Python object_detection.builders.post_processing_builder.build() Examples

def _get_second_stage_box_predictor(self, num_classes, is_training,
                                      predict_masks, masks_are_class_agnostic):
    box_predictor_proto = box_predictor_pb2.BoxPredictor()
    text_format.Merge(self._get_second_stage_box_predictor_text_proto(),
                      box_predictor_proto)
    if predict_masks:
      text_format.Merge(
          self._add_mask_to_second_stage_box_predictor_text_proto(
              masks_are_class_agnostic),
          box_predictor_proto)

    return box_predictor_builder.build(
        hyperparams_builder.build,
        box_predictor_proto,
        num_classes=num_classes,
        is_training=is_training) 

def build(model_config, is_training):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def build(model_config, is_training, add_summaries=True):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.
    add_summaries: Whether to add tensorflow summaries in the model graph.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training, add_summaries)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training,
                                    add_summaries)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def build(model_config, is_training):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def test_build_identity_score_converter_with_logit_scale(self):
    post_processing_text_proto = """
      score_converter: IDENTITY
      logit_scale: 2.0
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter.__name__, 'identity_with_logit_scale')

    inputs = tf.constant([1, 1], tf.float32)
    outputs = score_converter(inputs)
    with self.test_session() as sess:
      converted_scores = sess.run(outputs)
      expected_converted_scores = sess.run(tf.constant([.5, .5], tf.float32))
      self.assertAllClose(converted_scores, expected_converted_scores) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def build(model_config, is_training):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def test_build_identity_score_converter_with_logit_scale(self):
    post_processing_text_proto = """
      score_converter: IDENTITY
      logit_scale: 2.0
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter.__name__, 'identity_with_logit_scale')

    inputs = tf.constant([1, 1], tf.float32)
    outputs = score_converter(inputs)
    with self.test_session() as sess:
      converted_scores = sess.run(outputs)
      expected_converted_scores = sess.run(tf.constant([.5, .5], tf.float32))
      self.assertAllClose(converted_scores, expected_converted_scores) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def build(model_config, is_training):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def test_build_identity_score_converter_with_logit_scale(self):
    post_processing_text_proto = """
      score_converter: IDENTITY
      logit_scale: 2.0
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter.__name__, 'identity_with_logit_scale')

    inputs = tf.constant([1, 1], tf.float32)
    outputs = score_converter(inputs)
    with self.test_session() as sess:
      converted_scores = sess.run(outputs)
      expected_converted_scores = sess.run(tf.constant([.5, .5], tf.float32))
      self.assertAllClose(converted_scores, expected_converted_scores) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def build(model_config, is_training, add_summaries=True):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.
    add_summaries: Whether to add tensorflow summaries in the model graph.
  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training, add_summaries)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training,
                                    add_summaries)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def test_build_identity_score_converter_with_logit_scale(self):
    post_processing_text_proto = """
      score_converter: IDENTITY
      logit_scale: 2.0
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter.__name__, 'identity_with_logit_scale')

    inputs = tf.constant([1, 1], tf.float32)
    outputs = score_converter(inputs)
    with self.test_session() as sess:
      converted_scores = sess.run(outputs)
      expected_converted_scores = sess.run(tf.constant([.5, .5], tf.float32))
      self.assertAllClose(converted_scores, expected_converted_scores) 

def _get_second_stage_box_predictor(self, num_classes, is_training,
                                      predict_masks, masks_are_class_agnostic):
    box_predictor_proto = box_predictor_pb2.BoxPredictor()
    text_format.Merge(self._get_second_stage_box_predictor_text_proto(),
                      box_predictor_proto)
    if predict_masks:
      text_format.Merge(
          self._add_mask_to_second_stage_box_predictor_text_proto(
              masks_are_class_agnostic),
          box_predictor_proto)

    return box_predictor_builder.build(
        hyperparams_builder.build,
        box_predictor_proto,
        num_classes=num_classes,
        is_training=is_training) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def test_build_non_max_suppressor_with_correct_parameters(self):
    post_processing_text_proto = """
      batch_non_max_suppression {
        score_threshold: 0.7
        iou_threshold: 0.6
        max_detections_per_class: 100
        max_total_detections: 300
      }
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    non_max_suppressor, _ = post_processing_builder.build(
        post_processing_config)
    self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100)
    self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
    self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7)
    self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6) 

def test_build_identity_score_converter_with_logit_scale(self):
    post_processing_text_proto = """
      score_converter: IDENTITY
      logit_scale: 2.0
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter.__name__, 'identity_with_logit_scale')

    inputs = tf.constant([1, 1], tf.float32)
    outputs = score_converter(inputs)
    with self.test_session() as sess:
      converted_scores = sess.run(outputs)
      expected_converted_scores = sess.run(tf.constant([.5, .5], tf.float32))
      self.assertAllClose(converted_scores, expected_converted_scores) 

def build(model_config, is_training):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def build(model_config, is_training, add_summaries=True):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.
    add_summaries: Whether to add tensorflow summaries in the model graph.

  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training, add_summaries)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training,
                                    add_summaries)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def test_build_sigmoid_score_converter(self):
    post_processing_text_proto = """
      score_converter: SIGMOID
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter, tf.sigmoid) 

def test_build_identity_score_converter(self):
    post_processing_text_proto = """
      score_converter: IDENTITY
    """
    post_processing_config = post_processing_pb2.PostProcessing()
    text_format.Merge(post_processing_text_proto, post_processing_config)
    _, score_converter = post_processing_builder.build(post_processing_config)
    self.assertEqual(score_converter, tf.identity) 

def _get_second_stage_box_predictor(self, num_classes, is_training):
    box_predictor_proto = box_predictor_pb2.BoxPredictor()
    text_format.Merge(self._get_second_stage_box_predictor_text_proto(),
                      box_predictor_proto)
    return box_predictor_builder.build(
        hyperparams_builder.build,
        box_predictor_proto,
        num_classes=num_classes,
        is_training=is_training) 

def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 

def build(model_config, is_training, add_summaries=True,
          add_background_class=True):
  """Builds a DetectionModel based on the model config.

  Args:
    model_config: A model.proto object containing the config for the desired
      DetectionModel.
    is_training: True if this model is being built for training purposes.
    add_summaries: Whether to add tensorflow summaries in the model graph.
    add_background_class: Whether to add an implicit background class to one-hot
      encodings of groundtruth labels. Set to false if using groundtruth labels
      with an explicit background class or using multiclass scores instead of
      truth in the case of distillation. Ignored in the case of faster_rcnn.
  Returns:
    DetectionModel based on the config.

  Raises:
    ValueError: On invalid meta architecture or model.
  """
  if not isinstance(model_config, model_pb2.DetectionModel):
    raise ValueError('model_config not of type model_pb2.DetectionModel.')
  meta_architecture = model_config.WhichOneof('model')
  if meta_architecture == 'ssd':
    return _build_ssd_model(model_config.ssd, is_training, add_summaries,
                            add_background_class)
  if meta_architecture == 'faster_rcnn':
    return _build_faster_rcnn_model(model_config.faster_rcnn, is_training,
                                    add_summaries)
  raise ValueError('Unknown meta architecture: {}'.format(meta_architecture)) 

def _build_arg_scope_with_hyperparams(self,
                                        hyperparams_text_proto,
                                        is_training):
    hyperparams = hyperparams_pb2.Hyperparams()
    text_format.Merge(hyperparams_text_proto, hyperparams)
    return hyperparams_builder.build(hyperparams, is_training=is_training)