def _create_model(self, apply_hard_mining=True, normalize_loc_loss_by_codesize=False): is_training = False num_classes = 1 mock_anchor_generator = MockAnchorGenerator2x2() mock_box_predictor = test_utils.MockBoxPredictor( is_training, num_classes) mock_box_coder = test_utils.MockBoxCoder() fake_feature_extractor = FakeSSDFeatureExtractor() mock_matcher = test_utils.MockMatcher() region_similarity_calculator = sim_calc.IouSimilarity() encode_background_as_zeros = False def image_resizer_fn(image): return [tf.identity(image), tf.shape(image)] classification_loss = losses.WeightedSigmoidClassificationLoss() localization_loss = losses.WeightedSmoothL1LocalizationLoss() non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=-20.0, iou_thresh=1.0, max_size_per_class=5, max_total_size=5) classification_loss_weight = 1.0 localization_loss_weight = 1.0 negative_class_weight = 1.0 normalize_loss_by_num_matches = False hard_example_miner = None if apply_hard_mining: # This hard example miner is expected to be a no-op. hard_example_miner = losses.HardExampleMiner( num_hard_examples=None, iou_threshold=1.0) code_size = 4 model = ssd_meta_arch.SSDMetaArch( is_training, mock_anchor_generator, mock_box_predictor, mock_box_coder, fake_feature_extractor, mock_matcher, region_similarity_calculator, encode_background_as_zeros, negative_class_weight, image_resizer_fn, non_max_suppression_fn, tf.identity, classification_loss, localization_loss, classification_loss_weight, localization_loss_weight, normalize_loss_by_num_matches, hard_example_miner, add_summaries=False, normalize_loc_loss_by_codesize=normalize_loc_loss_by_codesize) return model, num_classes, mock_anchor_generator.num_anchors( ), code_size
def setUp(self): """Set up mock SSD model. Here we set up a simple mock SSD model that will always predict 4 detections that happen to always be exactly the anchors that are set up in the above MockAnchorGenerator. Because we let max_detections=5, we will also always end up with an extra padded row in the detection results. """ is_training = False self._num_classes = 1 conv_hyperparams = {} self._conv_hyperparams = conv_hyperparams mock_anchor_generator = MockAnchorGenerator2x2() mock_box_predictor = test_utils.MockBoxPredictor( is_training, self._num_classes) mock_class_predictor = test_utils.MockClassPredictor( is_training, 7, self._conv_hyperparams, True, 0.5, 5, 0.0, False) mock_box_coder = test_utils.MockBoxCoder() fake_feature_extractor = FakeSSDFeatureExtractor() mock_matcher = test_utils.MockMatcher() region_similarity_calculator = sim_calc.IouSimilarity() def image_resizer_fn(image): return tf.identity(image) classification_loss = losses.WeightedSigmoidClassificationLoss( anchorwise_output=True) localization_loss = losses.WeightedSmoothL1LocalizationLoss( anchorwise_output=True) classification_loss_in_image_level = losses.WeightedSigmoidClassificationLossInImageLevel( ) non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=-20.0, iou_thresh=1.0, max_size_per_class=5, max_total_size=5) classification_loss_weight = 1.0 localization_loss_weight = 1.0 classification_loss_in_image_level_weight = 1.0 normalize_loss_by_num_matches = False # This hard example miner is expected to be a no-op. hard_example_miner = losses.HardExampleMiner(num_hard_examples=None, iou_threshold=1.0) self._num_anchors = 4 self._code_size = 4 self._model = ssd_meta_arch.SSDMetaArch( is_training, mock_anchor_generator, mock_box_predictor, mock_class_predictor, mock_box_coder, fake_feature_extractor, mock_matcher, region_similarity_calculator, image_resizer_fn, non_max_suppression_fn, tf.identity, classification_loss, localization_loss, classification_loss_in_image_level, classification_loss_weight, localization_loss_weight, classification_loss_in_image_level_weight, normalize_loss_by_num_matches, hard_example_miner)
def _create_model(self, interleaved=False, apply_hard_mining=True, normalize_loc_loss_by_codesize=False, add_background_class=True, random_example_sampling=False, use_expected_classification_loss_under_sampling=False, min_num_negative_samples=1, desired_negative_sampling_ratio=3, unroll_length=1): num_classes = NUM_CLASSES is_training = False mock_anchor_generator = MockAnchorGenerator2x2() mock_box_predictor = test_utils.MockBoxPredictor(is_training, num_classes) mock_box_coder = test_utils.MockBoxCoder() if interleaved: fake_feature_extractor = FakeLSTMInterleavedFeatureExtractor() else: fake_feature_extractor = FakeLSTMFeatureExtractor() mock_matcher = test_utils.MockMatcher() region_similarity_calculator = sim_calc.IouSimilarity() encode_background_as_zeros = False def image_resizer_fn(image): return [tf.identity(image), tf.shape(image)] classification_loss = losses.WeightedSigmoidClassificationLoss() localization_loss = losses.WeightedSmoothL1LocalizationLoss() non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=-20.0, iou_thresh=1.0, max_size_per_class=5, max_total_size=MAX_TOTAL_NUM_BOXES) classification_loss_weight = 1.0 localization_loss_weight = 1.0 negative_class_weight = 1.0 normalize_loss_by_num_matches = False hard_example_miner = None if apply_hard_mining: # This hard example miner is expected to be a no-op. hard_example_miner = losses.HardExampleMiner( num_hard_examples=None, iou_threshold=1.0) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, mock_matcher, mock_box_coder, negative_class_weight=negative_class_weight) code_size = 4 model = lstm_ssd_meta_arch.LSTMSSDMetaArch( is_training=is_training, anchor_generator=mock_anchor_generator, box_predictor=mock_box_predictor, box_coder=mock_box_coder, feature_extractor=fake_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=tf.identity, classification_loss=classification_loss, localization_loss=localization_loss, classification_loss_weight=classification_loss_weight, localization_loss_weight=localization_loss_weight, normalize_loss_by_num_matches=normalize_loss_by_num_matches, hard_example_miner=hard_example_miner, unroll_length=unroll_length, target_assigner_instance=target_assigner_instance, add_summaries=False) return model, num_classes, mock_anchor_generator.num_anchors(), code_size
def _create_model( self, model_fn=ssd_meta_arch.SSDMetaArch, apply_hard_mining=True, normalize_loc_loss_by_codesize=False, add_background_class=True, random_example_sampling=False, expected_loss_weights=model_pb2.DetectionModel().ssd.loss.NONE, min_num_negative_samples=1, desired_negative_sampling_ratio=3, use_keras=False, predict_mask=False, use_static_shapes=False, nms_max_size_per_class=5, calibration_mapping_value=None, return_raw_detections_during_predict=False): is_training = False num_classes = 1 mock_anchor_generator = MockAnchorGenerator2x2() if use_keras: mock_box_predictor = test_utils.MockKerasBoxPredictor( is_training, num_classes, add_background_class=add_background_class) else: mock_box_predictor = test_utils.MockBoxPredictor( is_training, num_classes, add_background_class=add_background_class) mock_box_coder = test_utils.MockBoxCoder() if use_keras: fake_feature_extractor = FakeSSDKerasFeatureExtractor() else: fake_feature_extractor = FakeSSDFeatureExtractor() mock_matcher = test_utils.MockMatcher() region_similarity_calculator = sim_calc.IouSimilarity() encode_background_as_zeros = False def image_resizer_fn(image): return [tf.identity(image), tf.shape(image)] classification_loss = losses.WeightedSigmoidClassificationLoss() localization_loss = losses.WeightedSmoothL1LocalizationLoss() non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=-20.0, iou_thresh=1.0, max_size_per_class=nms_max_size_per_class, max_total_size=nms_max_size_per_class, use_static_shapes=use_static_shapes) score_conversion_fn = tf.identity calibration_config = calibration_pb2.CalibrationConfig() if calibration_mapping_value: calibration_text_proto = """ function_approximation { x_y_pairs { x_y_pair { x: 0.0 y: %f } x_y_pair { x: 1.0 y: %f }}}""" % (calibration_mapping_value, calibration_mapping_value) text_format.Merge(calibration_text_proto, calibration_config) score_conversion_fn = ( post_processing_builder._build_calibrated_score_converter( # pylint: disable=protected-access tf.identity, calibration_config)) classification_loss_weight = 1.0 localization_loss_weight = 1.0 negative_class_weight = 1.0 normalize_loss_by_num_matches = False hard_example_miner = None if apply_hard_mining: # This hard example miner is expected to be a no-op. hard_example_miner = losses.HardExampleMiner( num_hard_examples=None, iou_threshold=1.0) random_example_sampler = None if random_example_sampling: random_example_sampler = sampler.BalancedPositiveNegativeSampler( positive_fraction=0.5) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, mock_matcher, mock_box_coder, negative_class_weight=negative_class_weight) model_config = model_pb2.DetectionModel() if expected_loss_weights == model_config.ssd.loss.NONE: expected_loss_weights_fn = None else: raise ValueError('Not a valid value for expected_loss_weights.') code_size = 4 kwargs = {} if predict_mask: kwargs.update({ 'mask_prediction_fn': test_utils.MockMaskHead(num_classes=1).predict, }) model = model_fn( is_training=is_training, anchor_generator=mock_anchor_generator, box_predictor=mock_box_predictor, box_coder=mock_box_coder, feature_extractor=fake_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_loss_weight, localization_loss_weight=localization_loss_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=False, normalize_loc_loss_by_codesize=normalize_loc_loss_by_codesize, freeze_batchnorm=False, inplace_batchnorm_update=False, add_background_class=add_background_class, random_example_sampler=random_example_sampler, expected_loss_weights_fn=expected_loss_weights_fn, return_raw_detections_during_predict=( return_raw_detections_during_predict), **kwargs) return model, num_classes, mock_anchor_generator.num_anchors(), code_size
def _create_model(self, model_fn=ssd_meta_arch.SSDMetaArch, apply_hard_mining=True, normalize_loc_loss_by_codesize=False, add_background_class=True, random_example_sampling=False, weight_regression_loss_by_score=False, use_expected_classification_loss_under_sampling=False, min_num_negative_samples=1, desired_negative_sampling_ratio=3, use_keras=False, predict_mask=False, use_static_shapes=False, nms_max_size_per_class=5): is_training = False num_classes = 1 mock_anchor_generator = MockAnchorGenerator2x2() if use_keras: mock_box_predictor = test_utils.MockKerasBoxPredictor( is_training, num_classes, add_background_class=add_background_class, predict_mask=predict_mask) else: mock_box_predictor = test_utils.MockBoxPredictor( is_training, num_classes, add_background_class=add_background_class, predict_mask=predict_mask) mock_box_coder = test_utils.MockBoxCoder() if use_keras: fake_feature_extractor = FakeSSDKerasFeatureExtractor() else: fake_feature_extractor = FakeSSDFeatureExtractor() mock_matcher = test_utils.MockMatcher() region_similarity_calculator = sim_calc.IouSimilarity() encode_background_as_zeros = False def image_resizer_fn(image): return [tf.identity(image), tf.shape(image)] classification_loss = losses.WeightedSigmoidClassificationLoss() localization_loss = losses.WeightedSmoothL1LocalizationLoss() non_max_suppression_fn = functools.partial( post_processing.batch_multiclass_non_max_suppression, score_thresh=-20.0, iou_thresh=1.0, max_size_per_class=nms_max_size_per_class, max_total_size=nms_max_size_per_class, use_static_shapes=use_static_shapes) classification_loss_weight = 1.0 localization_loss_weight = 1.0 negative_class_weight = 1.0 normalize_loss_by_num_matches = False hard_example_miner = None if apply_hard_mining: # This hard example miner is expected to be a no-op. hard_example_miner = losses.HardExampleMiner( num_hard_examples=None, iou_threshold=1.0) random_example_sampler = None if random_example_sampling: random_example_sampler = sampler.BalancedPositiveNegativeSampler( positive_fraction=0.5) target_assigner_instance = target_assigner.TargetAssigner( region_similarity_calculator, mock_matcher, mock_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 use_expected_classification_loss_under_sampling: expected_classification_loss_under_sampling = functools.partial( ops.expected_classification_loss_under_sampling, min_num_negative_samples=min_num_negative_samples, desired_negative_sampling_ratio=desired_negative_sampling_ratio ) code_size = 4 model = model_fn( is_training=is_training, anchor_generator=mock_anchor_generator, box_predictor=mock_box_predictor, box_coder=mock_box_coder, feature_extractor=fake_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=tf.identity, classification_loss=classification_loss, localization_loss=localization_loss, classification_loss_weight=classification_loss_weight, localization_loss_weight=localization_loss_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=False, normalize_loc_loss_by_codesize=normalize_loc_loss_by_codesize, freeze_batchnorm=False, inplace_batchnorm_update=False, add_background_class=add_background_class, random_example_sampler=random_example_sampler, expected_classification_loss_under_sampling= expected_classification_loss_under_sampling) return model, num_classes, mock_anchor_generator.num_anchors( ), code_size