Python object_detection.utils.test_utils.MockMatcher() Examples

The following are 17 code examples of object_detection.utils.test_utils.MockMatcher(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module object_detection.utils.test_utils , or try the search function .
Example #1
Source File: ssd_meta_arch_test.py    From tensorflow with BSD 2-Clause "Simplified" License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #2
Source File: ssd_meta_arch_test.py    From mtl-ssl with Apache License 2.0 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #3
Source File: ssd_meta_arch_test.py    From object_detection_with_tensorflow with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #4
Source File: ssd_meta_arch_test.py    From object_detection_with_tensorflow with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #5
Source File: ssd_meta_arch_test.py    From Elphas with Apache License 2.0 4 votes vote down vote up 
def _create_model(self, apply_hard_mining=True):
    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
    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, 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)
    return model, num_classes, mock_anchor_generator.num_anchors(), code_size
Example #6
Source File: ssd_meta_arch_test.py    From MBMD with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #7
Source File: ssd_meta_arch_test.py    From object_detection_kitti with Apache License 2.0 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #8
Source File: ssd_meta_arch_test.py    From hands-detection with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #9
Source File: ssd_meta_arch_test.py    From moveo_ros with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #10
Source File: ssd_meta_arch_test.py    From DOTA_models with Apache License 2.0 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #11
Source File: ssd_meta_arch_test.py    From Hands-On-Machine-Learning-with-OpenCV-4 with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #12
Source File: ssd_meta_arch_test.py    From Traffic-Rule-Violation-Detection-System with MIT License 4 votes vote down vote up 
def _create_model(self, apply_hard_mining=True):
    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()

    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
    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,
        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)
    return model, num_classes, mock_anchor_generator.num_anchors(), code_size
Example #13
Source File: ssd_meta_arch_test.py    From yolo_v2 with Apache License 2.0 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #14
Source File: ssd_meta_arch_test.py    From HereIsWally with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #15
Source File: ssd_meta_arch_test.py    From garbage-object-detection-tensorflow with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)
Example #16
Source File: ssd_meta_arch_test.py    From ros_people_object_detection_tensorflow with Apache License 2.0 4 votes vote down vote up 
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
Example #17
Source File: ssd_meta_arch_test.py    From object_detector_app with MIT License 4 votes vote down vote up 
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
    mock_anchor_generator = MockAnchorGenerator2x2()
    mock_box_predictor = test_utils.MockBoxPredictor(
        is_training, self._num_classes)
    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)
    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
    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_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_weight,
        localization_loss_weight, normalize_loss_by_num_matches,
        hard_example_miner)