Python box_list_ops.concatenate方法代码示例

# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import concatenate [as 别名]
def test_concatenate_is_correct(self):
    corners1 = tf.constant([[0, 0, 0, 0], [1, 2, 3, 4]], tf.float32)
    scores1 = tf.constant([1.0, 2.1])
    corners2 = tf.constant([[0, 3, 1, 6], [2, 4, 3, 8], [1, 0, 5, 10]],
                           tf.float32)
    scores2 = tf.constant([1.0, 2.1, 5.6])

    exp_corners = [[0, 0, 0, 0],
                   [1, 2, 3, 4],
                   [0, 3, 1, 6],
                   [2, 4, 3, 8],
                   [1, 0, 5, 10]]
    exp_scores = [1.0, 2.1, 1.0, 2.1, 5.6]

    boxlist1 = box_list.BoxList(corners1)
    boxlist1.add_field('scores', scores1)
    boxlist2 = box_list.BoxList(corners2)
    boxlist2.add_field('scores', scores2)
    result = box_list_ops.concatenate([boxlist1, boxlist2])
    with self.test_session() as sess:
      corners_output, scores_output = sess.run(
          [result.get(), result.get_field('scores')])
      self.assertAllClose(corners_output, exp_corners)
      self.assertAllClose(scores_output, exp_scores) 

# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import concatenate [as 别名]
def test_invalid_input_box_list_list(self):
    with self.assertRaises(ValueError):
      box_list_ops.concatenate(None)
    with self.assertRaises(ValueError):
      box_list_ops.concatenate([])
    with self.assertRaises(ValueError):
      corners = tf.constant([[0, 0, 0, 0]], tf.float32)
      boxlist = box_list.BoxList(corners)
      box_list_ops.concatenate([boxlist, 2]) 

# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import concatenate [as 别名]
def test_concatenate_with_missing_fields(self):
    corners1 = tf.constant([[0, 0, 0, 0], [1, 2, 3, 4]], tf.float32)
    scores1 = tf.constant([1.0, 2.1])
    corners2 = tf.constant([[0, 3, 1, 6], [2, 4, 3, 8]], tf.float32)
    boxlist1 = box_list.BoxList(corners1)
    boxlist1.add_field('scores', scores1)
    boxlist2 = box_list.BoxList(corners2)
    with self.assertRaises(ValueError):
      box_list_ops.concatenate([boxlist1, boxlist2]) 

# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import concatenate [as 别名]
def test_concatenate_with_incompatible_field_shapes(self):
    corners1 = tf.constant([[0, 0, 0, 0], [1, 2, 3, 4]], tf.float32)
    scores1 = tf.constant([1.0, 2.1])
    corners2 = tf.constant([[0, 3, 1, 6], [2, 4, 3, 8]], tf.float32)
    scores2 = tf.constant([[1.0, 1.0], [2.1, 3.2]])
    boxlist1 = box_list.BoxList(corners1)
    boxlist1.add_field('scores', scores1)
    boxlist2 = box_list.BoxList(corners2)
    boxlist2.add_field('scores', scores2)
    with self.assertRaises(ValueError):
      box_list_ops.concatenate([boxlist1, boxlist2]) 

# 需要导入模块: from object_detection.core import box_list_ops [as 别名]
# 或者: from object_detection.core.box_list_ops import concatenate [as 别名]
def _extract_rpn_feature_maps(self, preprocessed_inputs):
    """Extracts RPN features.

    This function extracts two feature maps: a feature map to be directly
    fed to a box predictor (to predict location and objectness scores for
    proposals) and a feature map from which to crop regions which will then
    be sent to the second stage box classifier.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] image tensor.

    Returns:
      rpn_box_predictor_features: A 4-D float32 tensor with shape
        [batch, height, width, depth] to be used for predicting proposal boxes
        and corresponding objectness scores.
      rpn_features_to_crop: A 4-D float32 tensor with shape
        [batch, height, width, depth] representing image features to crop using
        the proposals boxes.
      anchors: A BoxList representing anchors (for the RPN) in
        absolute coordinates.
      image_shape: A 1-D tensor representing the input image shape.
    """
    image_shape = tf.shape(preprocessed_inputs)
    rpn_features_to_crop, _ = self._feature_extractor.extract_proposal_features(
        preprocessed_inputs, scope=self.first_stage_feature_extractor_scope)

    feature_map_shape = tf.shape(rpn_features_to_crop)
    anchors = box_list_ops.concatenate(
        self._first_stage_anchor_generator.generate([(feature_map_shape[1],
                                                      feature_map_shape[2])]))
    with slim.arg_scope(self._first_stage_box_predictor_arg_scope):
      kernel_size = self._first_stage_box_predictor_kernel_size
      rpn_box_predictor_features = slim.conv2d(
          rpn_features_to_crop,
          self._first_stage_box_predictor_depth,
          kernel_size=[kernel_size, kernel_size],
          rate=self._first_stage_atrous_rate,
          activation_fn=tf.nn.relu6)
    return (rpn_box_predictor_features, rpn_features_to_crop,
            anchors, image_shape)