方法的典型用法代碼示例。如果您正苦於以下問題：Python inception_v3.inception_v3_base方法的具體用法？Python inception_v3.inception_v3_base怎麽用？Python inception_v3.inception_v3_base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: extract_features

# 需要導入模塊: from nets import inception_v3 [as 別名]
# 或者: from nets.inception_v3 import inception_v3_base [as 別名]
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()

開發者ID:ahmetozlu，項目名稱:vehicle_counting_tensorflow，代碼行數:39，代碼來源:ssd_inception_v3_feature_extractor.py

示例2: extract_features

# 需要導入模塊: from nets import inception_v3 [as 別名]
# 或者: from nets.inception_v3 import inception_v3_base [as 別名]
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()

開發者ID:cagbal，項目名稱:ros_people_object_detection_tensorflow，代碼行數:39，代碼來源:ssd_inception_v3_feature_extractor.py

示例3: extract_features

# 需要導入模塊: from nets import inception_v3 [as 別名]
# 或者: from nets.inception_v3 import inception_v3_base [as 別名]
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()

開發者ID:danmacnish，項目名稱:cartoonify，代碼行數:42，代碼來源:ssd_inception_v3_feature_extractor.py

示例4: extract_features

# 需要導入模塊: from nets import inception_v3 [as 別名]
# 或者: from nets.inception_v3 import inception_v3_base [as 別名]
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()

開發者ID:ShivangShekhar，項目名稱:Live-feed-object-device-identification-using-Tensorflow-and-OpenCV，代碼行數:40，代碼來源:ssd_inception_v3_feature_extractor.py

示例5: extract_features

# 需要導入模塊: from nets import inception_v3 [as 別名]
# 或者: from nets.inception_v3 import inception_v3_base [as 別名]
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())

開發者ID:tensorflow，項目名稱:models，代碼行數:40，代碼來源:ssd_inception_v3_feature_extractor.py

注：本文中的nets.inception_v3.inception_v3_base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。