def test_raise_value_error_on_empty_anchor_genertor(self): anchor_generator_text_proto = """ """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) with self.assertRaises(ValueError): anchor_generator_builder.build(anchor_generator_proto)
def test_build_ssd_anchor_generator_without_reduced_boxes(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [1.0] reduce_boxes_in_lowest_layer: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertIsInstance( anchor_generator_object, multiple_grid_anchor_generator.MultipleGridAnchorGenerator) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.2, 0.264), (0.35, 0.418), (0.499, 0.570), (0.649, 0.721), (0.799, 0.871), (0.949, 0.974)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), 6 * [(1.0, 1.0)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) self.assertAllClose(anchor_generator_object._base_anchor_size, [1.0, 1.0])
def test_build_ssd_anchor_generator_without_reduced_boxes(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [1.0] reduce_boxes_in_lowest_layer: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.2, 0.264), (0.35, 0.418), (0.499, 0.570), (0.649, 0.721), (0.799, 0.871), (0.949, 0.974)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), 6 * [(1.0, 1.0)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) self.assertAllClose(anchor_generator_object._base_anchor_size, [1.0, 1.0])
def test_build_grid_anchor_generator_with_non_default_parameters(self): anchor_generator_text_proto = """ grid_anchor_generator { height: 128 width: 512 height_stride: 10 width_stride: 20 height_offset: 30 width_offset: 40 scales: [0.4, 2.2] aspect_ratios: [0.3, 4.5] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, grid_anchor_generator.GridAnchorGenerator)) self.assert_almost_list_equal(anchor_generator_object._scales, [0.4, 2.2]) self.assert_almost_list_equal(anchor_generator_object._aspect_ratios, [0.3, 4.5]) with self.test_session() as sess: base_anchor_size, anchor_offset, anchor_stride = sess.run( [anchor_generator_object._base_anchor_size, anchor_generator_object._anchor_offset, anchor_generator_object._anchor_stride]) self.assertAllEqual(anchor_offset, [30, 40]) self.assertAllEqual(anchor_stride, [10, 20]) self.assertAllEqual(base_anchor_size, [128, 512])
def test_build_ssd_anchor_generator_with_defaults(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [1.0] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, 0.2, 0.2), (0.35, 0.418), (0.499, 0.570), (0.649, 0.721), (0.799, 0.871), (0.949, 0.974)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5)] + 5 * [(1.0, 1.0)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) with self.test_session() as sess: base_anchor_size = sess.run(anchor_generator_object._base_anchor_size) self.assertAllClose(base_anchor_size, [1.0, 1.0])
def test_build_ssd_anchor_generator_with_non_default_parameters(self): anchor_generator_text_proto = """ ssd_anchor_generator { num_layers: 2 min_scale: 0.3 max_scale: 0.8 aspect_ratios: [2.0] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue( isinstance( anchor_generator_object, multiple_grid_anchor_generator.MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, 0.3, 0.3), (0.8, )]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5), (2.0, )]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) with self.test_session() as sess: base_anchor_size = sess.run( anchor_generator_object._base_anchor_size) self.assertAllClose(base_anchor_size, [1.0, 1.0])
def test_build_multiscale_anchor_generator_custom_aspect_ratios(self): anchor_generator_text_proto = """ multiscale_anchor_generator { aspect_ratios: [1.0] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue( isinstance( anchor_generator_object, multiscale_grid_anchor_generator. MultiscaleGridAnchorGenerator)) for level, anchor_grid_info in zip( range(3, 8), anchor_generator_object._anchor_grid_info): self.assertEqual(set(anchor_grid_info.keys()), set(['level', 'info'])) self.assertTrue(level, anchor_grid_info['level']) self.assertEqual(len(anchor_grid_info['info']), 4) self.assertAllClose(anchor_grid_info['info'][0], [2**0, 2**0.5]) self.assertTrue(anchor_grid_info['info'][1], 1.0) self.assertAllClose(anchor_grid_info['info'][2], [4.0 * 2**level, 4.0 * 2**level]) self.assertAllClose(anchor_grid_info['info'][3], [2**level, 2**level])
def test_build_grid_anchor_generator_with_non_default_parameters(self): anchor_generator_text_proto = """ grid_anchor_generator { height: 128 width: 512 height_stride: 10 width_stride: 20 height_offset: 30 width_offset: 40 scales: [0.4, 2.2] aspect_ratios: [0.3, 4.5] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue( isinstance(anchor_generator_object, grid_anchor_generator.GridAnchorGenerator)) self.assert_almost_list_equal(anchor_generator_object._scales, [0.4, 2.2]) self.assert_almost_list_equal(anchor_generator_object._aspect_ratios, [0.3, 4.5]) with self.test_session() as sess: base_anchor_size, anchor_offset, anchor_stride = sess.run([ anchor_generator_object._base_anchor_size, anchor_generator_object._anchor_offset, anchor_generator_object._anchor_stride ]) self.assertAllEqual(anchor_offset, [30, 40]) self.assertAllEqual(anchor_stride, [10, 20]) self.assertAllEqual(base_anchor_size, [128, 512])
def test_build_ssd_anchor_generator_with_defaults(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [1.0] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue( isinstance( anchor_generator_object, multiple_grid_anchor_generator.MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, 0.2, 0.2), (0.35, 0.418), (0.499, 0.570), (0.649, 0.721), (0.799, 0.871), (0.949, 0.974)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5)] + 5 * [(1.0, 1.0)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) with self.test_session() as sess: base_anchor_size = sess.run( anchor_generator_object._base_anchor_size) self.assertAllClose(base_anchor_size, [1.0, 1.0])
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 contains a method named "match" to return a "Match" Object. matcher = matcher_builder.build(ssd_config.matcher) # region_similarity_calculator.compare: return a tensor with shape [N, M] representing the IOA/IOU score, etc. region_similarity_calculator = sim_calc.build( ssd_config.similarity_calculator) # ssd_box_predictor.predict: returns a prediction dictionary ssd_box_predictor = box_predictor_builder.build(hyperparams_builder.build, ssd_config.box_predictor, is_training, num_classes) # anchor_generator: is MultipleGridAnchorGenerator object are always in normalized coordinate # Usage: anchor_generator.generate: Generates a collection of bounding boxes to be used as anchors. 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_ssd_anchor_generator_with_non_default_parameters(self): anchor_generator_text_proto = """ ssd_anchor_generator { num_layers: 2 min_scale: 0.3 max_scale: 0.8 aspect_ratios: [2.0] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, 0.3, 0.3), (0.8,)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5), (2.0,)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) with self.test_session() as sess: base_anchor_size = sess.run(anchor_generator_object._base_anchor_size) self.assertAllClose(base_anchor_size, [1.0, 1.0])
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) encode_background_as_zeros = ssd_config.encode_background_as_zeros 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, encode_background_as_zeros, 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 _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 _build_sssfd_model(sssfd_config, is_training, add_summaries, add_background_class=True): num_classes = sssfd_config.num_classes # Feature extractor feature_extractor = _build_sssfd_feature_extractor( feature_extractor_config=sssfd_config.feature_extractor, is_training=is_training) box_coder = box_coder_builder.build(sssfd_config.box_coder) matcher = matcher_builder.build(sssfd_config.matcher) region_similarity_calculator = sim_calc.build( sssfd_config.similarity_calculator) encode_background_as_zeros = sssfd_config.encode_background_as_zeros negative_class_weight = sssfd_config.negative_class_weight sssfd_box_predictor = box_predictor_builder.build( hyperparams_builder.build, sssfd_config.box_predictor, is_training, num_classes) anchor_generator = anchor_generator_builder.build( sssfd_config.anchor_generator) image_resizer_fn = image_resizer_builder.build(sssfd_config.image_resizer) non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( sssfd_config.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner, random_example_sampler) = losses_builder.build(sssfd_config.loss) normalize_loss_by_num_matches = sssfd_config.normalize_loss_by_num_matches normalize_loc_loss_by_codesize = sssfd_config.normalize_loc_loss_by_codesize return ssd_meta_arch.SSDMetaArch( is_training, anchor_generator, sssfd_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=sssfd_config.freeze_batchnorm, inplace_batchnorm_update=sssfd_config.inplace_batchnorm_update, add_background_class=add_background_class, random_example_sampler=random_example_sampler)
def test_build_flexible_anchor_generator(self): anchor_generator_text_proto = """ flexible_grid_anchor_generator { anchor_grid { base_sizes: [1.5] aspect_ratios: [1.0] height_stride: 16 width_stride: 20 height_offset: 8 width_offset: 9 } anchor_grid { base_sizes: [1.0, 2.0] aspect_ratios: [1.0, 0.5] height_stride: 32 width_stride: 30 height_offset: 10 width_offset: 11 } } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertIsInstance( anchor_generator_object, flexible_grid_anchor_generator.FlexibleGridAnchorGenerator) for actual_base_sizes, expected_base_sizes in zip( list(anchor_generator_object._base_sizes), [(1.5, ), (1.0, 2.0)]): self.assert_almost_list_equal(expected_base_sizes, actual_base_sizes) for actual_aspect_ratios, expected_aspect_ratios in zip( list(anchor_generator_object._aspect_ratios), [(1.0, ), (1.0, 0.5)]): self.assert_almost_list_equal(expected_aspect_ratios, actual_aspect_ratios) for actual_strides, expected_strides in zip( list(anchor_generator_object._anchor_strides), [(16, 20), (32, 30)]): self.assert_almost_list_equal(expected_strides, actual_strides) for actual_offsets, expected_offsets in zip( list(anchor_generator_object._anchor_offsets), [(8, 9), (10, 11)]): self.assert_almost_list_equal(expected_offsets, actual_offsets) self.assertTrue(anchor_generator_object._normalize_coordinates)
def test_build_ssd_anchor_generator_with_non_default_parameters(self): anchor_generator_text_proto = """ ssd_anchor_generator { num_layers: 2 min_scale: 0.3 max_scale: 0.8 aspect_ratios: [2.0] height_stride: 16 height_stride: 32 width_stride: 20 width_stride: 30 height_offset: 8 height_offset: 16 width_offset: 0 width_offset: 10 } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue( isinstance( anchor_generator_object, multiple_grid_anchor_generator.MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, 0.3, 0.3), (0.8, 0.894)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5), (2.0, 1.0)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) for actual_strides, expected_strides in zip( list(anchor_generator_object._anchor_strides), [(16, 20), (32, 30)]): self.assert_almost_list_equal(expected_strides, actual_strides) for actual_offsets, expected_offsets in zip( list(anchor_generator_object._anchor_offsets), [(8, 0), (16, 10)]): self.assert_almost_list_equal(expected_offsets, actual_offsets) self.assertAllClose(anchor_generator_object._base_anchor_size, [1.0, 1.0])
def _build_faster_rcnn_model(frcnn_config, is_training): #parameters are config of the faster RCNN """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). """ #The config file consist of the the model parammeters num_classes = frcnn_config.num_classes #getting the classes image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer) #returns - image_resizer_fn: Callable for image resizing feature_extractor = _build_faster_rcnn_feature_extractor( #create the feature extractor frcnn_config.feature_extractor, is_training) #this will take the part of the resnet as a feature extrator first_stage_only = frcnn_config.first_stage_only #No field in faser Rcnn config file Since this is fale this is comple faster Rcnn first_stage_anchor_generator = anchor_generator_builder.build( #here the anchor generator model preparation frcnn_config.first_stage_anchor_generator) #here inside the model we get the first_stage_anchor_generator and with that we go to the it's params #In above 3 outputs we get 3 functions capable of doing aboive tasks ! first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate #not in the config file first_stage_box_predictor_arg_scope = hyperparams_builder.build( #hyper parameters builder for first stage rpn network frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training) first_stage_box_predictor_kernel_size = ( #This predicts the first stage conv window on the feature map of RON frcnn_config.first_stage_box_predictor_kernel_size) #not given first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth #not given #Output depth for the convolution op just prior to RPN box predictions first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size # What is the bathc size first_stage_positive_balance_fraction = ( #balance of the positive examples any way not given frcnn_config.first_stage_positive_balance_fraction)
def test_build_grid_anchor_generator_with_defaults(self): anchor_generator_text_proto = """ grid_anchor_generator { } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, grid_anchor_generator.GridAnchorGenerator)) self.assertListEqual(anchor_generator_object._scales, []) self.assertListEqual(anchor_generator_object._aspect_ratios, []) self.assertAllEqual(anchor_generator_object._anchor_offset, [0, 0]) self.assertAllEqual(anchor_generator_object._anchor_stride, [16, 16]) self.assertAllEqual(anchor_generator_object._base_anchor_size, [256, 256])
def test_build_multiscale_anchor_generator_with_anchors_in_pixel_coordinates( self): anchor_generator_text_proto = """ multiscale_anchor_generator { aspect_ratios: [1.0] normalize_coordinates: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiscale_grid_anchor_generator. MultiscaleGridAnchorGenerator)) self.assertFalse(anchor_generator_object._normalize_coordinates)
def test_build_multiscale_anchor_generator_with_anchors_in_pixel_coordinates( self): anchor_generator_text_proto = """ multiscale_anchor_generator { aspect_ratios: [1.0] normalize_coordinates: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertIsInstance( anchor_generator_object, multiscale_grid_anchor_generator.MultiscaleGridAnchorGenerator) self.assertFalse(anchor_generator_object._normalize_coordinates)
def test_build_grid_anchor_generator_with_defaults(self): anchor_generator_text_proto = """ grid_anchor_generator { } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertIsInstance(anchor_generator_object, grid_anchor_generator.GridAnchorGenerator) self.assertListEqual(anchor_generator_object._scales, []) self.assertListEqual(anchor_generator_object._aspect_ratios, []) self.assertAllEqual(anchor_generator_object._anchor_offset, [0, 0]) self.assertAllEqual(anchor_generator_object._anchor_stride, [16, 16]) self.assertAllEqual(anchor_generator_object._base_anchor_size, [256, 256])
def test_build_ssd_anchor_generator_with_non_default_parameters(self): anchor_generator_text_proto = """ ssd_anchor_generator { num_layers: 2 min_scale: 0.3 max_scale: 0.8 aspect_ratios: [2.0] height_stride: 16 height_stride: 32 width_stride: 20 width_stride: 30 height_offset: 8 height_offset: 16 width_offset: 0 width_offset: 10 } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, 0.3, 0.3), (0.8, 0.894)]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5), (2.0, 1.0)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio) for actual_strides, expected_strides in zip( list(anchor_generator_object._anchor_strides), [(16, 20), (32, 30)]): self.assert_almost_list_equal(expected_strides, actual_strides) for actual_offsets, expected_offsets in zip( list(anchor_generator_object._anchor_offsets), [(8, 0), (16, 10)]): self.assert_almost_list_equal(expected_offsets, actual_offsets) self.assertAllClose(anchor_generator_object._base_anchor_size, [1.0, 1.0])
def test_build_ssd_anchor_generator_with_custom_interpolated_scale(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [0.5] interpolated_scale_aspect_ratio: 0.5 reduce_boxes_in_lowest_layer: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertIsInstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), 6 * [(0.5, 0.5)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
def _build_yolo_model(yolo_config, is_training): """Builds an YOLO detection model based on the model config. Args: yolo_config: A yolo.proto object containing the config for the desired YOLOMetaArch. is_training: True if this model is being built for training purposes. Returns: YOLOMetaArch based on the config. Raises: ValueError: If yolo_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = yolo_config.num_classes # Feature extractor feature_extractor = _build_yolo_feature_extractor( yolo_config.feature_extractor, is_training) box_coder = box_coder_builder.build(yolo_config.box_coder) matcher = matcher_builder.build(yolo_config.matcher) region_similarity_calculator = sim_calc.build( yolo_config.similarity_calculator) yolo_box_predictor = box_predictor_builder.build(hyperparams_builder.build, yolo_config.box_predictor, is_training, num_classes) anchor_generator = anchor_generator_builder.build( yolo_config.anchor_generator) image_resizer_fn = image_resizer_builder.build(yolo_config.image_resizer) non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( yolo_config.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(yolo_config.loss) normalize_loss_by_num_matches = yolo_config.normalize_loss_by_num_matches return yolo_meta_arch.YOLOMetaArch( is_training, anchor_generator, yolo_box_predictor, box_coder, feature_extractor, matcher, region_similarity_calculator, image_resizer_fn, non_max_suppression_fn, score_conversion_fn, classification_loss, localization_loss, classification_weight, localization_weight, normalize_loss_by_num_matches, hard_example_miner)
def test_build_ssd_anchor_generator_with_custom_interpolated_scale(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [0.5] interpolated_scale_aspect_ratio: 0.5 reduce_boxes_in_lowest_layer: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator)) for actual_aspect_ratio, expected_aspect_ratio in zip( list(anchor_generator_object._aspect_ratios), 6 * [(0.5, 0.5)]): self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
def _build_east_model(east_config, is_training): """Builds an EAST detection model based on the model config. Args: east_config: A east.proto object containing the config for the desired SSDMetaArch. is_training: True if this model is being built for training purposes. Returns: EASTMetaArch based on the config. Raises: ValueError: If east_config.type is not recognized (i.e. not registered in model_class_map). """ num_classes = east_config.num_classes # Feature extractor feature_extractor = _build_east_feature_extractor( east_config.feature_extractor, is_training) box_coder = box_coder_builder.build(east_config.box_coder) box_predictor = box_predictor_builder.build(hyperparams_builder.build, east_config.box_predictor, is_training, num_classes) anchor_generator = anchor_generator_builder.build( east_config.anchor_generator) #image_resizer_fn = image_resizer_builder.build(east_config.image_resizer) image_resizer_fn = None non_max_suppression_fn, score_conversion_fn = post_processing_builder.build( east_config.post_processing) (classification_loss, localization_loss, classification_weight, localization_weight, hard_example_miner) = losses_builder.build(east_config.loss) normalize_loss_by_num_matches = east_config.normalize_loss_by_num_matches return east_meta_arch.EASTMetaArch( is_training, anchor_generator, box_predictor, box_coder, feature_extractor, image_resizer_fn, non_max_suppression_fn, score_conversion_fn, classification_loss, localization_loss, classification_weight, localization_weight, normalize_loss_by_num_matches)
def test_build_ssd_anchor_generator_with_custom_scales(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [1.0] scales: [0.1, 0.15, 0.2, 0.4, 0.6, 0.8] reduce_boxes_in_lowest_layer: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertIsInstance( anchor_generator_object, multiple_grid_anchor_generator.MultipleGridAnchorGenerator) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, math.sqrt(0.1 * 0.15)), (0.15, math.sqrt(0.15 * 0.2)), (0.2, math.sqrt(0.2 * 0.4)), (0.4, math.sqrt(0.4 * 0.6)), (0.6, math.sqrt(0.6 * 0.8)), (0.8, math.sqrt(0.8 * 1.0))]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
def test_build_ssd_anchor_generator_with_custom_scales(self): anchor_generator_text_proto = """ ssd_anchor_generator { aspect_ratios: [1.0] scales: [0.1, 0.15, 0.2, 0.4, 0.6, 0.8] reduce_boxes_in_lowest_layer: false } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiple_grid_anchor_generator. MultipleGridAnchorGenerator)) for actual_scales, expected_scales in zip( list(anchor_generator_object._scales), [(0.1, math.sqrt(0.1 * 0.15)), (0.15, math.sqrt(0.15 * 0.2)), (0.2, math.sqrt(0.2 * 0.4)), (0.4, math.sqrt(0.4 * 0.6)), (0.6, math.sqrt(0.6 * 0.8)), (0.8, math.sqrt(0.8 * 1.0))]): self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
def test_build_multiscale_anchor_generator_custom_aspect_ratios(self): anchor_generator_text_proto = """ multiscale_anchor_generator { aspect_ratios: [1.0] } """ anchor_generator_proto = anchor_generator_pb2.AnchorGenerator() text_format.Merge(anchor_generator_text_proto, anchor_generator_proto) anchor_generator_object = anchor_generator_builder.build( anchor_generator_proto) self.assertTrue(isinstance(anchor_generator_object, multiscale_grid_anchor_generator. MultiscaleGridAnchorGenerator)) for level, anchor_grid_info in zip( range(3, 8), anchor_generator_object._anchor_grid_info): self.assertEqual(set(anchor_grid_info.keys()), set(['level', 'info'])) self.assertTrue(level, anchor_grid_info['level']) self.assertEqual(len(anchor_grid_info['info']), 4) self.assertAllClose(anchor_grid_info['info'][0], [2**0, 2**0.5]) self.assertTrue(anchor_grid_info['info'][1], 1.0) self.assertAllClose(anchor_grid_info['info'][2], [4.0 * 2**level, 4.0 * 2**level]) self.assertAllClose(anchor_grid_info['info'][3], [2**level, 2**level]) self.assertTrue(anchor_generator_object._normalize_coordinates)
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_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 _build_faster_rcnn_model(frcnn_config, is_training, add_summaries, meta_architecture='faster_rcnn'): """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 first_stage_proposals_path = frcnn_config.first_stage_proposals_path 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, iou_threshold=frcnn_config.second_stage_target_iou_threshold) 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) elif meta_architecture == 'faster_rcnn': 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) elif meta_architecture == 'faster_rcnn_override_RPN': return faster_rcnn_meta_arch_override_RPN.FasterRCNNMetaArchOverrideRPN( initial_crop_size=initial_crop_size, maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, first_stage_proposals_path=first_stage_proposals_path, second_stage_mask_rcnn_box_predictor=second_stage_box_predictor, second_stage_mask_prediction_loss_weight=( second_stage_mask_prediction_loss_weight), **common_kwargs) elif meta_architecture == 'faster_rcnn_rpn_blend': common_kwargs['use_matmul_crop_and_resize'] = False common_kwargs[ 'first_stage_nms_iou_threshold'] = frcnn_config.first_stage_nms_iou_threshold common_kwargs[ 'first_stage_nms_score_threshold'] = frcnn_config.first_stage_nms_score_threshold common_kwargs.pop('crop_and_resize_fn') common_kwargs.pop('first_stage_non_max_suppression_fn') common_kwargs.pop('resize_masks') common_kwargs.pop('use_static_shapes') return faster_rcnn_meta_arch_rpn_blend.FasterRCNNMetaArchRPNBlend( initial_crop_size=initial_crop_size, maxpool_kernel_size=maxpool_kernel_size, maxpool_stride=maxpool_stride, first_stage_proposals_path=first_stage_proposals_path, 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): """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_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)
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_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) 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 = 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': 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, '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 _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_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, 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_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) 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 use_static_shapes = frcnn_config.use_static_shapes 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): """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): """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_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_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, 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)