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) feature_extractor = _build_faster_rcnn_feature_extractor( frcnn_config.feature_extractor, is_training, 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_atrous_rate = frcnn_config.first_stage_atrous_rate 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 first_stage_positive_balance_fraction = ( frcnn_config.first_stage_positive_balance_fraction) first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold first_stage_max_proposals = frcnn_config.first_stage_max_proposals 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_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_balance_fraction = frcnn_config.second_stage_balance_fraction (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) 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_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_positive_balance_fraction': first_stage_positive_balance_fraction, 'first_stage_nms_score_threshold': first_stage_nms_score_threshold, 'first_stage_nms_iou_threshold': first_stage_nms_iou_threshold, '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_batch_size': second_stage_batch_size, 'second_stage_balance_fraction': second_stage_balance_fraction, '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 } if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor): 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 _get_model(self, box_predictor, **common_kwargs): return rfcn_meta_arch.RFCNMetaArch( second_stage_rfcn_box_predictor=box_predictor, **common_kwargs)
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) feature_extractor = _build_faster_rcnn_feature_extractor( frcnn_config.feature_extractor, is_training, 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 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 # TODO(bhattad): When eval is supported using static shapes, add separate # use_static_shapes_for_trainig and use_static_shapes_for_evaluation. use_static_shapes = frcnn_config.use_static_shapes and 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 is_training) 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 and is_training) 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) 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 is_training) (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 } if isinstance(second_stage_box_predictor, rfcn_box_predictor.RfcnBoxPredictor): 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_faster_rcnn_model(frcnn_config, is_training, add_summaries, **kwargs): """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. kwargs: key-value 'rpn_type' is the type of rpn which is 'cascade_rpn','orign_rpn' and 'without_rpn' which need some boxes replacing the proposal generated by rpn 'filter_fn_arg' is the args of filter fn which need the boxes to filter the proposals. 'replace_rpn_arg' is a dictionary. only if the rpn_type=='without_rpn' and not None, it's useful in order to replace the proposals generated by rpn with the gt which maybe adjusted. 'type': a string which is 'gt' or 'others'. 'scale': a float which is used to scale the boxes(maybe gt). 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) 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 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) 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) 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 } filter_fn_arg = kwargs.get('filter_fn_arg') if filter_fn_arg: filter_fn = functools.partial(filter_bbox, **filter_fn_arg) common_kwargs['filter_fn'] = filter_fn rpn_type = kwargs.get('rpn_type') if rpn_type: common_kwargs['rpn_type'] = rpn_type replace_rpn_arg = kwargs.get('replace_rpn_arg') if replace_rpn_arg: common_kwargs['replace_rpn_arg'] = replace_rpn_arg if isinstance(second_stage_box_predictor, rfcn_box_predictor.RfcnBoxPredictor): 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)
'first_stage_box_predictor_depth': first_stage_box_predictor_depth, #Output depth for the convolution op just prior to RPN box predictions 'first_stage_minibatch_size': first_stage_minibatch_size, 'first_stage_positive_balance_fraction': first_stage_positive_balance_fraction, 'first_stage_nms_score_threshold': first_stage_nms_score_threshold, 'first_stage_nms_iou_threshold': first_stage_nms_iou_threshold, '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_batch_size': second_stage_batch_size, 'second_stage_balance_fraction': second_stage_balance_fraction, '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_weight': second_stage_classification_loss_weight, 'hard_example_miner': hard_example_miner} if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor): #this in not our intance is MaskRCNNBoxPredictor return rfcn_meta_arch.RFCNMetaArch( second_stage_rfcn_box_predictor=second_stage_box_predictor, **common_kwargs) else: return faster_rcnn_meta_arch.FasterRCNNMetaArch( #this is what we use in faster rcnn ##IN the faster Rcnn meta arch py maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, #this class object will later used to create the model second_stage_mask_rcnn_box_predictor=second_stage_box_predictor, **common_kwargs)
def _build_faster_rcnn_model(frcnn_config, is_training, mtl=None): """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. 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) feature_extractor_kwargs = {} feature_extractor_kwargs[ 'freeze_layer'] = frcnn_config.feature_extractor.freeze_layer feature_extractor_kwargs[ 'batch_norm_trainable'] = frcnn_config.feature_extractor.batch_norm_trainable if frcnn_config.feature_extractor.HasField('weight_decay'): feature_extractor_kwargs['weight_decay'] = \ frcnn_config.feature_extractor.weight_decay feature_extractor = _build_faster_rcnn_feature_extractor( frcnn_config.feature_extractor, is_training and frcnn_config.feature_extractor.trainable, reuse_weights=tf.AUTO_REUSE, **feature_extractor_kwargs) first_stage_only = frcnn_config.first_stage_only first_stage_anchor_generator = anchor_generator_builder.build( frcnn_config.first_stage_anchor_generator) first_stage_clip_window = frcnn_config.first_stage_clip_window first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate first_stage_box_predictor_trainable = \ frcnn_config.first_stage_box_predictor_trainable first_stage_box_predictor_arg_scope = 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 first_stage_positive_balance_fraction = ( frcnn_config.first_stage_positive_balance_fraction) first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold first_stage_max_proposals = frcnn_config.first_stage_max_proposals 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_box_predictor = box_predictor_builder.build( hyperparams_builder.build, frcnn_config.second_stage_box_predictor, is_training=is_training and frcnn_config.second_stage_box_predictor.trainable, num_classes=num_classes, reuse_weights=tf.AUTO_REUSE) second_stage_batch_size = frcnn_config.second_stage_batch_size second_stage_balance_fraction = frcnn_config.second_stage_balance_fraction (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_weight = ( frcnn_config.second_stage_classification_loss_weight) if mtl.window: window_box_predictor = box_predictor_builder.build( hyperparams_builder.build, mtl.window_box_predictor, is_training=is_training and mtl.window_box_predictor.trainable, num_classes=num_classes + 1, reuse_weights=tf.AUTO_REUSE) else: window_box_predictor = second_stage_box_predictor if mtl.closeness: closeness_box_predictor = box_predictor_builder.build( hyperparams_builder.build, mtl.closeness_box_predictor, is_training=is_training and mtl.closeness_box_predictor.trainable, num_classes=num_classes + 1, reuse_weights=tf.AUTO_REUSE) else: closeness_box_predictor = second_stage_box_predictor if mtl.edgemask: edgemask_predictor = mask_predictor_builder.build( hyperparams_builder.build, mtl.edgemask_predictor, is_training=is_training and mtl.edgemask_predictor.trainable, num_classes=2, reuse_weights=tf.AUTO_REUSE, channels=1) else: edgemask_predictor = None mtl_refiner_arg_scope = None if mtl.refine: mtl_refiner_arg_scope = hyperparams_builder.build( mtl.refiner_fc_hyperparams, is_training) 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) common_kwargs = { 'is_training': is_training, 'num_classes': num_classes, 'image_resizer_fn': image_resizer_fn, 'feature_extractor': feature_extractor, 'first_stage_only': first_stage_only, 'first_stage_anchor_generator': first_stage_anchor_generator, 'first_stage_clip_window': first_stage_clip_window, 'first_stage_atrous_rate': first_stage_atrous_rate, 'first_stage_box_predictor_trainable': first_stage_box_predictor_trainable, 'first_stage_box_predictor_arg_scope': first_stage_box_predictor_arg_scope, '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_positive_balance_fraction': first_stage_positive_balance_fraction, 'first_stage_nms_score_threshold': first_stage_nms_score_threshold, 'first_stage_nms_iou_threshold': first_stage_nms_iou_threshold, '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_batch_size': second_stage_batch_size, 'second_stage_balance_fraction': second_stage_balance_fraction, '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_weight': second_stage_classification_loss_weight, 'hard_example_miner': hard_example_miner, 'mtl': mtl, 'mtl_refiner_arg_scope': mtl_refiner_arg_scope, 'window_box_predictor': window_box_predictor, 'closeness_box_predictor': closeness_box_predictor, 'edgemask_predictor': edgemask_predictor } if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor): 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, **common_kwargs)
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) _check_feature_extractor_exists(frcnn_config.feature_extractor.type) is_keras = tf_version.is_tf2() 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 = (spatial_ops.multilevel_matmul_crop_and_resize if frcnn_config.use_matmul_crop_and_resize else spatial_ops.multilevel_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, 'output_final_box_features': frcnn_config.output_final_box_features, 'output_final_box_rpn_features': frcnn_config.output_final_box_rpn_features, } if ((not is_keras and isinstance(second_stage_box_predictor, rfcn_box_predictor.RfcnBoxPredictor)) or (is_keras and 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) elif frcnn_config.HasField('context_config'): context_config = frcnn_config.context_config common_kwargs.update({ 'attention_bottleneck_dimension': context_config.attention_bottleneck_dimension, 'attention_temperature': context_config.attention_temperature, 'use_self_attention': context_config.use_self_attention, 'use_long_term_attention': context_config.use_long_term_attention, 'self_attention_in_sequence': context_config.self_attention_in_sequence, 'num_attention_heads': context_config.num_attention_heads, 'num_attention_layers': context_config.num_attention_layers, 'attention_position': context_config.attention_position }) return context_rcnn_meta_arch.ContextRCNNMetaArch( 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) 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_sin_model(sin_config, is_training): """Builds a SIN detection model based on the model config. Args: sin_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. Returns: SINMetaArch based on the config. Raises: ValueError: If sin_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = sin_config.num_classes image_resizer_fn = image_resizer_builder.build(sin_config.image_resizer) feature_extractor = _build_faster_rcnn_feature_extractor( sin_config.feature_extractor, is_training, reuse_weights=tf.AUTO_REUSE) fc_hyperparams = hyperparams_builder.build( sin_config.second_stage_box_predictor.sin_box_predictor.fc_hyperparams, is_training) first_stage_only = sin_config.first_stage_only first_stage_anchor_generator = anchor_generator_builder.build( sin_config.first_stage_anchor_generator) first_stage_atrous_rate = sin_config.first_stage_atrous_rate first_stage_box_predictor_arg_scope = hyperparams_builder.build( sin_config.first_stage_box_predictor_conv_hyperparams, is_training) first_stage_box_predictor_kernel_size = ( sin_config.first_stage_box_predictor_kernel_size) first_stage_box_predictor_depth = sin_config.first_stage_box_predictor_depth first_stage_minibatch_size = sin_config.first_stage_minibatch_size first_stage_positive_balance_fraction = ( sin_config.first_stage_positive_balance_fraction) first_stage_nms_score_threshold = sin_config.first_stage_nms_score_threshold first_stage_nms_iou_threshold = sin_config.first_stage_nms_iou_threshold first_stage_max_proposals = sin_config.first_stage_max_proposals first_stage_loc_loss_weight = ( sin_config.first_stage_localization_loss_weight) first_stage_obj_loss_weight = sin_config.first_stage_objectness_loss_weight initial_crop_size = sin_config.initial_crop_size maxpool_kernel_size = sin_config.maxpool_kernel_size maxpool_stride = sin_config.maxpool_stride second_stage_box_predictor = box_predictor_builder.build( hyperparams_builder.build, sin_config.second_stage_box_predictor, is_training=is_training, num_classes=num_classes) second_stage_batch_size = sin_config.second_stage_batch_size second_stage_balance_fraction = sin_config.second_stage_balance_fraction (second_stage_non_max_suppression_fn, second_stage_score_conversion_fn ) = post_processing_builder.build(sin_config.second_stage_post_processing) second_stage_localization_loss_weight = ( sin_config.second_stage_localization_loss_weight) second_stage_classification_loss = ( losses_builder.build_faster_rcnn_classification_loss( sin_config.second_stage_classification_loss)) second_stage_classification_loss_weight = ( sin_config.second_stage_classification_loss_weight) second_stage_mask_prediction_loss_weight = ( sin_config.second_stage_mask_prediction_loss_weight) hard_example_miner = None if sin_config.HasField('hard_example_miner'): hard_example_miner = losses_builder.build_hard_example_miner( sin_config.hard_example_miner, second_stage_classification_loss_weight, second_stage_localization_loss_weight) common_kwargs = { 'is_training': is_training, 'num_classes': num_classes, 'image_resizer_fn': image_resizer_fn, 'feature_extractor': feature_extractor, 'fc_hyperparams': fc_hyperparams, 'first_stage_only': first_stage_only, 'first_stage_anchor_generator': first_stage_anchor_generator, 'first_stage_atrous_rate': first_stage_atrous_rate, 'first_stage_box_predictor_arg_scope': first_stage_box_predictor_arg_scope, '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_positive_balance_fraction': first_stage_positive_balance_fraction, 'first_stage_nms_score_threshold': first_stage_nms_score_threshold, 'first_stage_nms_iou_threshold': first_stage_nms_iou_threshold, '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_batch_size': second_stage_batch_size, 'second_stage_balance_fraction': second_stage_balance_fraction, '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} if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor): return rfcn_meta_arch.RFCNMetaArch( second_stage_rfcn_box_predictor=second_stage_box_predictor, **common_kwargs) else: return sin_meta_arch.SINMetaArch( initial_crop_size=initial_crop_size, maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, second_stage_box_predictor=second_stage_box_predictor, second_stage_mask_prediction_loss_weight=( second_stage_mask_prediction_loss_weight), **common_kwargs)