Python box_predictor.MASK_PREDICTIONS属性代码示例

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def test_get_instance_masks(self):
    image_features = tf.random_uniform([2, 7, 7, 3], dtype=tf.float32)
    mask_box_predictor = box_predictor.MaskRCNNBoxPredictor(
        is_training=False,
        num_classes=5,
        fc_hyperparams=self._build_arg_scope_with_hyperparams(),
        use_dropout=False,
        dropout_keep_prob=0.5,
        box_code_size=4,
        conv_hyperparams=self._build_arg_scope_with_hyperparams(
            op_type=hyperparams_pb2.Hyperparams.CONV),
        predict_instance_masks=True)
    box_predictions = mask_box_predictor.predict(
        image_features, num_predictions_per_location=1, scope='BoxPredictor')
    mask_predictions = box_predictions[box_predictor.MASK_PREDICTIONS]
    self.assertListEqual([2, 1, 5, 14, 14],
                         mask_predictions.get_shape().as_list()) 

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def _predict_head(self, head_name, head_obj, image_feature, box_tower_feature,
                    feature_index, has_different_feature_channels,
                    target_channel, inserted_layer_counter,
                    num_predictions_per_location):
    if head_name == CLASS_PREDICTIONS_WITH_BACKGROUND:
      tower_name_scope = 'ClassPredictionTower'
    elif head_name == MASK_PREDICTIONS:
      tower_name_scope = 'MaskPredictionTower'
    else:
      raise ValueError('Unknown head')
    if self._share_prediction_tower:
      head_tower_feature = box_tower_feature
    else:
      head_tower_feature = self._compute_base_tower(
          tower_name_scope=tower_name_scope,
          image_feature=image_feature,
          feature_index=feature_index,
          has_different_feature_channels=has_different_feature_channels,
          target_channel=target_channel,
          inserted_layer_counter=inserted_layer_counter)
    return head_obj.predict(
        features=head_tower_feature,
        num_predictions_per_location=num_predictions_per_location) 

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def test_get_instance_masks(self):
    image_features = tf.random_uniform([2, 7, 7, 3], dtype=tf.float32)
    mask_box_predictor = box_predictor.MaskRCNNBoxPredictor(
        is_training=False,
        num_classes=5,
        fc_hyperparams=self._build_arg_scope_with_hyperparams(),
        use_dropout=False,
        dropout_keep_prob=0.5,
        box_code_size=4,
        conv_hyperparams=self._build_arg_scope_with_hyperparams(
            op_type=hyperparams_pb2.Hyperparams.CONV),
        predict_instance_masks=True)
    box_predictions = mask_box_predictor.predict(
        [image_features],
        num_predictions_per_location=[1],
        scope='BoxPredictor',
        predict_boxes_and_classes=True,
        predict_auxiliary_outputs=True)
    mask_predictions = box_predictions[box_predictor.MASK_PREDICTIONS]
    self.assertListEqual([2, 1, 5, 14, 14],
                         mask_predictions.get_shape().as_list()) 

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def test_get_instance_masks(self):
    image_features = tf.random_uniform([2, 7, 7, 3], dtype=tf.float32)
    mask_box_predictor = box_predictor.MaskRCNNBoxPredictor(
        is_training=False,
        num_classes=5,
        fc_hyperparams_fn=self._build_arg_scope_with_hyperparams(),
        use_dropout=False,
        dropout_keep_prob=0.5,
        box_code_size=4,
        conv_hyperparams_fn=self._build_arg_scope_with_hyperparams(
            op_type=hyperparams_pb2.Hyperparams.CONV),
        predict_instance_masks=True)
    box_predictions = mask_box_predictor.predict(
        [image_features],
        num_predictions_per_location=[1],
        scope='BoxPredictor',
        predict_boxes_and_classes=True,
        predict_auxiliary_outputs=True)
    mask_predictions = box_predictions[box_predictor.MASK_PREDICTIONS]
    self.assertListEqual([2, 1, 5, 14, 14],
                         mask_predictions.get_shape().as_list()) 

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def test_get_instance_masks(self):
    image_features = tf.random_uniform([2, 7, 7, 3], dtype=tf.float32)
    mask_box_predictor = box_predictor.MaskRCNNBoxPredictor(
        is_training=False,
        num_classes=5,
        fc_hyperparams=self._build_arg_scope_with_hyperparams(),
        use_dropout=False,
        dropout_keep_prob=0.5,
        box_code_size=4,
        conv_hyperparams=self._build_arg_scope_with_hyperparams(
            op_type=hyperparams_pb2.Hyperparams.CONV),
        predict_instance_masks=True,
        num_layers_before_mask_prediction=2)
    box_predictions = mask_box_predictor.predict(
        image_features, num_predictions_per_location=1, scope='BoxPredictor')
    mask_predictions = box_predictions[box_predictor.MASK_PREDICTIONS]
    self.assertListEqual([2, 1, 5, 14, 14],
                         mask_predictions.get_shape().as_list()) 

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def _predict(self, image_features, num_predictions_per_location):
    image_feature = image_features[0]
    combined_feature_shape = shape_utils.combined_static_and_dynamic_shape(
        image_feature)
    batch_size = combined_feature_shape[0]
    num_anchors = (combined_feature_shape[1] * combined_feature_shape[2])
    code_size = 4
    zero = tf.reduce_sum(0 * image_feature)
    num_class_slots = self.num_classes
    if self._add_background_class:
      num_class_slots = num_class_slots + 1
    box_encodings = zero + tf.zeros(
        (batch_size, num_anchors, 1, code_size), dtype=tf.float32)
    class_predictions_with_background = zero + tf.zeros(
        (batch_size, num_anchors, num_class_slots), dtype=tf.float32)
    masks = zero + tf.zeros(
        (batch_size, num_anchors, self.num_classes, DEFAULT_MASK_SIZE,
         DEFAULT_MASK_SIZE),
        dtype=tf.float32)
    predictions_dict = {
        box_predictor.BOX_ENCODINGS:
            box_encodings,
        box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND:
            class_predictions_with_background
    }
    if self._predict_mask:
      predictions_dict[box_predictor.MASK_PREDICTIONS] = masks

    return predictions_dict 

# 需要导入模块: from object_detection.core import box_predictor [as 别名]
# 或者: from object_detection.core.box_predictor import MASK_PREDICTIONS [as 别名]
def predict_edgemask(self, prediction_dict):
    input_feature = prediction_dict['rpn_features_to_crop']
    edgemask_predictions = self._edgemask_predictor.predict(
      input_feature, scope=self.edgemask_predictor_scope)
    prediction_dict['edgemask_predictions'] = edgemask_predictions[mask_predictor.MASK_PREDICTIONS]
    return prediction_dict