def test_build_softmax_score_converter(self):
post_processing_text_proto = """
score_converter: SOFTMAX
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
_, score_converter = post_processing_builder.build(
post_processing_config)
self.assertEqual(score_converter, tf.nn.softmax)
def test_build_softmax_score_converter(self):
post_processing_text_proto = """
score_converter: SOFTMAX
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
_, score_converter = post_processing_builder.build(
post_processing_config)
self.assertEqual(score_converter.__name__, 'softmax_with_logit_scale')
def test_build_sigmoid_score_converter(self):
post_processing_text_proto = """
score_converter: SIGMOID
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
_, score_converter = post_processing_builder.build(
post_processing_config)
self.assertEqual(score_converter, tf.sigmoid)
def test_build_identity_score_converter(self):
post_processing_text_proto = """
score_converter: IDENTITY
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
_, score_converter = post_processing_builder.build(
post_processing_config)
self.assertEqual(score_converter, tf.identity)
def test_build_identity_score_converter(self):
post_processing_text_proto = """
score_converter: IDENTITY
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
_, score_converter = post_processing_builder.build(
post_processing_config)
self.assertEqual(score_converter.__name__, 'identity_with_logit_scale')
inputs = tf.constant([1, 1], tf.float32)
outputs = score_converter(inputs)
with self.test_session() as sess:
converted_scores = sess.run(outputs)
expected_converted_scores = sess.run(inputs)
self.assertAllClose(converted_scores, expected_converted_scores)
def test_build_non_max_suppressor_with_correct_parameters(self):
post_processing_text_proto = """
batch_non_max_suppression {
score_threshold: 0.7
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 300
}
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
non_max_suppressor, _ = post_processing_builder.build(
post_processing_config)
self.assertEqual(non_max_suppressor.keywords['max_size_per_class'],
100)
self.assertEqual(non_max_suppressor.keywords['max_total_size'], 300)
self.assertAlmostEqual(non_max_suppressor.keywords['score_thresh'],
0.7)
self.assertAlmostEqual(non_max_suppressor.keywords['iou_thresh'], 0.6)
def _build_model(self,
is_training,
first_stage_only,
second_stage_batch_size,
first_stage_max_proposals=8,
num_classes=2,
hard_mining=False):
def image_resizer_fn(image):
return tf.identity(image)
# anchors in this test are designed so that a subset of anchors are inside
# the image and a subset of anchors are outside.
first_stage_anchor_scales = (0.001, 0.005, 0.1)
first_stage_anchor_aspect_ratios = (0.5, 1.0, 2.0)
first_stage_anchor_angles = (0.0, 0.1)
first_stage_anchor_strides = (1, 1)
first_stage_anchor_generator = grid_rbbox_anchor_generator.GridRbboxAnchorGenerator(
first_stage_anchor_scales,
first_stage_anchor_aspect_ratios,
first_stage_anchor_angles,
anchor_stride=first_stage_anchor_strides)
fake_feature_extractor = FakeFasterRCNNFeatureExtractor()
first_stage_box_predictor_hyperparams_text_proto = """
op: CONV
activation: RELU
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
}
}
"""
first_stage_box_predictor_arg_scope = (
self._build_arg_scope_with_hyperparams(
first_stage_box_predictor_hyperparams_text_proto, is_training))
first_stage_box_predictor_kernel_size = 3
first_stage_atrous_rate = 1
first_stage_box_predictor_depth = 512
first_stage_minibatch_size = 3
first_stage_positive_balance_fraction = .5
first_stage_nms_score_threshold = -1.0
first_stage_nms_iou_threshold = 1.0
first_stage_max_proposals = first_stage_max_proposals
first_stage_localization_loss_weight = 1.0
first_stage_objectness_loss_weight = 1.0
post_processing_text_proto = """
batch_non_max_suppression {
box_type: RBBOX
score_threshold: -20.0
iou_threshold: 1.0
max_detections_per_class: 5
max_total_detections: 5
}
"""
post_processing_config = post_processing_pb2.PostProcessing()
text_format.Merge(post_processing_text_proto, post_processing_config)
second_stage_non_max_suppression_fn, _ = post_processing_builder.build(post_processing_config)
second_stage_balance_fraction = 1.0
second_stage_score_conversion_fn = tf.identity
second_stage_localization_loss_weight = 1.0
second_stage_classification_loss_weight = 1.0
hard_example_miner = None
if hard_mining:
hard_example_miner = losses.HardExampleMiner(
num_hard_examples=1,
iou_threshold=0.99,
loss_type='both',
cls_loss_weight=second_stage_classification_loss_weight,
loc_loss_weight=second_stage_localization_loss_weight,
max_negatives_per_positive=None)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': fake_feature_extractor,
'first_stage_only': first_stage_only,
'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_localization_loss_weight,
'first_stage_objectness_loss_weight': first_stage_objectness_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}
return self._get_model(self._get_second_stage_box_predictor(
num_classes=num_classes, is_training=is_training), **common_kwargs)