def _get_second_stage_box_predictor(self, num_classes, is_training, predict_masks, masks_are_class_agnostic, share_box_across_classes=False, use_keras=False): box_predictor_proto = box_predictor_pb2.BoxPredictor() text_format.Merge( self._get_second_stage_box_predictor_text_proto( share_box_across_classes), 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) if use_keras: return box_predictor_builder.build_keras( hyperparams_builder.KerasLayerHyperparams, inplace_batchnorm_update=False, freeze_batchnorm=False, box_predictor_config=box_predictor_proto, num_classes=num_classes, num_predictions_per_location_list=None, is_training=is_training) else: return box_predictor_builder.build(hyperparams_builder.build, box_predictor_proto, num_classes=num_classes, is_training=is_training)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries): """Builds a Faster R-CNN or R-FCN detection model based on the model config. Builds R-FCN model if the second_stage_box_predictor in the config is of type `rfcn_box_predictor` else builds a Faster R-CNN model. Args: frcnn_config: A faster_rcnn.proto object containing the config for the desired FasterRCNNMetaArch or RFCNMetaArch. is_training: True if this model is being built for training purposes. add_summaries: Whether to add tf summaries in the model. Returns: FasterRCNNMetaArch based on the config. Raises: ValueError: If frcnn_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = frcnn_config.num_classes image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer) is_keras = (frcnn_config.feature_extractor.type in FASTER_RCNN_KERAS_FEATURE_EXTRACTOR_CLASS_MAP) if is_keras: feature_extractor = _build_faster_rcnn_keras_feature_extractor( frcnn_config.feature_extractor, is_training, inplace_batchnorm_update=frcnn_config.inplace_batchnorm_update) else: feature_extractor = _build_faster_rcnn_feature_extractor( frcnn_config.feature_extractor, is_training, inplace_batchnorm_update=frcnn_config.inplace_batchnorm_update) number_of_stages = frcnn_config.number_of_stages first_stage_anchor_generator = anchor_generator_builder.build( frcnn_config.first_stage_anchor_generator) first_stage_target_assigner = target_assigner.create_target_assigner( 'FasterRCNN', 'proposal', use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher) first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate if is_keras: first_stage_box_predictor_arg_scope_fn = ( hyperparams_builder.KerasLayerHyperparams( frcnn_config.first_stage_box_predictor_conv_hyperparams)) else: first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build( frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training) first_stage_box_predictor_kernel_size = ( frcnn_config.first_stage_box_predictor_kernel_size) first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size use_static_shapes = frcnn_config.use_static_shapes and ( frcnn_config.use_static_shapes_for_eval or is_training) first_stage_sampler = sampler.BalancedPositiveNegativeSampler( positive_fraction=frcnn_config.first_stage_positive_balance_fraction, is_static=(frcnn_config.use_static_balanced_label_sampler and use_static_shapes)) first_stage_max_proposals = frcnn_config.first_stage_max_proposals if (frcnn_config.first_stage_nms_iou_threshold < 0 or frcnn_config.first_stage_nms_iou_threshold > 1.0): raise ValueError('iou_threshold not in [0, 1.0].') if (is_training and frcnn_config.second_stage_batch_size > first_stage_max_proposals): raise ValueError('second_stage_batch_size should be no greater than ' 'first_stage_max_proposals.') first_stage_non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=frcnn_config.first_stage_nms_score_threshold, iou_thresh=frcnn_config.first_stage_nms_iou_threshold, max_size_per_class=frcnn_config.first_stage_max_proposals, max_total_size=frcnn_config.first_stage_max_proposals, use_static_shapes=use_static_shapes, use_partitioned_nms=frcnn_config.use_partitioned_nms_in_first_stage, use_combined_nms=frcnn_config.use_combined_nms_in_first_stage) first_stage_loc_loss_weight = ( frcnn_config.first_stage_localization_loss_weight) first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight initial_crop_size = frcnn_config.initial_crop_size maxpool_kernel_size = frcnn_config.maxpool_kernel_size maxpool_stride = frcnn_config.maxpool_stride second_stage_target_assigner = target_assigner.create_target_assigner( 'FasterRCNN', 'detection', use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher) if is_keras: second_stage_box_predictor = box_predictor_builder.build_keras( hyperparams_builder.KerasLayerHyperparams, freeze_batchnorm=False, inplace_batchnorm_update=False, num_predictions_per_location_list=[1], box_predictor_config=frcnn_config.second_stage_box_predictor, is_training=is_training, num_classes=num_classes) else: second_stage_box_predictor = box_predictor_builder.build( hyperparams_builder.build, frcnn_config.second_stage_box_predictor, is_training=is_training, num_classes=num_classes) second_stage_batch_size = frcnn_config.second_stage_batch_size second_stage_sampler = sampler.BalancedPositiveNegativeSampler( positive_fraction=frcnn_config.second_stage_balance_fraction, is_static=(frcnn_config.use_static_balanced_label_sampler and use_static_shapes)) (second_stage_non_max_suppression_fn, second_stage_score_conversion_fn) = post_processing_builder.build( frcnn_config.second_stage_post_processing) second_stage_localization_loss_weight = ( frcnn_config.second_stage_localization_loss_weight) second_stage_classification_loss = ( losses_builder.build_faster_rcnn_classification_loss( frcnn_config.second_stage_classification_loss)) second_stage_classification_loss_weight = ( frcnn_config.second_stage_classification_loss_weight) second_stage_mask_prediction_loss_weight = ( frcnn_config.second_stage_mask_prediction_loss_weight) hard_example_miner = None if frcnn_config.HasField('hard_example_miner'): hard_example_miner = losses_builder.build_hard_example_miner( frcnn_config.hard_example_miner, second_stage_classification_loss_weight, second_stage_localization_loss_weight) crop_and_resize_fn = (ops.matmul_crop_and_resize if frcnn_config.use_matmul_crop_and_resize else ops.native_crop_and_resize) clip_anchors_to_image = (frcnn_config.clip_anchors_to_image) common_kwargs = { 'is_training': is_training, 'num_classes': num_classes, 'image_resizer_fn': image_resizer_fn, 'feature_extractor': feature_extractor, 'number_of_stages': number_of_stages, 'first_stage_anchor_generator': first_stage_anchor_generator, 'first_stage_target_assigner': first_stage_target_assigner, 'first_stage_atrous_rate': first_stage_atrous_rate, 'first_stage_box_predictor_arg_scope_fn': first_stage_box_predictor_arg_scope_fn, 'first_stage_box_predictor_kernel_size': first_stage_box_predictor_kernel_size, 'first_stage_box_predictor_depth': first_stage_box_predictor_depth, 'first_stage_minibatch_size': first_stage_minibatch_size, 'first_stage_sampler': first_stage_sampler, 'first_stage_non_max_suppression_fn': first_stage_non_max_suppression_fn, 'first_stage_max_proposals': first_stage_max_proposals, 'first_stage_localization_loss_weight': first_stage_loc_loss_weight, 'first_stage_objectness_loss_weight': first_stage_obj_loss_weight, 'second_stage_target_assigner': second_stage_target_assigner, 'second_stage_batch_size': second_stage_batch_size, 'second_stage_sampler': second_stage_sampler, 'second_stage_non_max_suppression_fn': second_stage_non_max_suppression_fn, 'second_stage_score_conversion_fn': second_stage_score_conversion_fn, 'second_stage_localization_loss_weight': second_stage_localization_loss_weight, 'second_stage_classification_loss': second_stage_classification_loss, 'second_stage_classification_loss_weight': second_stage_classification_loss_weight, 'hard_example_miner': hard_example_miner, 'add_summaries': add_summaries, 'crop_and_resize_fn': crop_and_resize_fn, 'clip_anchors_to_image': clip_anchors_to_image, 'use_static_shapes': use_static_shapes, 'resize_masks': frcnn_config.resize_masks, 'return_raw_detections_during_predict': (frcnn_config.return_raw_detections_during_predict) } if (isinstance(second_stage_box_predictor, rfcn_box_predictor.RfcnBoxPredictor) or isinstance(second_stage_box_predictor, rfcn_keras_box_predictor.RfcnKerasBoxPredictor)): return rfcn_meta_arch.RFCNMetaArch( second_stage_rfcn_box_predictor=second_stage_box_predictor, **common_kwargs) else: return faster_rcnn_meta_arch.FasterRCNNMetaArch( initial_crop_size=initial_crop_size, maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, second_stage_mask_rcnn_box_predictor=second_stage_box_predictor, second_stage_mask_prediction_loss_weight=( second_stage_mask_prediction_loss_weight), **common_kwargs)
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)
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): """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)