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 _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 _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_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 _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_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 _create_model(self,
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,
minimum_negative_sampling=1,
desired_negative_sampling_ratio=3,
use_keras=False):
is_training = False
num_classes = 1
mock_anchor_generator = MockAnchorGenerator2x2()
if use_keras:
mock_box_predictor = test_utils.MockKerasBoxPredictor(
is_training, num_classes)
else:
mock_box_predictor = test_utils.MockBoxPredictor(
is_training, num_classes)
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=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)
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,
minimum_negative_sampling=minimum_negative_sampling,
desired_negative_sampling_ratio=desired_negative_sampling_ratio
)
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,
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
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)
