def test_build_softmax_score_converter(self): post_processing_text_proto = """ score_converter: SOFTMAX """ post_processing_config = post_processing_pb2.PostProcessing() text_format.Merge(post_processing_text_proto, post_processing_config) _, score_converter = post_processing_builder.build( post_processing_config) self.assertEqual(score_converter.__name__, 'softmax_with_logit_scale')
def test_build_identity_score_converter(self): post_processing_text_proto = """ score_converter: IDENTITY """ post_processing_config = post_processing_pb2.PostProcessing() text_format.Merge(post_processing_text_proto, post_processing_config) _, score_converter = post_processing_builder.build( post_processing_config) self.assertEqual(score_converter.__name__, 'identity_with_logit_scale') inputs = tf.constant([1, 1], tf.float32) outputs = score_converter(inputs) with self.test_session() as sess: converted_scores = sess.run(outputs) expected_converted_scores = sess.run(inputs) self.assertAllClose(converted_scores, expected_converted_scores)
def test_build_non_max_suppressor_with_correct_parameters(self): post_processing_text_proto = """ batch_non_max_suppression { score_threshold: 0.7 iou_threshold: 0.6 max_detections_per_class: 100 max_total_detections: 300 } """ post_processing_config = post_processing_pb2.PostProcessing() text_format.Merge(post_processing_text_proto, post_processing_config) non_max_suppressor, _ = post_processing_builder.build( post_processing_config) self.assertEqual(non_max_suppressor.keywords['max_size_per_class'], 100) self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300) self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'], 0.7) self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6)
def _build_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, 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 } 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_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, 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 export_tflite_graph(pipeline_config, trained_checkpoint_prefix, output_dir, add_postprocessing_op, max_detections, max_classes_per_detection, detections_per_class=100, use_regular_nms=False): """Exports a tflite compatible graph and anchors for ssd detection model. Anchors are written to a tensor and tflite compatible graph is written to output_dir/tflite_graph.pb. Args: pipeline_config: a pipeline.proto object containing the configuration for SSD model to export. trained_checkpoint_prefix: a file prefix for the checkpoint containing the trained parameters of the SSD model. output_dir: A directory to write the tflite graph and anchor file to. add_postprocessing_op: If add_postprocessing_op is true: frozen graph adds a TFLite_Detection_PostProcess custom op max_detections: Maximum number of detections (boxes) to show max_classes_per_detection: Number of classes to display per detection detections_per_class: In regular NonMaxSuppression, number of anchors used for NonMaxSuppression per class use_regular_nms: Flag to set postprocessing op to use Regular NMS instead of Fast NMS. Raises: ValueError: if the pipeline config contains models other than ssd or uses an fixed_shape_resizer and provides a shape as well. """ tf.gfile.MakeDirs(output_dir) if pipeline_config.model.WhichOneof('model') != 'ssd': raise ValueError('Only ssd models are supported in tflite. ' 'Found {} in config'.format( pipeline_config.model.WhichOneof('model'))) num_classes = pipeline_config.model.ssd.num_classes nms_score_threshold = { pipeline_config.model.ssd.post_processing.batch_non_max_suppression. score_threshold } nms_iou_threshold = { pipeline_config.model.ssd.post_processing.batch_non_max_suppression. iou_threshold } scale_values = {} scale_values['y_scale'] = { pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.y_scale } scale_values['x_scale'] = { pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.x_scale } scale_values['h_scale'] = { pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.height_scale } scale_values['w_scale'] = { pipeline_config.model.ssd.box_coder.faster_rcnn_box_coder.width_scale } image_resizer_config = pipeline_config.model.ssd.image_resizer image_resizer = image_resizer_config.WhichOneof('image_resizer_oneof') num_channels = _DEFAULT_NUM_CHANNELS if image_resizer == 'fixed_shape_resizer': height = image_resizer_config.fixed_shape_resizer.height width = image_resizer_config.fixed_shape_resizer.width if image_resizer_config.fixed_shape_resizer.convert_to_grayscale: num_channels = 1 shape = [1, height, width, num_channels] else: raise ValueError( 'Only fixed_shape_resizer' 'is supported with tflite. Found {}'.format( image_resizer_config.WhichOneof('image_resizer_oneof'))) image = tf.placeholder(tf.float32, shape=shape, name='normalized_input_image_tensor') detection_model = model_builder.build(pipeline_config.model, is_training=False) predicted_tensors = detection_model.predict(image, true_image_shapes=None) # The score conversion occurs before the post-processing custom op _, score_conversion_fn = post_processing_builder.build( pipeline_config.model.ssd.post_processing) class_predictions = score_conversion_fn( predicted_tensors['class_predictions_with_background']) with tf.name_scope('raw_outputs'): # 'raw_outputs/box_encodings': a float32 tensor of shape [1, num_anchors, 4] # containing the encoded box predictions. Note that these are raw # predictions and no Non-Max suppression is applied on them and # no decode center size boxes is applied to them. tf.identity(predicted_tensors['box_encodings'], name='box_encodings') # 'raw_outputs/class_predictions': a float32 tensor of shape # [1, num_anchors, num_classes] containing the class scores for each anchor # after applying score conversion. tf.identity(class_predictions, name='class_predictions') # 'anchors': a float32 tensor of shape # [4, num_anchors] containing the anchors as a constant node. tf.identity(get_const_center_size_encoded_anchors( predicted_tensors['anchors']), name='anchors') # Add global step to the graph, so we know the training step number when we # evaluate the model. tf.train.get_or_create_global_step() # graph rewriter is_quantized = pipeline_config.HasField('graph_rewriter') if is_quantized: graph_rewriter_config = pipeline_config.graph_rewriter graph_rewriter_fn = graph_rewriter_builder.build(graph_rewriter_config, is_training=False) graph_rewriter_fn() if pipeline_config.model.ssd.feature_extractor.HasField('fpn'): exporter.rewrite_nn_resize_op(is_quantized) # freeze the graph saver_kwargs = {} if pipeline_config.eval_config.use_moving_averages: saver_kwargs['write_version'] = saver_pb2.SaverDef.V1 moving_average_checkpoint = tempfile.NamedTemporaryFile() exporter.replace_variable_values_with_moving_averages( tf.get_default_graph(), trained_checkpoint_prefix, moving_average_checkpoint.name) checkpoint_to_use = moving_average_checkpoint.name else: checkpoint_to_use = trained_checkpoint_prefix saver = tf.train.Saver(**saver_kwargs) input_saver_def = saver.as_saver_def() frozen_graph_def = exporter.freeze_graph_with_def_protos( input_graph_def=tf.get_default_graph().as_graph_def(), input_saver_def=input_saver_def, input_checkpoint=checkpoint_to_use, output_node_names=','.join([ 'raw_outputs/box_encodings', 'raw_outputs/class_predictions', 'anchors' ]), restore_op_name='save/restore_all', filename_tensor_name='save/Const:0', clear_devices=True, output_graph='', initializer_nodes='') # Add new operation to do post processing in a custom op (TF Lite only) if add_postprocessing_op: transformed_graph_def = append_postprocessing_op( frozen_graph_def, max_detections, max_classes_per_detection, nms_score_threshold, nms_iou_threshold, num_classes, scale_values, detections_per_class, use_regular_nms) else: # Return frozen without adding post-processing custom op transformed_graph_def = frozen_graph_def binary_graph = os.path.join(output_dir, 'tflite_graph.pb') with tf.gfile.GFile(binary_graph, 'wb') as f: f.write(transformed_graph_def.SerializeToString()) txt_graph = os.path.join(output_dir, 'tflite_graph.pbtxt') with tf.gfile.GFile(txt_graph, 'w') as f: f.write(str(transformed_graph_def))