def setUp(self): """Set up mock YOLO model. Here we set up a simple mock YOLO model that will always predict 4 detections that happen to always be exactly the anchors that are set up in the above MockAnchorGenerator. Because we let max_detections=5, we will also always end up with an extra padded row in the detection results. """ is_training = False self._num_classes = 1 mock_anchor_generator = MockAnchorGenerator2x2() mock_box_predictor = test_utils.MockBoxPredictor( is_training, self._num_classes) mock_box_coder = test_utils.MockBoxCoder() fake_feature_extractor = FakeYOLOFeatureExtractor() mock_matcher = test_utils.MockMatcher() region_similarity_calculator = sim_calc.IouSimilarity() def image_resizer_fn(image): return tf.identity(image) classification_loss = losses.WeightedSigmoidClassificationLoss( anchorwise_output=True) localization_loss = losses.WeightedSmoothL1LocalizationLoss( anchorwise_output=True) non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=-20.0, iou_thresh=1.0, max_size_per_class=5, max_total_size=5) classification_loss_weight = 1.0 localization_loss_weight = 1.0 normalize_loss_by_num_matches = False # This hard example miner is expected to be a no-op. hard_example_miner = losses.HardExampleMiner(num_hard_examples=None, iou_threshold=1.0) self._num_anchors = 4 self._code_size = 4 self._model = yolo_meta_arch.YOLOMetaArch( is_training, mock_anchor_generator, mock_box_predictor, mock_box_coder, fake_feature_extractor, mock_matcher, region_similarity_calculator, image_resizer_fn, non_max_suppression_fn, tf.identity, classification_loss, localization_loss, classification_loss_weight, localization_loss_weight, normalize_loss_by_num_matches, hard_example_miner)
def _build_yolo_model(yolo_config, is_training): """Builds an YOLO detection model based on the model config. Args: yolo_config: A yolo.proto object containing the config for the desired YOLOMetaArch. is_training: True if this model is being built for training purposes. Returns: YOLOMetaArch based on the config. Raises: ValueError: If yolo_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = yolo_config.num_classes # Feature extractor feature_extractor = _build_yolo_feature_extractor( yolo_config.feature_extractor, is_training) box_coder = box_coder_builder.build(yolo_config.box_coder) matcher = matcher_builder.build(yolo_config.matcher) region_similarity_calculator = sim_calc.build( yolo_config.similarity_calculator) yolo_box_predictor = box_predictor_builder.build(hyperparams_builder.build, yolo_config.box_predictor, is_training, num_classes) anchor_generator = anchor_generator_builder.build( yolo_config.anchor_generator) image_resizer_fn = image_resizer_builder.build(yolo_config.image_resizer) non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( yolo_config.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(yolo_config.loss) normalize_loss_by_num_matches = yolo_config.normalize_loss_by_num_matches return yolo_meta_arch.YOLOMetaArch( is_training, anchor_generator, yolo_box_predictor, box_coder, feature_extractor, matcher, region_similarity_calculator, image_resizer_fn, non_max_suppression_fn, score_conversion_fn, classification_loss, localization_loss, classification_weight, localization_weight, normalize_loss_by_num_matches, hard_example_miner)
def _build_ssd_model(ssd_config, is_training): """Builds an SSD detection model based on the model config. Args: ssd_config: A ssd.proto object containing the config for the desired SSDMetaArch. is_training: True if this model is being built for training purposes. Returns: SSDMetaArch based on the config. Raises: ValueError: If ssd_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = ssd_config.num_classes # Feature extractor feature_extractor = _build_ssd_feature_extractor( ssd_config.feature_extractor, is_training) box_coder = box_coder_builder.build(ssd_config.box_coder) matcher = matcher_builder.build(ssd_config.matcher) region_similarity_calculator = sim_calc.build( ssd_config.similarity_calculator) ssd_box_predictor = box_predictor_builder.build(hyperparams_builder.build, ssd_config.box_predictor, is_training, num_classes) anchor_generator = anchor_generator_builder.build( ssd_config.anchor_generator) image_resizer_fn = image_resizer_builder.build(ssd_config.image_resizer) non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( ssd_config.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(ssd_config.loss) normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches common_kwargs = { 'is_training': is_training, 'anchor_generator': anchor_generator, 'box_predictor': ssd_box_predictor, 'box_coder': box_coder, 'feature_extractor': feature_extractor, 'matcher': matcher, 'region_similarity_calculator': region_similarity_calculator, 'image_resizer_fn': image_resizer_fn, 'non_max_suppression_fn': non_max_suppression_fn, 'score_conversion_fn': score_conversion_fn, 'classification_loss': classification_loss, 'localization_loss': localization_loss, 'classification_loss_weight': classification_weight, 'localization_loss_weight': localization_weight, 'normalize_loss_by_num_matches': normalize_loss_by_num_matches, 'hard_example_miner': hard_example_miner } if isinstance(anchor_generator, yolo_grid_anchor_generator.YoloGridAnchorGenerator): return yolo_meta_arch.YOLOMetaArch(**common_kwargs) else: return ssd_meta_arch.SSDMetaArch(**common_kwargs)
def _build_ssd_model(ssd_config, is_training, add_summaries, add_background_class=True): """Builds an SSD detection model based on the model config. Args: ssd_config: A ssd.proto object containing the config for the desired SSDMetaArch. is_training: True if this model is being built for training purposes. add_summaries: Whether to add tf summaries in the model. 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. Returns: SSDMetaArch based on the config. Raises: ValueError: If ssd_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = ssd_config.num_classes # Feature extractor feature_extractor = _build_ssd_feature_extractor( feature_extractor_config=ssd_config.feature_extractor, is_training=is_training) box_coder = box_coder_builder.build(ssd_config.box_coder) matcher = matcher_builder.build(ssd_config.matcher) region_similarity_calculator = sim_calc.build( ssd_config.similarity_calculator) encode_background_as_zeros = ssd_config.encode_background_as_zeros negative_class_weight = ssd_config.negative_class_weight ssd_box_predictor = box_predictor_builder.build(hyperparams_builder.build, ssd_config.box_predictor, is_training, num_classes) anchor_generator = anchor_generator_builder.build( ssd_config.anchor_generator) image_resizer_fn = image_resizer_builder.build(ssd_config.image_resizer) non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( ssd_config.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner, random_example_sampler) = losses_builder.build(ssd_config.loss) normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches normalize_loc_loss_by_codesize = ssd_config.normalize_loc_loss_by_codesize common_kwargs = { 'is_training': is_training, 'anchor_generator': anchor_generator, 'box_predictor': ssd_box_predictor, 'box_coder': box_coder, 'feature_extractor': feature_extractor, 'matcher': matcher, 'region_similarity_calculator': region_similarity_calculator, 'image_resizer_fn': image_resizer_fn, 'non_max_suppression_fn': non_max_suppression_fn, 'score_conversion_fn': score_conversion_fn, 'classification_loss': classification_loss, 'localization_loss': localization_loss, 'classification_loss_weight': classification_weight, 'localization_loss_weight': localization_weight, 'normalize_loss_by_num_matches': normalize_loss_by_num_matches, 'hard_example_miner': hard_example_miner } if isinstance(anchor_generator, yolo_grid_anchor_generator.YoloGridAnchorGenerator): return yolo_meta_arch.YOLOMetaArch(**common_kwargs) else: #return ssd_meta_arch.SSDMetaArch(**common_kwargs) return ssd_meta_arch.SSDMetaArch( is_training, anchor_generator, ssd_box_predictor, box_coder, feature_extractor, matcher, region_similarity_calculator, encode_background_as_zeros, negative_class_weight, image_resizer_fn, non_max_suppression_fn, score_conversion_fn, classification_loss, localization_loss, classification_weight, localization_weight, normalize_loss_by_num_matches, hard_example_miner, add_summaries=add_summaries, normalize_loc_loss_by_codesize=normalize_loc_loss_by_codesize, freeze_batchnorm=ssd_config.freeze_batchnorm, inplace_batchnorm_update=ssd_config.inplace_batchnorm_update, add_background_class=add_background_class, random_example_sampler=random_example_sampler)