def test_raise_error_on_empty_matcher(self): matcher_text_proto = """ """ matcher_proto = matcher_pb2.Matcher() text_format.Merge(matcher_text_proto, matcher_proto) with self.assertRaises(ValueError): matcher_builder.build(matcher_proto)
def _build_ssd_model(ssd_config, is_training, add_summaries): """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. 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 return ssd_meta_arch.SSDMetaArch( is_training, anchor_generator, ssd_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, add_summaries=add_summaries)
def test_build_bipartite_matcher(self): matcher_text_proto = """ bipartite_matcher { } """ matcher_proto = matcher_pb2.Matcher() text_format.Merge(matcher_text_proto, matcher_proto) matcher_object = matcher_builder.build(matcher_proto) self.assertTrue( isinstance(matcher_object, bipartite_matcher.GreedyBipartiteMatcher))
def test_build_arg_max_matcher_with_defaults(self): matcher_text_proto = """ argmax_matcher { } """ matcher_proto = matcher_pb2.Matcher() text_format.Merge(matcher_text_proto, matcher_proto) matcher_object = matcher_builder.build(matcher_proto) self.assertTrue(isinstance(matcher_object, argmax_matcher.ArgMaxMatcher)) self.assertAlmostEqual(matcher_object._matched_threshold, 0.5) self.assertAlmostEqual(matcher_object._unmatched_threshold, 0.5) self.assertTrue(matcher_object._negatives_lower_than_unmatched) self.assertFalse(matcher_object._force_match_for_each_row)
def test_build_arg_max_matcher_with_non_default_parameters(self): matcher_text_proto = """ argmax_matcher { matched_threshold: 0.7 unmatched_threshold: 0.3 negatives_lower_than_unmatched: false force_match_for_each_row: true use_matmul_gather: true } """ matcher_proto = matcher_pb2.Matcher() text_format.Merge(matcher_text_proto, matcher_proto) matcher_object = matcher_builder.build(matcher_proto) self.assertTrue(isinstance(matcher_object, argmax_matcher.ArgMaxMatcher)) self.assertAlmostEqual(matcher_object._matched_threshold, 0.7) self.assertAlmostEqual(matcher_object._unmatched_threshold, 0.3) self.assertFalse(matcher_object._negatives_lower_than_unmatched) self.assertTrue(matcher_object._force_match_for_each_row) self.assertTrue(matcher_object._use_matmul_gather)
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 return ssd_meta_arch.SSDMetaArch( is_training, anchor_generator, ssd_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 test_build_arg_max_matcher_with_non_default_parameters(self): matcher_text_proto = """ argmax_matcher { matched_threshold: 0.7 unmatched_threshold: 0.3 negatives_lower_than_unmatched: false force_match_for_each_row: true use_matmul_gather: true } """ matcher_proto = matcher_pb2.Matcher() text_format.Merge(matcher_text_proto, matcher_proto) matcher_object = matcher_builder.build(matcher_proto) self.assertTrue(isinstance(matcher_object, argmax_matcher.ArgMaxMatcher)) self.assertAlmostEqual(matcher_object._matched_threshold, 0.7) self.assertAlmostEqual(matcher_object._unmatched_threshold, 0.3) self.assertFalse(matcher_object._negatives_lower_than_unmatched) self.assertTrue(matcher_object._force_match_for_each_row) self.assertTrue(matcher_object._use_matmul_gather)
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): num_classes = ssd_config.num_classes # Feature extractor feature_extractor = _build_ssd_feature_extractor( feature_extractor_config=ssd_config.feature_extractor, freeze_batchnorm=ssd_config.freeze_batchnorm, 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 anchor_generator = anchor_generator_builder.build( ssd_config.anchor_generator) if feature_extractor.is_keras_model: ssd_box_predictor = box_predictor_builder.build_keras( hyperparams_fn=hyperparams_builder.KerasLayerHyperparams, freeze_batchnorm=ssd_config.freeze_batchnorm, inplace_batchnorm_update=False, num_predictions_per_location_list=anchor_generator .num_anchors_per_location(), box_predictor_config=ssd_config.box_predictor, is_training=is_training, num_classes=num_classes, add_background_class=ssd_config.add_background_class) else: ssd_box_predictor = box_predictor_builder.build( hyperparams_builder.build, ssd_config.box_predictor, is_training, num_classes, ssd_config.add_background_class) 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, expected_loss_weights_fn) = 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 equalization_loss_config = ops.EqualizationLossConfig( weight=ssd_config.loss.equalization_loss.weight, exclude_prefixes=ssd_config.loss.equalization_loss.exclude_prefixes) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, matcher, box_coder, negative_class_weight=negative_class_weight) ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch kwargs = {} return ssd_meta_arch_fn( is_training=is_training, anchor_generator=anchor_generator, box_predictor=ssd_box_predictor, box_coder=box_coder, feature_extractor=feature_extractor, encode_background_as_zeros=encode_background_as_zeros, 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, target_assigner_instance=target_assigner_instance, 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=ssd_config.add_background_class, explicit_background_class=ssd_config.explicit_background_class, random_example_sampler=random_example_sampler, expected_loss_weights_fn=expected_loss_weights_fn, use_confidences_as_targets=ssd_config.use_confidences_as_targets, implicit_example_weight=ssd_config.implicit_example_weight, equalization_loss_config=equalization_loss_config, **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 weight_regression_loss_by_score = ( ssd_config.weight_regression_loss_by_score) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, matcher, box_coder, negative_class_weight=negative_class_weight, weight_regression_loss_by_score=weight_regression_loss_by_score) expected_classification_loss_under_sampling = None if ssd_config.use_expected_classification_loss_under_sampling: expected_classification_loss_under_sampling = functools.partial( ops.expected_classification_loss_under_sampling, minimum_negative_sampling=ssd_config.minimum_negative_sampling, desired_negative_sampling_ratio=ssd_config. desired_negative_sampling_ratio) ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch # BEGIN GOOGLE-INTERNAL # TODO(lzc): move ssd_mask_meta_arch to third party when it has decent # performance relative to a comparable Mask R-CNN model (b/112561592). predictor_config = ssd_config.box_predictor predict_instance_masks = False if predictor_config.WhichOneof( 'box_predictor_oneof') == 'convolutional_box_predictor': predict_instance_masks = ( predictor_config.convolutional_box_predictor.HasField('mask_head')) elif predictor_config.WhichOneof( 'box_predictor_oneof' ) == 'weight_shared_convolutional_box_predictor': predict_instance_masks = ( predictor_config.weight_shared_convolutional_box_predictor. HasField('mask_head')) if predict_instance_masks: ssd_meta_arch_fn = ssd_mask_meta_arch.SSDMaskMetaArch # END GOOGLE-INTERNAL return ssd_meta_arch_fn( is_training=is_training, anchor_generator=anchor_generator, box_predictor=ssd_box_predictor, box_coder=box_coder, feature_extractor=feature_extractor, encode_background_as_zeros=encode_background_as_zeros, 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, target_assigner_instance=target_assigner_instance, 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, expected_classification_loss_under_sampling= expected_classification_loss_under_sampling)
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) = 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 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)
def _build_lstm_model(ssd_config, lstm_config, is_training): """Builds an LSTM detection model based on the model config. Args: ssd_config: A ssd.proto object containing the config for the desired LSTMSSDMetaArch. lstm_config: LstmModel config proto that specifies LSTM train/eval configs. is_training: True if this model is being built for training purposes. Returns: LSTMSSDMetaArch based on the config. Raises: ValueError: If ssd_config.type is not recognized (i.e. not registered in model_class_map), or if lstm_config.interleave_strategy is not recognized. ValueError: If unroll_length is not specified in the config file. """ feature_extractor = _build_lstm_feature_extractor( ssd_config.feature_extractor, is_training, lstm_config) 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) num_classes = ssd_config.num_classes 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, miner, _, _) = losses_builder.build(ssd_config.loss) normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches encode_background_as_zeros = ssd_config.encode_background_as_zeros negative_class_weight = ssd_config.negative_class_weight # Extra configs for lstm unroll length. unroll_length = None if 'lstm' in ssd_config.feature_extractor.type: if is_training: unroll_length = lstm_config.train_unroll_length else: unroll_length = lstm_config.eval_unroll_length if unroll_length is None: raise ValueError('No unroll length found in the config file') target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, matcher, box_coder, negative_class_weight=negative_class_weight) lstm_model = lstm_ssd_meta_arch.LSTMSSDMetaArch( is_training=is_training, anchor_generator=anchor_generator, box_predictor=ssd_box_predictor, box_coder=box_coder, feature_extractor=feature_extractor, encode_background_as_zeros=encode_background_as_zeros, 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=miner, unroll_length=unroll_length, target_assigner_instance=target_assigner_instance) return lstm_model
def _build_lstm_model(ssd_config, lstm_config, is_training): """Builds an LSTM detection model based on the model config. Args: ssd_config: A ssd.proto object containing the config for the desired LSTMMetaArch. lstm_config: LstmModel config proto that specifies LSTM train/eval configs. is_training: True if this model is being built for training purposes. Returns: LSTMMetaArch based on the config. Raises: ValueError: If ssd_config.type is not recognized (i.e. not registered in model_class_map), or if lstm_config.interleave_strategy is not recognized. ValueError: If unroll_length is not specified in the config file. """ feature_extractor = _build_lstm_feature_extractor( ssd_config.feature_extractor, is_training, lstm_config.lstm_state_depth) 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) num_classes = ssd_config.num_classes 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, miner, _, _) = losses_builder.build(ssd_config.loss) normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches encode_background_as_zeros = ssd_config.encode_background_as_zeros negative_class_weight = ssd_config.negative_class_weight # Extra configs for lstm unroll length. unroll_length = None if 'lstm' in ssd_config.feature_extractor.type: if is_training: unroll_length = lstm_config.train_unroll_length else: unroll_length = lstm_config.eval_unroll_length if unroll_length is None: raise ValueError('No unroll length found in the config file') target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, matcher, box_coder, negative_class_weight=negative_class_weight) lstm_model = lstm_meta_arch.LSTMMetaArch( is_training=is_training, anchor_generator=anchor_generator, box_predictor=ssd_box_predictor, box_coder=box_coder, feature_extractor=feature_extractor, encode_background_as_zeros=encode_background_as_zeros, 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=miner, unroll_length=unroll_length, target_assigner_instance=target_assigner_instance) return lstm_model
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 #number of clases # Feature extractor feature_extractor = _build_ssd_feature_extractor(ssd_config.feature_extractor, #we use ssd_mobilenet_v1 as the feature extractor is_training) #set the class in ssd_mobilenr_v1_feature_extractor amd ssd_meta+arch.py #when taking the regression loss we are working with some transorfmation. That means our predictors will predict 4 cordinates and those codinates should be regressed with some kind embedding which was made with ground truth boxes and default boxes , then after getting those we docode them for real images box_coder = box_coder_builder.build(ssd_config.box_coder) #set en encoding w.r.t ground truth boxes and achor boxes . The output creating with this object will then regressed with the predicted onece. chenck equation 2 in the ssd paper matcher = matcher_builder.build(ssd_config.matcher) #matching the predicted to ground trunth- Builds a matcher object based on the matcher config #in obove object matching is done with default boxes and ground truth boxes , that's how xij value in the paper obtained . region_similarity_calculator = sim_calc.build( #how to calculate the similarity parameter is iou . ssd_config.similarity_calculator) ssd_box_predictor = box_predictor_builder.build(hyperparams_builder.build, #This will take care of the convolutional kernal ssd_config.box_predictor, is_training, num_classes) #this returns a box_predictor object anchor_generator = anchor_generator_builder.build( #pass an instance or object where we can create ancho boxes for differen featuremaps ssd_config.anchor_generator) image_resizer_fn = image_resizer_builder.build(ssd_config.image_resizer) #this is imortatnt we use fixed_shape_resizer non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( #this is to work with NMS supression output ssd_config.post_processing) #score conversion function will convert logits to probabilities (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(ssd_config.loss) #now the loss for hard examples these outputs are objects normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches # we devide by the matching acnhorboxes return ssd_meta_arch.SSDMetaArch( #here we initialized a object of ssd_meta_arch which will be used in trainign is_training, anchor_generator, ssd_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, 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 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)
def _build_ssd_model(ssd_config, is_training, add_summaries): """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. 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, freeze_batchnorm=ssd_config.freeze_batchnorm, 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 anchor_generator = anchor_generator_builder.build( ssd_config.anchor_generator) if feature_extractor.is_keras_model: ssd_box_predictor = box_predictor_builder.build_keras( conv_hyperparams_fn=hyperparams_builder.KerasLayerHyperparams, freeze_batchnorm=ssd_config.freeze_batchnorm, inplace_batchnorm_update=False, num_predictions_per_location_list=anchor_generator .num_anchors_per_location(), box_predictor_config=ssd_config.box_predictor, is_training=is_training, num_classes=num_classes, add_background_class=ssd_config.add_background_class) else: ssd_box_predictor = box_predictor_builder.build( hyperparams_builder.build, ssd_config.box_predictor, is_training, num_classes, ssd_config.add_background_class) 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 weight_regression_loss_by_score = (ssd_config.weight_regression_loss_by_score) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, matcher, box_coder, negative_class_weight=negative_class_weight, weight_regression_loss_by_score=weight_regression_loss_by_score) expected_classification_loss_under_sampling = None if ssd_config.use_expected_classification_loss_under_sampling: expected_classification_loss_under_sampling = functools.partial( ops.expected_classification_loss_under_sampling, min_num_negative_samples=ssd_config.min_num_negative_samples, desired_negative_sampling_ratio=ssd_config. desired_negative_sampling_ratio) ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch return ssd_meta_arch_fn( is_training=is_training, anchor_generator=anchor_generator, box_predictor=ssd_box_predictor, box_coder=box_coder, feature_extractor=feature_extractor, encode_background_as_zeros=encode_background_as_zeros, 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, target_assigner_instance=target_assigner_instance, 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=ssd_config.add_background_class, random_example_sampler=random_example_sampler, expected_classification_loss_under_sampling= expected_classification_loss_under_sampling)
def _build_ssd_model(ssd_config, is_training, add_summaries): """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. 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, freeze_batchnorm=ssd_config.freeze_batchnorm, 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 anchor_generator = anchor_generator_builder.build( ssd_config.anchor_generator) if feature_extractor.is_keras_model: ssd_box_predictor = box_predictor_builder.build_keras( hyperparams_fn=hyperparams_builder.KerasLayerHyperparams, freeze_batchnorm=ssd_config.freeze_batchnorm, inplace_batchnorm_update=False, num_predictions_per_location_list=anchor_generator. num_anchors_per_location(), box_predictor_config=ssd_config.box_predictor, is_training=is_training, num_classes=num_classes, add_background_class=ssd_config.add_background_class) else: ssd_box_predictor = box_predictor_builder.build( hyperparams_builder.build, ssd_config.box_predictor, is_training, num_classes, ssd_config.add_background_class) 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, expected_loss_weights_fn) = 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 equalization_loss_config = ops.EqualizationLossConfig( weight=ssd_config.loss.equalization_loss.weight, exclude_prefixes=ssd_config.loss.equalization_loss.exclude_prefixes) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, matcher, box_coder, negative_class_weight=negative_class_weight) ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch kwargs = {} return ssd_meta_arch_fn( is_training=is_training, anchor_generator=anchor_generator, box_predictor=ssd_box_predictor, box_coder=box_coder, feature_extractor=feature_extractor, encode_background_as_zeros=encode_background_as_zeros, 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, target_assigner_instance=target_assigner_instance, 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=ssd_config.add_background_class, explicit_background_class=ssd_config.explicit_background_class, random_example_sampler=random_example_sampler, expected_loss_weights_fn=expected_loss_weights_fn, use_confidences_as_targets=ssd_config.use_confidences_as_targets, implicit_example_weight=ssd_config.implicit_example_weight, equalization_loss_config=equalization_loss_config, return_raw_detections_during_predict=( ssd_config.return_raw_detections_during_predict), **kwargs)
f.close() num_classes = 20 groundtruth_class = tf.get_variable('groundtruth_class', shape=[24, 5, 20]) groundtruth_box = tf.get_variable('groundtruth_box', shape=[24, 5, 4]) groundtruth_classes_with_background_list = [ tf.pad(one_hot_encoding, [[0, 0], [1, 0]], mode='CONSTANT') for one_hot_encoding in tf.unstack(groundtruth_class) ] groundtruth_boxlists = [ box_list.BoxList(boxes) for boxes in tf.unstack(groundtruth_box) ] # construct models box_coder = box_coder_builder.build(model.ssd.box_coder) matcher = matcher_builder.build(model.ssd.matcher) region_similarity_calculator = sim_calc_builder.build( model.ssd.similarity_calculator) anchor_generator = anchor_generator_builder.build(model.ssd.anchor_generator) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(model.ssd.loss) image_resizer_fn = image_resizer_builder.build(model.ssd.image_resizer) non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( model.ssd.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(model.ssd.loss) normalize_loss_by_num_matches = model.ssd.normalize_loss_by_num_matches matcher = matcher_builder.build(model.ssd.matcher) unmatched_cls_target = tf.constant([1] + num_classes * [0], tf.float32)