def graph_fn(similarity):
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=3.,
unmatched_threshold=2.,
force_match_for_each_row=True)
match = matcher.match(similarity)
matched_cols = match.matched_column_indicator()
unmatched_cols = match.unmatched_column_indicator()
match_results = match.match_results
return (matched_cols, unmatched_cols, match_results)
def _get_multi_class_target_assigner(self, num_classes):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.5)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder(stddev=0.1)
unmatched_cls_target = tf.constant([1] + num_classes * [0], tf.float32)
return targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder,
unmatched_cls_target=unmatched_cls_target)
def test_return_correct_matches_with_empty_rows(self):
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=None)
sim = 0.2 * tf.ones([0, 5])
match = matcher.match(sim)
unmatched_cols = match.unmatched_column_indices()
with self.test_session() as sess:
res_unmatched_cols = sess.run(unmatched_cols)
self.assertAllEqual(res_unmatched_cols, np.arange(5))
def _get_agnostic_target_assigner(self):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.5)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
return targetassigner.TargetAssigner(similarity_calc,
matcher,
box_coder,
unmatched_cls_target=None)
def graph_fn(similarity):
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=3.,
unmatched_threshold=2.,
negatives_lower_than_unmatched=False)
match = matcher.match(similarity)
matched_cols = match.matched_column_indicator()
unmatched_cols = match.unmatched_column_indicator()
match_results = match.match_results
return (matched_cols, unmatched_cols, match_results)
def _get_multi_dimensional_target_assigner(self, target_dimensions):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.5)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
unmatched_cls_target = tf.constant(np.zeros(target_dimensions),
tf.float32)
return targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder,
unmatched_cls_target=unmatched_cls_target)
def graph_fn(anchor_means, groundtruth_box_corners):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.3)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder(stddev=0.1)
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder, unmatched_cls_target=None)
anchors_boxlist = box_list.BoxList(anchor_means)
groundtruth_boxlist = box_list.BoxList(groundtruth_box_corners)
result = target_assigner.assign(anchors_boxlist, groundtruth_boxlist)
(cls_targets, cls_weights, reg_targets, reg_weights, _) = result
return (cls_targets, cls_weights, reg_targets, reg_weights)
def _get_multi_class_target_with_confidence_assigner(self, num_classes):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.3)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
unmatched_cls_target = tf.constant([1.0 / num_classes] * num_classes,
tf.float32)
return targetassigner.TargetAssigner(
similarity_calc,
matcher,
box_coder,
positive_class_weight=1.0,
negative_class_weight=1.0,
unmatched_cls_target=unmatched_cls_target)
def build(matcher_config):
"""Builds a matcher object based on the matcher config.
Args:
matcher_config: A matcher.proto object containing the config for the desired
Matcher.
Returns:
Matcher based on the config.
Raises:
ValueError: On empty matcher proto.
"""
if not isinstance(matcher_config, matcher_pb2.Matcher):
raise ValueError('matcher_config not of type matcher_pb2.Matcher.')
if matcher_config.WhichOneof('matcher_oneof') == 'argmax_matcher':
matcher = matcher_config.argmax_matcher
matched_threshold = unmatched_threshold = None
if not matcher.ignore_thresholds:
matched_threshold = matcher.matched_threshold
unmatched_threshold = matcher.unmatched_threshold
return argmax_matcher.ArgMaxMatcher(
matched_threshold=matched_threshold,
unmatched_threshold=unmatched_threshold,
negatives_lower_than_unmatched=matcher.
negatives_lower_than_unmatched,
force_match_for_each_row=matcher.force_match_for_each_row,
use_matmul_gather=matcher.use_matmul_gather)
if matcher_config.WhichOneof('matcher_oneof') == 'bipartite_matcher':
matcher = matcher_config.bipartite_matcher
return bipartite_matcher.GreedyBipartiteMatcher(
matcher.use_matmul_gather)
if matcher_config.WhichOneof('matcher_oneof') == 'argmax_matcher_sssfd':
matcher = matcher_config.argmax_matcher_sssfd
matched_threshold = unmatched_threshold = None
if not matcher.ignore_thresholds:
matched_threshold = matcher.matched_threshold
unmatched_threshold = matcher.unmatched_threshold
return argmax_matcher_sssfd.ArgMaxMatcherSssfd(
matched_threshold=matched_threshold,
unmatched_threshold=unmatched_threshold,
negatives_lower_than_unmatched=matcher.
negatives_lower_than_unmatched,
force_match_for_each_row=matcher.force_match_for_each_row,
use_matmul_gather=matcher.use_matmul_gather,
minimum_anchor_num=matcher.minimum_anchor_num,
minimum_threshold=matcher.minimum_threshold)
raise ValueError('Empty matcher.')
def test_assign_with_ignored_matches(self):
# Note: test is very similar to above. The third box matched with an IOU
# of 0.35, which is between the matched and unmatched threshold. This means
# That like above the expected classification targets are [1, 1, 0].
# Unlike above, the third target is ignored and therefore expected
# classification weights are [1, 1, 0].
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.3)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder)
prior_means = tf.constant([[0.0, 0.0, 0.5, 0.5],
[0.5, 0.5, 1.0, 0.8],
[0.0, 0.5, .9, 1.0]])
prior_stddevs = tf.constant(3 * [4 * [.1]])
priors = box_list.BoxList(prior_means)
priors.add_field('stddev', prior_stddevs)
box_corners = [[0.0, 0.0, 0.5, 0.5],
[0.5, 0.5, 0.9, 0.9]]
boxes = box_list.BoxList(tf.constant(box_corners))
exp_cls_targets = [[1], [1], [0]]
exp_cls_weights = [1, 1, 0]
exp_reg_targets = [[0, 0, 0, 0],
[0, 0, -1, 1],
[0, 0, 0, 0]]
exp_reg_weights = [1, 1, 0]
exp_matching_anchors = [0, 1]
result = target_assigner.assign(priors, boxes)
(cls_targets, cls_weights, reg_targets, reg_weights, match) = result
with self.test_session() as sess:
(cls_targets_out, cls_weights_out,
reg_targets_out, reg_weights_out, matching_anchors_out) = sess.run(
[cls_targets, cls_weights, reg_targets, reg_weights,
match.matched_column_indices()])
self.assertAllClose(cls_targets_out, exp_cls_targets)
self.assertAllClose(cls_weights_out, exp_cls_weights)
self.assertAllClose(reg_targets_out, exp_reg_targets)
self.assertAllClose(reg_weights_out, exp_reg_weights)
self.assertAllClose(matching_anchors_out, exp_matching_anchors)
self.assertEquals(cls_targets_out.dtype, np.float32)
self.assertEquals(cls_weights_out.dtype, np.float32)
self.assertEquals(reg_targets_out.dtype, np.float32)
self.assertEquals(reg_weights_out.dtype, np.float32)
self.assertEquals(matching_anchors_out.dtype, np.int32)
def test_assign_crowd(self):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.7,
unmatched_threshold=0.6,
force_match_for_each_row=True)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder, unmatched_cls_target=None)
prior_means = tf.constant([[0.5, 0.5, 1.0, 0.8], [0, 0.5, .5, 1.0],
[0.0, 0.0, 0.5, 0.5]])
prior_stddevs = tf.constant(3 * [4 * [.1]])
priors = box_list.BoxList(prior_means)
priors.add_field('stddev', prior_stddevs)
box_corners = [[0.0, 0.0, 0.5, 0.5], [0, 0.5, .5, 1.0],
[0.5, 0.5, 0.9, 0.9]]
boxes = box_list.BoxList(tf.constant(box_corners))
exp_cls_targets = [[1], [1], [1]]
exp_cls_weights = [1, 1, 1]
exp_reg_targets = [[0, 0, -1, 1], [0, 0, 0, 0], [0, 0, 0, 0]]
exp_reg_weights = [1, 1, 1]
exp_matching_anchors = [1]
# # crowd
# crowd = tf.constant([True, False, False], dtype=tf.bool)
# boxes.add_field(fields.BoxListFields.crowd, crowd)
#
# # ignore
# ignore = tf.constant([False, False, True], dtype=tf.bool)
# boxes.add_field(fields.BoxListFields.ignore, ignore)
result = target_assigner.assign(priors, boxes)
(cls_targets, cls_weights, reg_targets, reg_weights, match) = result
with self.test_session() as sess:
cls_targets_out, cls_weights_out, reg_targets_out, reg_weights_out, match_results_out, matching_anchors_out = \
sess.run([cls_targets, cls_weights, reg_targets, reg_weights, match.match_results, match.matched_column_indices()])
self.assertAllClose(cls_targets_out, exp_cls_targets)
self.assertAllClose(cls_weights_out, exp_cls_weights)
self.assertAllClose(reg_targets_out, exp_reg_targets)
self.assertAllClose(reg_weights_out, exp_reg_weights)
self.assertAllClose(matching_anchors_out, exp_matching_anchors)
self.assertEquals(cls_targets_out.dtype, np.float32)
self.assertEquals(cls_weights_out.dtype, np.float32)
self.assertEquals(reg_targets_out.dtype, np.float32)
self.assertEquals(reg_weights_out.dtype, np.float32)
def graph_fn(anchor_means, groundtruth_box_corners,
groundtruth_keypoints):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.5)
box_coder = keypoint_box_coder.KeypointBoxCoder(
num_keypoints=6, scale_factors=[10.0, 10.0, 5.0, 5.0])
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder, unmatched_cls_target=None)
anchors_boxlist = box_list.BoxList(anchor_means)
groundtruth_boxlist = box_list.BoxList(groundtruth_box_corners)
groundtruth_boxlist.add_field(fields.BoxListFields.keypoints,
groundtruth_keypoints)
result = target_assigner.assign(anchors_boxlist, groundtruth_boxlist)
(cls_targets, cls_weights, reg_targets, reg_weights, _) = result
return (cls_targets, cls_weights, reg_targets, reg_weights)
def __init__(self):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=ssd_constants.MATCH_THRESHOLD,
unmatched_threshold=ssd_constants.MATCH_THRESHOLD,
negatives_lower_than_unmatched=True,
force_match_for_each_row=True)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=ssd_constants.BOX_CODER_SCALES)
self.default_boxes = DefaultBoxes()('ltrb')
self.default_boxes = box_list.BoxList(
tf.convert_to_tensor(self.default_boxes))
self.assigner = target_assigner.TargetAssigner(similarity_calc,
matcher, box_coder)
def graph_fn(anchor_means, anchor_stddevs, groundtruth_box_corners,
groundtruth_labels):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.5)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
unmatched_cls_target = tf.constant([0, 0, 0], tf.float32)
anchors_boxlist = box_list.BoxList(anchor_means)
anchors_boxlist.add_field('stddev', anchor_stddevs)
groundtruth_boxlist = box_list.BoxList(groundtruth_box_corners)
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder,
unmatched_cls_target=unmatched_cls_target)
result = target_assigner.assign(anchors_boxlist, groundtruth_boxlist,
groundtruth_labels)
(cls_targets, cls_weights, reg_targets, reg_weights, _) = result
return (cls_targets, cls_weights, reg_targets, reg_weights)
def __init__(self, categories, iou_threshold=0.5):
"""Constructor.
Args:
categories: A list of dicts, each of which has the following keys -
'id': (required) an integer id uniquely identifying this category.
'name': (required) string representing category name e.g., 'cat', 'dog'.
iou_threshold: Threshold above which to consider a box as matched during
evaluation.
"""
super(CalibrationDetectionEvaluator, self).__init__(categories)
# Constructing target_assigner to match detections to groundtruth.
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=iou_threshold, unmatched_threshold=iou_threshold)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder(stddev=0.1)
self._target_assigner = target_assigner.TargetAssigner(
similarity_calc, matcher, box_coder)
def test_return_correct_matches_with_default_thresholds(self):
similarity = np.array([[1., 1, 1, 3, 1], [2, -1, 2, 0, 4],
[3, 0, -1, 0, 0]])
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=None)
expected_matched_rows = np.array([2, 0, 1, 0, 1])
sim = tf.constant(similarity)
match = matcher.match(sim)
matched_cols = match.matched_column_indices()
matched_rows = match.matched_row_indices()
unmatched_cols = match.unmatched_column_indices()
with self.test_session() as sess:
res_matched_cols = sess.run(matched_cols)
res_matched_rows = sess.run(matched_rows)
res_unmatched_cols = sess.run(unmatched_cols)
self.assertAllEqual(res_matched_rows, expected_matched_rows)
self.assertAllEqual(res_matched_cols, np.arange(similarity.shape[1]))
def test_categorize_crowd_ignore(self):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.7,
unmatched_threshold=0.6,
force_match_for_each_row=True)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder, unmatched_cls_target=None)
box_corners = [[0.0, 0.0, 0.1, 0.1], [0.1, 0.1, 0.2, 0.2],
[0.2, 0.2, 0.3, 0.3], [0.3, 0.3, 0.4, 0.4],
[0.4, 0.4, 0.5, 0.5], [0.5, 0.5, 0.6, 0.6]]
boxes = box_list.BoxList(tf.constant(box_corners))
crowd = tf.constant([False, True, False, False, True, False],
dtype=tf.bool)
boxes.add_field(fields.BoxListFields.crowd, crowd)
ignore = tf.constant([False, False, True, False, True, True],
dtype=tf.bool)
boxes.add_field(fields.BoxListFields.ignore, ignore)
gt_boxes, crowd_boxes, ignore_boxes = target_assigner.categorize_crowd_ignore(
boxes)
gt_boxes_tensor = gt_boxes.get()
crowd_boxes_tensor = crowd_boxes.get()
ignore_boxes_tensor = ignore_boxes.get()
exp_gt_boxes = [[0.0, 0.0, 0.1, 0.1], [0.3, 0.3, 0.4, 0.4]]
exp_crowd_boxes = [[0.1, 0.1, 0.2, 0.2], [0.4, 0.4, 0.5, 0.5]]
exp_ignore_boxes = [[0.2, 0.2, 0.3, 0.3], [0.4, 0.4, 0.5, 0.5],
[0.5, 0.5, 0.6, 0.6]]
with self.test_session() as sess:
gt_boxes_out, crowd_boxes_out, ignore_boxes_out = \
sess.run([gt_boxes_tensor, crowd_boxes_tensor, ignore_boxes_tensor])
self.assertAllClose(gt_boxes_out, exp_gt_boxes)
self.assertAllClose(crowd_boxes_out, exp_crowd_boxes)
self.assertAllClose(ignore_boxes_out, exp_ignore_boxes)
def test_set_values_using_indicator(self):
input_a = np.array([3, 4, 5, 1, 4, 3, 2])
expected_b = np.array([3, 0, 0, 1, 0, 3, 2]) # Set a>3 to 0
expected_c = np.array([3., 4., 5., -1., 4., 3.,
-1.]) # Set a<3 to -1. Float32
idxb_ = input_a > 3
idxc_ = input_a < 3
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=None)
a = tf.constant(input_a)
idxb = tf.constant(idxb_)
idxc = tf.constant(idxc_)
b = matcher._set_values_using_indicator(a, idxb, 0)
c = matcher._set_values_using_indicator(tf.cast(a, tf.float32), idxc,
-1)
with self.test_session() as sess:
res_b = sess.run(b)
res_c = sess.run(c)
self.assertAllEqual(res_b, expected_b)
self.assertAllEqual(res_c, expected_c)
def build(matcher_config):
if not isinstance(matcher_config, matcher_pb2.Matcher):
raise ValueError('matcher_config not of type matcher_pb2.Matcher.')
if matcher_config.WhichOneof('matcher_oneof') == 'argmax_matcher':
matcher = matcher_config.argmax_matcher
matched_threshold = unmatched_threshold = None
if not matcher.ignore_thresholds:
matched_threshold = matcher.matched_threshold
unmatched_threshold = matcher.unmatched_threshold
return argmax_matcher.ArgMaxMatcher(
matched_threshold=matched_threshold,
unmatched_threshold=unmatched_threshold,
negatives_lower_than_unmatched=matcher.
negatives_lower_than_unmatched,
force_match_for_each_row=matcher.force_match_for_each_row,
use_matmul_gather=matcher.use_matmul_gather)
if matcher_config.WhichOneof('matcher_oneof') == 'bipartite_matcher':
matcher = matcher_config.bipartite_matcher
return bipartite_matcher.GreedyBipartiteMatcher(
matcher.use_matmul_gather)
raise ValueError('Empty matcher.')
def graph_fn(anchor_means, groundtruth_box_corners,
groundtruth_labels):
similarity_calc = region_similarity_calculator.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.5,
unmatched_threshold=0.5)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder(stddev=0.1)
unmatched_class_label = tf.constant([1, 0, 0, 0, 0, 0, 0],
tf.float32)
target_assigner = targetassigner.TargetAssigner(
similarity_calc,
matcher,
box_coder,
weight_regression_loss_by_score=True)
anchors_boxlist = box_list.BoxList(anchor_means)
groundtruth_boxlist = box_list.BoxList(groundtruth_box_corners)
result = target_assigner.assign(
anchors_boxlist,
groundtruth_boxlist,
groundtruth_labels,
unmatched_class_label=unmatched_class_label)
(_, cls_weights, _, reg_weights, _) = result
return (cls_weights, reg_weights)
def test_assign_agnostic(self):
similarity_calc = region_similarity_calculator.IoaSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(0.5)
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
target_assigner = targetassigner.TargetAssigner(
similarity_calc, matcher, box_coder, unmatched_cls_target=None)
prior_means = tf.constant([[0.5, 0.5, 1.0, 0.8], [0, 0.5, .5, 1.0],
[0.0, 0.0, 0.5, 0.5]])
prior_stddevs = tf.constant(3 * [4 * [.1]])
priors = box_list.BoxList(prior_means)
priors.add_field('stddev', prior_stddevs)
box_corners = [[0.0, 0.0, 0.5, 0.5], [0.5, 0.5, 0.9, 0.9]]
boxes = box_list.BoxList(tf.constant(box_corners))
exp_cls_targets = [[1], [0], [1]]
exp_cls_weights = [1, 1, 1]
exp_reg_targets = [[0, 0, -1, 1], [0, 0, 0, 0], [0, 0, 0, 0]]
exp_reg_weights = [1, 0, 1]
exp_matching_anchors = [0, 2]
result = target_assigner.assign(priors, boxes)
(cls_targets, cls_weights, reg_targets, reg_weights, match) = result
with self.test_session() as sess:
cls_targets_out, cls_weights_out, reg_targets_out, reg_weights_out, matching_anchors_out = \
sess.run([cls_targets, cls_weights, reg_targets, reg_weights, match.matched_column_indices()])
self.assertAllClose(cls_targets_out, exp_cls_targets)
self.assertAllClose(cls_weights_out, exp_cls_weights)
self.assertAllClose(reg_targets_out, exp_reg_targets)
self.assertAllClose(reg_weights_out, exp_reg_weights)
self.assertAllClose(matching_anchors_out, exp_matching_anchors)
self.assertEquals(cls_targets_out.dtype, np.float32)
self.assertEquals(cls_weights_out.dtype, np.float32)
self.assertEquals(reg_targets_out.dtype, np.float32)
self.assertEquals(reg_weights_out.dtype, np.float32)
def build(matcher_config):
"""Builds a matcher object based on the matcher config.
Args:
matcher_config: A matcher.proto object containing the config for the desired
Matcher.
Returns:
Matcher based on the config.
Raises:
ValueError: On empty matcher proto.
"""
if not isinstance(matcher_config, matcher_pb2.Matcher):
raise ValueError('matcher_config not of type matcher_pb2.Matcher.')
if matcher_config.WhichOneof('matcher_oneof') == 'argmax_matcher':
matcher = matcher_config.argmax_matcher
matched_threshold = unmatched_threshold = None
if not matcher.ignore_thresholds:
matched_threshold = matcher.matched_threshold
unmatched_threshold = matcher.unmatched_threshold
return argmax_matcher.ArgMaxMatcher(
matched_threshold=matched_threshold,
unmatched_threshold=unmatched_threshold,
negatives_lower_than_unmatched=matcher.negatives_lower_than_unmatched,
force_match_for_each_row=matcher.force_match_for_each_row)
if matcher_config.WhichOneof('matcher_oneof') == 'bipartite_matcher':
return bipartite_matcher.GreedyBipartiteMatcher()
if matcher_config.WhichOneof('matcher_oneof') == 'top_k_anchor_matcher':
matcher = matcher_config.top_k_anchor_matcher
number_of_top_k = matcher.number_of_top_k
unmatched_threshold = matcher.unmatched_threshold
return top_k_anchor_matcher.TopKAnchorMatcher(
number_of_top_k=number_of_top_k,
unmatched_threshold=unmatched_threshold)
raise ValueError('Empty matcher.')
def test_invalid_arguments_unmatched_thres_larger_than_matched_thres(self):
with self.assertRaises(ValueError):
argmax_matcher.ArgMaxMatcher(matched_threshold=1,
unmatched_threshold=2)
def test_invalid_arguments_no_matched_threshold(self):
with self.assertRaises(ValueError):
argmax_matcher.ArgMaxMatcher(matched_threshold=None,
unmatched_threshold=4)
def test_invalid_arguments_corner_case_negatives_lower_than_thres_false(
self):
with self.assertRaises(ValueError):
argmax_matcher.ArgMaxMatcher(matched_threshold=1,
unmatched_threshold=1,
negatives_lower_than_unmatched=False)
def test_valid_arguments_corner_case(self):
argmax_matcher.ArgMaxMatcher(matched_threshold=1,
unmatched_threshold=1)
def create_target_assigner(reference,
stage=None,
positive_class_weight=1.0,
negative_class_weight=1.0,
unmatched_cls_target=None):
"""Factory function for creating standard target assigners.
Args:
reference: string referencing the type of TargetAssigner.
stage: string denoting stage: {proposal, detection}.
positive_class_weight: classification weight to be associated to positive
anchors (default: 1.0)
negative_class_weight: classification weight to be associated to negative
anchors (default: 1.0)
unmatched_cls_target: a float32 tensor with shape [d_1, d_2, ..., d_k]
which is consistent with the classification target for each
anchor (and can be empty for scalar targets). This shape must thus be
compatible with the groundtruth labels that are passed to the Assign
function (which have shape [num_gt_boxes, d_1, d_2, ..., d_k]).
If set to None, unmatched_cls_target is set to be 0 for each anchor.
Returns:
TargetAssigner: desired target assigner.
Raises:
ValueError: if combination reference+stage is invalid.
"""
if reference == 'Multibox' and stage == 'proposal':
similarity_calc = sim_calc.NegSqDistSimilarity()
matcher = bipartite_matcher.GreedyBipartiteMatcher()
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
elif reference == 'FasterRCNN' and stage == 'proposal':
print("GGGGGGGGGGGGGGGGGGGGGGGG")
similarity_calc = sim_calc.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=0.7,
unmatched_threshold=0.3,
force_match_for_each_row=True)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=[10.0, 10.0, 5.0, 5.0])
elif reference == 'FasterRCNN' and stage == 'detection':
print("gggggggggggggggggggggggg")
similarity_calc = sim_calc.IouSimilarity()
# Uses all proposals with IOU < 0.5 as candidate negatives.
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=0.5, negatives_lower_than_unmatched=True)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=[10.0, 10.0, 5.0, 5.0])
elif reference == 'FasterRCNN' and stage == 'proposal51':
print("FFFFFFFFFFFFFFFFFFFFFFF")
similarity_calc = sim_calc.IouSimilarity()
matcher = top_k_anchor_matcher.TopKAnchorMatcher(
number_of_top_k=5, unmatched_threshold=0.3)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=[10.0, 10.0, 5.0, 5.0])
elif reference == 'FasterRCNN' and stage == 'detection51':
print("fffffffffffffffffffffffffff")
similarity_calc = sim_calc.IouSimilarity()
# Uses all proposals with IOU < 0.5 as candidate negatives.
matcher = top_k_anchor_matcher.TopKAnchorMatcher(
number_of_top_k=1, unmatched_threshold=0.5)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=[10.0, 10.0, 5.0, 5.0])
elif reference == 'FastRCNN':
similarity_calc = sim_calc.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=0.5,
unmatched_threshold=0.1,
force_match_for_each_row=False,
negatives_lower_than_unmatched=False)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder()
else:
raise ValueError('No valid combination of reference and stage.')
return TargetAssigner(similarity_calc,
matcher,
box_coder,
positive_class_weight=positive_class_weight,
negative_class_weight=negative_class_weight,
unmatched_cls_target=unmatched_cls_target)
def create_target_assigner(reference,
stage=None,
negative_class_weight=1.0,
use_matmul_gather=False):
"""Factory function for creating standard target assigners.
Args:
reference: string referencing the type of TargetAssigner.
stage: string denoting stage: {proposal, detection}.
negative_class_weight: classification weight to be associated to negative
anchors (default: 1.0)
use_matmul_gather: whether to use matrix multiplication based gather which
are better suited for TPUs.
Returns:
TargetAssigner: desired target assigner.
Raises:
ValueError: if combination reference+stage is invalid.
"""
if reference == 'Multibox' and stage == 'proposal':
similarity_calc = sim_calc.NegSqDistSimilarity()
matcher = bipartite_matcher.GreedyBipartiteMatcher()
box_coder = mean_stddev_box_coder.MeanStddevBoxCoder()
elif reference == 'FasterRCNN' and stage == 'proposal':
similarity_calc = sim_calc.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=0.7,
unmatched_threshold=0.3,
force_match_for_each_row=True,
use_matmul_gather=use_matmul_gather)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=[10.0, 10.0, 5.0, 5.0])
elif reference == 'FasterRCNN' and stage == 'detection':
similarity_calc = sim_calc.IouSimilarity()
# Uses all proposals with IOU < 0.5 as candidate negatives.
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=0.5,
negatives_lower_than_unmatched=True,
use_matmul_gather=use_matmul_gather)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder(
scale_factors=[10.0, 10.0, 5.0, 5.0])
elif reference == 'FastRCNN':
similarity_calc = sim_calc.IouSimilarity()
matcher = argmax_matcher.ArgMaxMatcher(
matched_threshold=0.5,
unmatched_threshold=0.1,
force_match_for_each_row=False,
negatives_lower_than_unmatched=False,
use_matmul_gather=use_matmul_gather)
box_coder = faster_rcnn_box_coder.FasterRcnnBoxCoder()
else:
raise ValueError('No valid combination of reference and stage.')
return TargetAssigner(similarity_calc,
matcher,
box_coder,
negative_class_weight=negative_class_weight)
def graph_fn(similarity_matrix):
matcher = argmax_matcher.ArgMaxMatcher(matched_threshold=None)
match = matcher.match(similarity_matrix)
return match.unmatched_column_indicator()
