def test_raise_value_error_on_empty_anchor_genertor(self):
anchor_generator_text_proto = """
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
with self.assertRaises(ValueError):
anchor_generator_builder.build(anchor_generator_proto)
def test_raise_value_error_on_empty_anchor_genertor(self):
anchor_generator_text_proto = """
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
with self.assertRaises(ValueError):
anchor_generator_builder.build(anchor_generator_proto)
def test_build_ssd_anchor_generator_without_reduced_boxes(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [1.0]
reduce_boxes_in_lowest_layer: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertIsInstance(
anchor_generator_object,
multiple_grid_anchor_generator.MultipleGridAnchorGenerator)
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales), [(0.2, 0.264),
(0.35, 0.418),
(0.499, 0.570),
(0.649, 0.721),
(0.799, 0.871),
(0.949, 0.974)]):
self.assert_almost_list_equal(expected_scales,
actual_scales,
delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
6 * [(1.0, 1.0)]):
self.assert_almost_list_equal(expected_aspect_ratio,
actual_aspect_ratio)
self.assertAllClose(anchor_generator_object._base_anchor_size,
[1.0, 1.0])
def test_build_ssd_anchor_generator_without_reduced_boxes(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [1.0]
reduce_boxes_in_lowest_layer: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales),
[(0.2, 0.264),
(0.35, 0.418),
(0.499, 0.570),
(0.649, 0.721),
(0.799, 0.871),
(0.949, 0.974)]):
self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
6 * [(1.0, 1.0)]):
self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
self.assertAllClose(anchor_generator_object._base_anchor_size, [1.0, 1.0])
def test_build_grid_anchor_generator_with_non_default_parameters(self):
anchor_generator_text_proto = """
grid_anchor_generator {
height: 128
width: 512
height_stride: 10
width_stride: 20
height_offset: 30
width_offset: 40
scales: [0.4, 2.2]
aspect_ratios: [0.3, 4.5]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
grid_anchor_generator.GridAnchorGenerator))
self.assert_almost_list_equal(anchor_generator_object._scales,
[0.4, 2.2])
self.assert_almost_list_equal(anchor_generator_object._aspect_ratios,
[0.3, 4.5])
with self.test_session() as sess:
base_anchor_size, anchor_offset, anchor_stride = sess.run(
[anchor_generator_object._base_anchor_size,
anchor_generator_object._anchor_offset,
anchor_generator_object._anchor_stride])
self.assertAllEqual(anchor_offset, [30, 40])
self.assertAllEqual(anchor_stride, [10, 20])
self.assertAllEqual(base_anchor_size, [128, 512])
def test_build_ssd_anchor_generator_with_defaults(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [1.0]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales),
[(0.1, 0.2, 0.2),
(0.35, 0.418),
(0.499, 0.570),
(0.649, 0.721),
(0.799, 0.871),
(0.949, 0.974)]):
self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
[(1.0, 2.0, 0.5)] + 5 * [(1.0, 1.0)]):
self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
with self.test_session() as sess:
base_anchor_size = sess.run(anchor_generator_object._base_anchor_size)
self.assertAllClose(base_anchor_size, [1.0, 1.0])
def test_build_ssd_anchor_generator_with_non_default_parameters(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
num_layers: 2
min_scale: 0.3
max_scale: 0.8
aspect_ratios: [2.0]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(
isinstance(
anchor_generator_object,
multiple_grid_anchor_generator.MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales), [(0.1, 0.3, 0.3),
(0.8, )]):
self.assert_almost_list_equal(expected_scales,
actual_scales,
delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5),
(2.0, )]):
self.assert_almost_list_equal(expected_aspect_ratio,
actual_aspect_ratio)
with self.test_session() as sess:
base_anchor_size = sess.run(
anchor_generator_object._base_anchor_size)
self.assertAllClose(base_anchor_size, [1.0, 1.0])
def test_build_multiscale_anchor_generator_custom_aspect_ratios(self):
anchor_generator_text_proto = """
multiscale_anchor_generator {
aspect_ratios: [1.0]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(
isinstance(
anchor_generator_object, multiscale_grid_anchor_generator.
MultiscaleGridAnchorGenerator))
for level, anchor_grid_info in zip(
range(3, 8), anchor_generator_object._anchor_grid_info):
self.assertEqual(set(anchor_grid_info.keys()),
set(['level', 'info']))
self.assertTrue(level, anchor_grid_info['level'])
self.assertEqual(len(anchor_grid_info['info']), 4)
self.assertAllClose(anchor_grid_info['info'][0], [2**0, 2**0.5])
self.assertTrue(anchor_grid_info['info'][1], 1.0)
self.assertAllClose(anchor_grid_info['info'][2],
[4.0 * 2**level, 4.0 * 2**level])
self.assertAllClose(anchor_grid_info['info'][3],
[2**level, 2**level])
def test_build_grid_anchor_generator_with_non_default_parameters(self):
anchor_generator_text_proto = """
grid_anchor_generator {
height: 128
width: 512
height_stride: 10
width_stride: 20
height_offset: 30
width_offset: 40
scales: [0.4, 2.2]
aspect_ratios: [0.3, 4.5]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(
isinstance(anchor_generator_object,
grid_anchor_generator.GridAnchorGenerator))
self.assert_almost_list_equal(anchor_generator_object._scales,
[0.4, 2.2])
self.assert_almost_list_equal(anchor_generator_object._aspect_ratios,
[0.3, 4.5])
with self.test_session() as sess:
base_anchor_size, anchor_offset, anchor_stride = sess.run([
anchor_generator_object._base_anchor_size,
anchor_generator_object._anchor_offset,
anchor_generator_object._anchor_stride
])
self.assertAllEqual(anchor_offset, [30, 40])
self.assertAllEqual(anchor_stride, [10, 20])
self.assertAllEqual(base_anchor_size, [128, 512])
def test_build_ssd_anchor_generator_with_defaults(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [1.0]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(
isinstance(
anchor_generator_object,
multiple_grid_anchor_generator.MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales), [(0.1, 0.2, 0.2),
(0.35, 0.418),
(0.499, 0.570),
(0.649, 0.721),
(0.799, 0.871),
(0.949, 0.974)]):
self.assert_almost_list_equal(expected_scales,
actual_scales,
delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
[(1.0, 2.0, 0.5)] + 5 * [(1.0, 1.0)]):
self.assert_almost_list_equal(expected_aspect_ratio,
actual_aspect_ratio)
with self.test_session() as sess:
base_anchor_size = sess.run(
anchor_generator_object._base_anchor_size)
self.assertAllClose(base_anchor_size, [1.0, 1.0])
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 test_build_ssd_anchor_generator_with_non_default_parameters(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
num_layers: 2
min_scale: 0.3
max_scale: 0.8
aspect_ratios: [2.0]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales),
[(0.1, 0.3, 0.3), (0.8,)]):
self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
[(1.0, 2.0, 0.5), (2.0,)]):
self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
with self.test_session() as sess:
base_anchor_size = sess.run(anchor_generator_object._base_anchor_size)
self.assertAllClose(base_anchor_size, [1.0, 1.0])
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_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)
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,
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 test_build_flexible_anchor_generator(self):
anchor_generator_text_proto = """
flexible_grid_anchor_generator {
anchor_grid {
base_sizes: [1.5]
aspect_ratios: [1.0]
height_stride: 16
width_stride: 20
height_offset: 8
width_offset: 9
}
anchor_grid {
base_sizes: [1.0, 2.0]
aspect_ratios: [1.0, 0.5]
height_stride: 32
width_stride: 30
height_offset: 10
width_offset: 11
}
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertIsInstance(
anchor_generator_object,
flexible_grid_anchor_generator.FlexibleGridAnchorGenerator)
for actual_base_sizes, expected_base_sizes in zip(
list(anchor_generator_object._base_sizes), [(1.5, ),
(1.0, 2.0)]):
self.assert_almost_list_equal(expected_base_sizes,
actual_base_sizes)
for actual_aspect_ratios, expected_aspect_ratios in zip(
list(anchor_generator_object._aspect_ratios), [(1.0, ),
(1.0, 0.5)]):
self.assert_almost_list_equal(expected_aspect_ratios,
actual_aspect_ratios)
for actual_strides, expected_strides in zip(
list(anchor_generator_object._anchor_strides), [(16, 20),
(32, 30)]):
self.assert_almost_list_equal(expected_strides, actual_strides)
for actual_offsets, expected_offsets in zip(
list(anchor_generator_object._anchor_offsets), [(8, 9),
(10, 11)]):
self.assert_almost_list_equal(expected_offsets, actual_offsets)
self.assertTrue(anchor_generator_object._normalize_coordinates)
def test_build_ssd_anchor_generator_with_non_default_parameters(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
num_layers: 2
min_scale: 0.3
max_scale: 0.8
aspect_ratios: [2.0]
height_stride: 16
height_stride: 32
width_stride: 20
width_stride: 30
height_offset: 8
height_offset: 16
width_offset: 0
width_offset: 10
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(
isinstance(
anchor_generator_object,
multiple_grid_anchor_generator.MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales), [(0.1, 0.3, 0.3),
(0.8, 0.894)]):
self.assert_almost_list_equal(expected_scales,
actual_scales,
delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios), [(1.0, 2.0, 0.5),
(2.0, 1.0)]):
self.assert_almost_list_equal(expected_aspect_ratio,
actual_aspect_ratio)
for actual_strides, expected_strides in zip(
list(anchor_generator_object._anchor_strides), [(16, 20),
(32, 30)]):
self.assert_almost_list_equal(expected_strides, actual_strides)
for actual_offsets, expected_offsets in zip(
list(anchor_generator_object._anchor_offsets), [(8, 0),
(16, 10)]):
self.assert_almost_list_equal(expected_offsets, actual_offsets)
self.assertAllClose(anchor_generator_object._base_anchor_size,
[1.0, 1.0])
def _build_faster_rcnn_model(frcnn_config, is_training): #parameters are config of the faster RCNN
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
#The config file consist of the the model parammeters
num_classes = frcnn_config.num_classes #getting the classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer) #returns - image_resizer_fn: Callable for image resizing
feature_extractor = _build_faster_rcnn_feature_extractor( #create the feature extractor
frcnn_config.feature_extractor, is_training) #this will take the part of the resnet as a feature extrator
first_stage_only = frcnn_config.first_stage_only #No field in faser Rcnn config file Since this is fale this is comple faster Rcnn
first_stage_anchor_generator = anchor_generator_builder.build( #here the anchor generator model preparation
frcnn_config.first_stage_anchor_generator) #here inside the model we get the first_stage_anchor_generator and with that we go to the it's params
#In above 3 outputs we get 3 functions capable of doing aboive tasks !
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate #not in the config file
first_stage_box_predictor_arg_scope = hyperparams_builder.build( #hyper parameters builder for first stage rpn network
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = ( #This predicts the first stage conv window on the feature map of RON
frcnn_config.first_stage_box_predictor_kernel_size) #not given
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth #not given #Output depth for the convolution op just prior to RPN box predictions
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size # What is the bathc size
first_stage_positive_balance_fraction = ( #balance of the positive examples any way not given
frcnn_config.first_stage_positive_balance_fraction)
def test_build_grid_anchor_generator_with_defaults(self):
anchor_generator_text_proto = """
grid_anchor_generator {
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
grid_anchor_generator.GridAnchorGenerator))
self.assertListEqual(anchor_generator_object._scales, [])
self.assertListEqual(anchor_generator_object._aspect_ratios, [])
self.assertAllEqual(anchor_generator_object._anchor_offset, [0, 0])
self.assertAllEqual(anchor_generator_object._anchor_stride, [16, 16])
self.assertAllEqual(anchor_generator_object._base_anchor_size, [256, 256])
def test_build_multiscale_anchor_generator_with_anchors_in_pixel_coordinates(
self):
anchor_generator_text_proto = """
multiscale_anchor_generator {
aspect_ratios: [1.0]
normalize_coordinates: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiscale_grid_anchor_generator.
MultiscaleGridAnchorGenerator))
self.assertFalse(anchor_generator_object._normalize_coordinates)
def test_build_multiscale_anchor_generator_with_anchors_in_pixel_coordinates(
self):
anchor_generator_text_proto = """
multiscale_anchor_generator {
aspect_ratios: [1.0]
normalize_coordinates: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertIsInstance(
anchor_generator_object,
multiscale_grid_anchor_generator.MultiscaleGridAnchorGenerator)
self.assertFalse(anchor_generator_object._normalize_coordinates)
def test_build_grid_anchor_generator_with_defaults(self):
anchor_generator_text_proto = """
grid_anchor_generator {
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertIsInstance(anchor_generator_object,
grid_anchor_generator.GridAnchorGenerator)
self.assertListEqual(anchor_generator_object._scales, [])
self.assertListEqual(anchor_generator_object._aspect_ratios, [])
self.assertAllEqual(anchor_generator_object._anchor_offset, [0, 0])
self.assertAllEqual(anchor_generator_object._anchor_stride, [16, 16])
self.assertAllEqual(anchor_generator_object._base_anchor_size, [256, 256])
def test_build_ssd_anchor_generator_with_non_default_parameters(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
num_layers: 2
min_scale: 0.3
max_scale: 0.8
aspect_ratios: [2.0]
height_stride: 16
height_stride: 32
width_stride: 20
width_stride: 30
height_offset: 8
height_offset: 16
width_offset: 0
width_offset: 10
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales),
[(0.1, 0.3, 0.3), (0.8, 0.894)]):
self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
[(1.0, 2.0, 0.5), (2.0, 1.0)]):
self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
for actual_strides, expected_strides in zip(
list(anchor_generator_object._anchor_strides), [(16, 20), (32, 30)]):
self.assert_almost_list_equal(expected_strides, actual_strides)
for actual_offsets, expected_offsets in zip(
list(anchor_generator_object._anchor_offsets), [(8, 0), (16, 10)]):
self.assert_almost_list_equal(expected_offsets, actual_offsets)
self.assertAllClose(anchor_generator_object._base_anchor_size, [1.0, 1.0])
def test_build_ssd_anchor_generator_with_custom_interpolated_scale(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [0.5]
interpolated_scale_aspect_ratio: 0.5
reduce_boxes_in_lowest_layer: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertIsInstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator)
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
6 * [(0.5, 0.5)]):
self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
def _build_yolo_model(yolo_config, is_training):
"""Builds an YOLO detection model based on the model config.
Args:
yolo_config: A yolo.proto object containing the config for the desired
YOLOMetaArch.
is_training: True if this model is being built for training purposes.
Returns:
YOLOMetaArch based on the config.
Raises:
ValueError: If yolo_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = yolo_config.num_classes
# Feature extractor
feature_extractor = _build_yolo_feature_extractor(
yolo_config.feature_extractor, is_training)
box_coder = box_coder_builder.build(yolo_config.box_coder)
matcher = matcher_builder.build(yolo_config.matcher)
region_similarity_calculator = sim_calc.build(
yolo_config.similarity_calculator)
yolo_box_predictor = box_predictor_builder.build(hyperparams_builder.build,
yolo_config.box_predictor,
is_training, num_classes)
anchor_generator = anchor_generator_builder.build(
yolo_config.anchor_generator)
image_resizer_fn = image_resizer_builder.build(yolo_config.image_resizer)
non_max_suppression_fn, score_conversion_fn = post_processing_builder.build(
yolo_config.post_processing)
(classification_loss, localization_loss, classification_weight,
localization_weight,
hard_example_miner) = losses_builder.build(yolo_config.loss)
normalize_loss_by_num_matches = yolo_config.normalize_loss_by_num_matches
return yolo_meta_arch.YOLOMetaArch(
is_training, anchor_generator, yolo_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 test_build_ssd_anchor_generator_with_custom_interpolated_scale(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [0.5]
interpolated_scale_aspect_ratio: 0.5
reduce_boxes_in_lowest_layer: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator))
for actual_aspect_ratio, expected_aspect_ratio in zip(
list(anchor_generator_object._aspect_ratios),
6 * [(0.5, 0.5)]):
self.assert_almost_list_equal(expected_aspect_ratio, actual_aspect_ratio)
def _build_east_model(east_config, is_training):
"""Builds an EAST detection model based on the model config.
Args:
east_config: A east.proto object containing the config for the desired
SSDMetaArch.
is_training: True if this model is being built for training purposes.
Returns:
EASTMetaArch based on the config.
Raises:
ValueError: If east_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = east_config.num_classes
# Feature extractor
feature_extractor = _build_east_feature_extractor(
east_config.feature_extractor, is_training)
box_coder = box_coder_builder.build(east_config.box_coder)
box_predictor = box_predictor_builder.build(hyperparams_builder.build,
east_config.box_predictor,
is_training, num_classes)
anchor_generator = anchor_generator_builder.build(
east_config.anchor_generator)
#image_resizer_fn = image_resizer_builder.build(east_config.image_resizer)
image_resizer_fn = None
non_max_suppression_fn, score_conversion_fn = post_processing_builder.build(
east_config.post_processing)
(classification_loss, localization_loss, classification_weight,
localization_weight,
hard_example_miner) = losses_builder.build(east_config.loss)
normalize_loss_by_num_matches = east_config.normalize_loss_by_num_matches
return east_meta_arch.EASTMetaArch(
is_training, anchor_generator, box_predictor, box_coder,
feature_extractor, image_resizer_fn, non_max_suppression_fn,
score_conversion_fn, classification_loss, localization_loss,
classification_weight, localization_weight,
normalize_loss_by_num_matches)
def test_build_ssd_anchor_generator_with_custom_scales(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [1.0]
scales: [0.1, 0.15, 0.2, 0.4, 0.6, 0.8]
reduce_boxes_in_lowest_layer: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertIsInstance(
anchor_generator_object,
multiple_grid_anchor_generator.MultipleGridAnchorGenerator)
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales),
[(0.1, math.sqrt(0.1 * 0.15)), (0.15, math.sqrt(0.15 * 0.2)),
(0.2, math.sqrt(0.2 * 0.4)), (0.4, math.sqrt(0.4 * 0.6)),
(0.6, math.sqrt(0.6 * 0.8)), (0.8, math.sqrt(0.8 * 1.0))]):
self.assert_almost_list_equal(expected_scales,
actual_scales,
delta=1e-2)
def test_build_ssd_anchor_generator_with_custom_scales(self):
anchor_generator_text_proto = """
ssd_anchor_generator {
aspect_ratios: [1.0]
scales: [0.1, 0.15, 0.2, 0.4, 0.6, 0.8]
reduce_boxes_in_lowest_layer: false
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiple_grid_anchor_generator.
MultipleGridAnchorGenerator))
for actual_scales, expected_scales in zip(
list(anchor_generator_object._scales),
[(0.1, math.sqrt(0.1 * 0.15)),
(0.15, math.sqrt(0.15 * 0.2)),
(0.2, math.sqrt(0.2 * 0.4)),
(0.4, math.sqrt(0.4 * 0.6)),
(0.6, math.sqrt(0.6 * 0.8)),
(0.8, math.sqrt(0.8 * 1.0))]):
self.assert_almost_list_equal(expected_scales, actual_scales, delta=1e-2)
def test_build_multiscale_anchor_generator_custom_aspect_ratios(self):
anchor_generator_text_proto = """
multiscale_anchor_generator {
aspect_ratios: [1.0]
}
"""
anchor_generator_proto = anchor_generator_pb2.AnchorGenerator()
text_format.Merge(anchor_generator_text_proto, anchor_generator_proto)
anchor_generator_object = anchor_generator_builder.build(
anchor_generator_proto)
self.assertTrue(isinstance(anchor_generator_object,
multiscale_grid_anchor_generator.
MultiscaleGridAnchorGenerator))
for level, anchor_grid_info in zip(
range(3, 8), anchor_generator_object._anchor_grid_info):
self.assertEqual(set(anchor_grid_info.keys()), set(['level', 'info']))
self.assertTrue(level, anchor_grid_info['level'])
self.assertEqual(len(anchor_grid_info['info']), 4)
self.assertAllClose(anchor_grid_info['info'][0], [2**0, 2**0.5])
self.assertTrue(anchor_grid_info['info'][1], 1.0)
self.assertAllClose(anchor_grid_info['info'][2],
[4.0 * 2**level, 4.0 * 2**level])
self.assertAllClose(anchor_grid_info['info'][3], [2**level, 2**level])
self.assertTrue(anchor_generator_object._normalize_coordinates)
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_faster_rcnn_model(frcnn_config, is_training, add_summaries):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor, is_training,
frcnn_config.inplace_batchnorm_update)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
first_stage_positive_balance_fraction = (
frcnn_config.first_stage_positive_balance_fraction)
first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold
first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_balance_fraction = frcnn_config.second_stage_balance_fraction
(second_stage_non_max_suppression_fn,
second_stage_score_conversion_fn) = post_processing_builder.build(
frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'number_of_stages': number_of_stages,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope_fn':
first_stage_box_predictor_arg_scope_fn,
'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_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_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': second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner,
'add_summaries': add_summaries
}
if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
def _build_faster_rcnn_model(frcnn_config,
is_training,
add_summaries,
meta_architecture='faster_rcnn'):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor, is_training,
frcnn_config.inplace_batchnorm_update)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
# TODO(bhattad): When eval is supported using static shapes, add separate
# use_static_shapes_for_trainig and use_static_shapes_for_evaluation.
use_static_shapes = frcnn_config.use_static_shapes and is_training
first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.first_stage_positive_balance_fraction,
is_static=frcnn_config.use_static_balanced_label_sampler
and is_training)
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
first_stage_proposals_path = frcnn_config.first_stage_proposals_path
if (frcnn_config.first_stage_nms_iou_threshold < 0
or frcnn_config.first_stage_nms_iou_threshold > 1.0):
raise ValueError('iou_threshold not in [0, 1.0].')
if (is_training and
frcnn_config.second_stage_batch_size > first_stage_max_proposals):
raise ValueError('second_stage_batch_size should be no greater than '
'first_stage_max_proposals.')
first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=frcnn_config.first_stage_nms_score_threshold,
iou_thresh=frcnn_config.first_stage_nms_iou_threshold,
max_size_per_class=frcnn_config.first_stage_max_proposals,
max_total_size=frcnn_config.first_stage_max_proposals,
use_static_shapes=use_static_shapes and is_training)
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher,
iou_threshold=frcnn_config.second_stage_target_iou_threshold)
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.second_stage_balance_fraction,
is_static=frcnn_config.use_static_balanced_label_sampler
and is_training)
(second_stage_non_max_suppression_fn,
second_stage_score_conversion_fn) = post_processing_builder.build(
frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
crop_and_resize_fn = (ops.matmul_crop_and_resize
if frcnn_config.use_matmul_crop_and_resize else
ops.native_crop_and_resize)
clip_anchors_to_image = (frcnn_config.clip_anchors_to_image)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'number_of_stages': number_of_stages,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_target_assigner': first_stage_target_assigner,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope_fn':
first_stage_box_predictor_arg_scope_fn,
'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_sampler': first_stage_sampler,
'first_stage_non_max_suppression_fn':
first_stage_non_max_suppression_fn,
'first_stage_max_proposals': first_stage_max_proposals,
'first_stage_localization_loss_weight': first_stage_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_loss_weight,
'second_stage_target_assigner': second_stage_target_assigner,
'second_stage_batch_size': second_stage_batch_size,
'second_stage_sampler': second_stage_sampler,
'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': second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner,
'add_summaries': add_summaries,
'crop_and_resize_fn': crop_and_resize_fn,
'clip_anchors_to_image': clip_anchors_to_image,
'use_static_shapes': use_static_shapes,
'resize_masks': frcnn_config.resize_masks
}
if isinstance(second_stage_box_predictor,
rfcn_box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
elif meta_architecture == 'faster_rcnn':
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
elif meta_architecture == 'faster_rcnn_override_RPN':
return faster_rcnn_meta_arch_override_RPN.FasterRCNNMetaArchOverrideRPN(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
first_stage_proposals_path=first_stage_proposals_path,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
elif meta_architecture == 'faster_rcnn_rpn_blend':
common_kwargs['use_matmul_crop_and_resize'] = False
common_kwargs[
'first_stage_nms_iou_threshold'] = frcnn_config.first_stage_nms_iou_threshold
common_kwargs[
'first_stage_nms_score_threshold'] = frcnn_config.first_stage_nms_score_threshold
common_kwargs.pop('crop_and_resize_fn')
common_kwargs.pop('first_stage_non_max_suppression_fn')
common_kwargs.pop('resize_masks')
common_kwargs.pop('use_static_shapes')
return faster_rcnn_meta_arch_rpn_blend.FasterRCNNMetaArchRPNBlend(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
first_stage_proposals_path=first_stage_proposals_path,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
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)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries, **kwargs):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
kwargs: key-value
'rpn_type' is the type of rpn which is 'cascade_rpn','orign_rpn'
and 'without_rpn' which need some boxes replacing the proposal
generated by rpn
'filter_fn_arg' is the args of filter fn which need the boxes to filter
the proposals.
'replace_rpn_arg' is a dictionary.
only if the rpn_type=='without_rpn' and not None, it's useful in order to
replace the proposals generated by rpn with the gt which maybe adjusted.
'type': a string which is 'gt' or 'others'.
'scale': a float which is used to scale the boxes(maybe gt).
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor, is_training,
inplace_batchnorm_update=frcnn_config.inplace_batchnorm_update)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
use_static_shapes = frcnn_config.use_static_shapes and (
frcnn_config.use_static_shapes_for_eval or is_training)
first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.first_stage_positive_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler and
use_static_shapes))
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
if (frcnn_config.first_stage_nms_iou_threshold < 0 or
frcnn_config.first_stage_nms_iou_threshold > 1.0):
raise ValueError('iou_threshold not in [0, 1.0].')
if (is_training and frcnn_config.second_stage_batch_size >
first_stage_max_proposals):
raise ValueError('second_stage_batch_size should be no greater than '
'first_stage_max_proposals.')
first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=frcnn_config.first_stage_nms_score_threshold,
iou_thresh=frcnn_config.first_stage_nms_iou_threshold,
max_size_per_class=frcnn_config.first_stage_max_proposals,
max_total_size=frcnn_config.first_stage_max_proposals,
use_static_shapes=use_static_shapes)
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.second_stage_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler and
use_static_shapes))
(second_stage_non_max_suppression_fn, second_stage_score_conversion_fn
) = post_processing_builder.build(frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
crop_and_resize_fn = (
ops.matmul_crop_and_resize if frcnn_config.use_matmul_crop_and_resize
else ops.native_crop_and_resize)
clip_anchors_to_image = (
frcnn_config.clip_anchors_to_image)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'number_of_stages': number_of_stages,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_target_assigner': first_stage_target_assigner,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope_fn':
first_stage_box_predictor_arg_scope_fn,
'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_sampler': first_stage_sampler,
'first_stage_non_max_suppression_fn': first_stage_non_max_suppression_fn,
'first_stage_max_proposals': first_stage_max_proposals,
'first_stage_localization_loss_weight': first_stage_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_loss_weight,
'second_stage_target_assigner': second_stage_target_assigner,
'second_stage_batch_size': second_stage_batch_size,
'second_stage_sampler': second_stage_sampler,
'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':
second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner,
'add_summaries': add_summaries,
'crop_and_resize_fn': crop_and_resize_fn,
'clip_anchors_to_image': clip_anchors_to_image,
'use_static_shapes': use_static_shapes,
'resize_masks': frcnn_config.resize_masks
}
filter_fn_arg = kwargs.get('filter_fn_arg')
if filter_fn_arg:
filter_fn = functools.partial(filter_bbox, **filter_fn_arg)
common_kwargs['filter_fn'] = filter_fn
rpn_type = kwargs.get('rpn_type')
if rpn_type:
common_kwargs['rpn_type'] = rpn_type
replace_rpn_arg = kwargs.get('replace_rpn_arg')
if replace_rpn_arg:
common_kwargs['replace_rpn_arg'] = replace_rpn_arg
if isinstance(second_stage_box_predictor,
rfcn_box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
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(
feature_extractor_config=ssd_config.feature_extractor,
freeze_batchnorm=ssd_config.freeze_batchnorm,
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
anchor_generator = anchor_generator_builder.build(
ssd_config.anchor_generator)
if feature_extractor.is_keras_model:
ssd_box_predictor = box_predictor_builder.build_keras(
hyperparams_fn=hyperparams_builder.KerasLayerHyperparams,
freeze_batchnorm=ssd_config.freeze_batchnorm,
inplace_batchnorm_update=False,
num_predictions_per_location_list=anchor_generator.
num_anchors_per_location(),
box_predictor_config=ssd_config.box_predictor,
is_training=is_training,
num_classes=num_classes,
add_background_class=ssd_config.add_background_class)
else:
ssd_box_predictor = box_predictor_builder.build(
hyperparams_builder.build, ssd_config.box_predictor, is_training,
num_classes, ssd_config.add_background_class)
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,
expected_loss_weights_fn) = 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
equalization_loss_config = ops.EqualizationLossConfig(
weight=ssd_config.loss.equalization_loss.weight,
exclude_prefixes=ssd_config.loss.equalization_loss.exclude_prefixes)
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
box_coder,
negative_class_weight=negative_class_weight)
ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch
kwargs = {}
return ssd_meta_arch_fn(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=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_weight,
localization_loss_weight=localization_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=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=ssd_config.add_background_class,
explicit_background_class=ssd_config.explicit_background_class,
random_example_sampler=random_example_sampler,
expected_loss_weights_fn=expected_loss_weights_fn,
use_confidences_as_targets=ssd_config.use_confidences_as_targets,
implicit_example_weight=ssd_config.implicit_example_weight,
equalization_loss_config=equalization_loss_config,
return_raw_detections_during_predict=(
ssd_config.return_raw_detections_during_predict),
**kwargs)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor, is_training)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
first_stage_positive_balance_fraction = (
frcnn_config.first_stage_positive_balance_fraction)
first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold
first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_balance_fraction = frcnn_config.second_stage_balance_fraction
(second_stage_non_max_suppression_fn, second_stage_score_conversion_fn
) = post_processing_builder.build(frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'number_of_stages': number_of_stages,
'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_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_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':
second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner,
'add_summaries': add_summaries}
if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
def _build_ssd_model(ssd_config, is_training, add_summaries):
num_classes = ssd_config.num_classes
# Feature extractor
feature_extractor = _build_ssd_feature_extractor(
feature_extractor_config=ssd_config.feature_extractor,
freeze_batchnorm=ssd_config.freeze_batchnorm,
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
anchor_generator = anchor_generator_builder.build(
ssd_config.anchor_generator)
if feature_extractor.is_keras_model:
ssd_box_predictor = box_predictor_builder.build_keras(
hyperparams_fn=hyperparams_builder.KerasLayerHyperparams,
freeze_batchnorm=ssd_config.freeze_batchnorm,
inplace_batchnorm_update=False,
num_predictions_per_location_list=anchor_generator
.num_anchors_per_location(),
box_predictor_config=ssd_config.box_predictor,
is_training=is_training,
num_classes=num_classes,
add_background_class=ssd_config.add_background_class)
else:
ssd_box_predictor = box_predictor_builder.build(
hyperparams_builder.build, ssd_config.box_predictor, is_training,
num_classes, ssd_config.add_background_class)
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,
expected_loss_weights_fn) = 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
equalization_loss_config = ops.EqualizationLossConfig(
weight=ssd_config.loss.equalization_loss.weight,
exclude_prefixes=ssd_config.loss.equalization_loss.exclude_prefixes)
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
box_coder,
negative_class_weight=negative_class_weight)
ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch
kwargs = {}
return ssd_meta_arch_fn(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=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_weight,
localization_loss_weight=localization_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=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=ssd_config.add_background_class,
explicit_background_class=ssd_config.explicit_background_class,
random_example_sampler=random_example_sampler,
expected_loss_weights_fn=expected_loss_weights_fn,
use_confidences_as_targets=ssd_config.use_confidences_as_targets,
implicit_example_weight=ssd_config.implicit_example_weight,
equalization_loss_config=equalization_loss_config,
**kwargs)
def _build_lstm_model(ssd_config, lstm_config, is_training):
"""Builds an LSTM detection model based on the model config.
Args:
ssd_config: A ssd.proto object containing the config for the desired
LSTMMetaArch.
lstm_config: LstmModel config proto that specifies LSTM train/eval configs.
is_training: True if this model is being built for training purposes.
Returns:
LSTMMetaArch based on the config.
Raises:
ValueError: If ssd_config.type is not recognized (i.e. not registered in
model_class_map), or if lstm_config.interleave_strategy is not recognized.
ValueError: If unroll_length is not specified in the config file.
"""
feature_extractor = _build_lstm_feature_extractor(
ssd_config.feature_extractor, is_training, lstm_config.lstm_state_depth)
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)
num_classes = ssd_config.num_classes
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, miner, _, _) = losses_builder.build(ssd_config.loss)
normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches
encode_background_as_zeros = ssd_config.encode_background_as_zeros
negative_class_weight = ssd_config.negative_class_weight
# Extra configs for lstm unroll length.
unroll_length = None
if 'lstm' in ssd_config.feature_extractor.type:
if is_training:
unroll_length = lstm_config.train_unroll_length
else:
unroll_length = lstm_config.eval_unroll_length
if unroll_length is None:
raise ValueError('No unroll length found in the config file')
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
box_coder,
negative_class_weight=negative_class_weight)
lstm_model = lstm_meta_arch.LSTMMetaArch(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=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_weight,
localization_loss_weight=localization_weight,
normalize_loss_by_num_matches=normalize_loss_by_num_matches,
hard_example_miner=miner,
unroll_length=unroll_length,
target_assigner_instance=target_assigner_instance)
return lstm_model
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
weight_regression_loss_by_score = (
ssd_config.weight_regression_loss_by_score)
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
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 ssd_config.use_expected_classification_loss_under_sampling:
expected_classification_loss_under_sampling = functools.partial(
ops.expected_classification_loss_under_sampling,
minimum_negative_sampling=ssd_config.minimum_negative_sampling,
desired_negative_sampling_ratio=ssd_config.
desired_negative_sampling_ratio)
ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch
# BEGIN GOOGLE-INTERNAL
# TODO(lzc): move ssd_mask_meta_arch to third party when it has decent
# performance relative to a comparable Mask R-CNN model (b/112561592).
predictor_config = ssd_config.box_predictor
predict_instance_masks = False
if predictor_config.WhichOneof(
'box_predictor_oneof') == 'convolutional_box_predictor':
predict_instance_masks = (
predictor_config.convolutional_box_predictor.HasField('mask_head'))
elif predictor_config.WhichOneof(
'box_predictor_oneof'
) == 'weight_shared_convolutional_box_predictor':
predict_instance_masks = (
predictor_config.weight_shared_convolutional_box_predictor.
HasField('mask_head'))
if predict_instance_masks:
ssd_meta_arch_fn = ssd_mask_meta_arch.SSDMaskMetaArch
# END GOOGLE-INTERNAL
return ssd_meta_arch_fn(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=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_weight,
localization_loss_weight=localization_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=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,
expected_classification_loss_under_sampling=
expected_classification_loss_under_sampling)
def _build_faster_rcnn_model(frcnn_config, is_training, mtl=None):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor_kwargs = {}
feature_extractor_kwargs[
'freeze_layer'] = frcnn_config.feature_extractor.freeze_layer
feature_extractor_kwargs[
'batch_norm_trainable'] = frcnn_config.feature_extractor.batch_norm_trainable
if frcnn_config.feature_extractor.HasField('weight_decay'):
feature_extractor_kwargs['weight_decay'] = \
frcnn_config.feature_extractor.weight_decay
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor,
is_training and frcnn_config.feature_extractor.trainable,
reuse_weights=tf.AUTO_REUSE,
**feature_extractor_kwargs)
first_stage_only = frcnn_config.first_stage_only
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_clip_window = frcnn_config.first_stage_clip_window
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_trainable = \
frcnn_config.first_stage_box_predictor_trainable
first_stage_box_predictor_arg_scope = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
first_stage_positive_balance_fraction = (
frcnn_config.first_stage_positive_balance_fraction)
first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold
first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training
and frcnn_config.second_stage_box_predictor.trainable,
num_classes=num_classes,
reuse_weights=tf.AUTO_REUSE)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_balance_fraction = frcnn_config.second_stage_balance_fraction
(second_stage_non_max_suppression_fn,
second_stage_score_conversion_fn) = post_processing_builder.build(
frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
if mtl.window:
window_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
mtl.window_box_predictor,
is_training=is_training and mtl.window_box_predictor.trainable,
num_classes=num_classes + 1,
reuse_weights=tf.AUTO_REUSE)
else:
window_box_predictor = second_stage_box_predictor
if mtl.closeness:
closeness_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
mtl.closeness_box_predictor,
is_training=is_training and mtl.closeness_box_predictor.trainable,
num_classes=num_classes + 1,
reuse_weights=tf.AUTO_REUSE)
else:
closeness_box_predictor = second_stage_box_predictor
if mtl.edgemask:
edgemask_predictor = mask_predictor_builder.build(
hyperparams_builder.build,
mtl.edgemask_predictor,
is_training=is_training and mtl.edgemask_predictor.trainable,
num_classes=2,
reuse_weights=tf.AUTO_REUSE,
channels=1)
else:
edgemask_predictor = None
mtl_refiner_arg_scope = None
if mtl.refine:
mtl_refiner_arg_scope = hyperparams_builder.build(
mtl.refiner_fc_hyperparams, is_training)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'first_stage_only': first_stage_only,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_clip_window': first_stage_clip_window,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_trainable':
first_stage_box_predictor_trainable,
'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_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_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,
'mtl': mtl,
'mtl_refiner_arg_scope': mtl_refiner_arg_scope,
'window_box_predictor': window_box_predictor,
'closeness_box_predictor': closeness_box_predictor,
'edgemask_predictor': edgemask_predictor
}
if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
**common_kwargs)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor, is_training,
frcnn_config.inplace_batchnorm_update)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
use_static_shapes = frcnn_config.use_static_shapes
first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.first_stage_positive_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler and
use_static_shapes))
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
if (frcnn_config.first_stage_nms_iou_threshold < 0 or
frcnn_config.first_stage_nms_iou_threshold > 1.0):
raise ValueError('iou_threshold not in [0, 1.0].')
if (is_training and frcnn_config.second_stage_batch_size >
first_stage_max_proposals):
raise ValueError('second_stage_batch_size should be no greater than '
'first_stage_max_proposals.')
first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=frcnn_config.first_stage_nms_score_threshold,
iou_thresh=frcnn_config.first_stage_nms_iou_threshold,
max_size_per_class=frcnn_config.first_stage_max_proposals,
max_total_size=frcnn_config.first_stage_max_proposals,
use_static_shapes=use_static_shapes)
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.second_stage_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler and
use_static_shapes))
(second_stage_non_max_suppression_fn, second_stage_score_conversion_fn
) = post_processing_builder.build(frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
crop_and_resize_fn = (
ops.matmul_crop_and_resize if frcnn_config.use_matmul_crop_and_resize
else ops.native_crop_and_resize)
clip_anchors_to_image = (
frcnn_config.clip_anchors_to_image)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'number_of_stages': number_of_stages,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_target_assigner': first_stage_target_assigner,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope_fn':
first_stage_box_predictor_arg_scope_fn,
'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_sampler': first_stage_sampler,
'first_stage_non_max_suppression_fn': first_stage_non_max_suppression_fn,
'first_stage_max_proposals': first_stage_max_proposals,
'first_stage_localization_loss_weight': first_stage_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_loss_weight,
'second_stage_target_assigner': second_stage_target_assigner,
'second_stage_batch_size': second_stage_batch_size,
'second_stage_sampler': second_stage_sampler,
'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':
second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner,
'add_summaries': add_summaries,
'crop_and_resize_fn': crop_and_resize_fn,
'clip_anchors_to_image': clip_anchors_to_image,
'use_static_shapes': use_static_shapes,
'resize_masks': frcnn_config.resize_masks
}
if isinstance(second_stage_box_predictor,
rfcn_box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
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 _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(
feature_extractor_config=ssd_config.feature_extractor,
freeze_batchnorm=ssd_config.freeze_batchnorm,
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
anchor_generator = anchor_generator_builder.build(
ssd_config.anchor_generator)
if feature_extractor.is_keras_model:
ssd_box_predictor = box_predictor_builder.build_keras(
conv_hyperparams_fn=hyperparams_builder.KerasLayerHyperparams,
freeze_batchnorm=ssd_config.freeze_batchnorm,
inplace_batchnorm_update=False,
num_predictions_per_location_list=anchor_generator
.num_anchors_per_location(),
box_predictor_config=ssd_config.box_predictor,
is_training=is_training,
num_classes=num_classes,
add_background_class=ssd_config.add_background_class)
else:
ssd_box_predictor = box_predictor_builder.build(
hyperparams_builder.build, ssd_config.box_predictor, is_training,
num_classes, ssd_config.add_background_class)
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
weight_regression_loss_by_score = (ssd_config.weight_regression_loss_by_score)
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
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 ssd_config.use_expected_classification_loss_under_sampling:
expected_classification_loss_under_sampling = functools.partial(
ops.expected_classification_loss_under_sampling,
min_num_negative_samples=ssd_config.min_num_negative_samples,
desired_negative_sampling_ratio=ssd_config.
desired_negative_sampling_ratio)
ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch
return ssd_meta_arch_fn(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=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_weight,
localization_loss_weight=localization_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=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=ssd_config.add_background_class,
random_example_sampler=random_example_sampler,
expected_classification_loss_under_sampling=
expected_classification_loss_under_sampling)
def _build_lstm_model(ssd_config, lstm_config, is_training):
"""Builds an LSTM detection model based on the model config.
Args:
ssd_config: A ssd.proto object containing the config for the desired
LSTMSSDMetaArch.
lstm_config: LstmModel config proto that specifies LSTM train/eval configs.
is_training: True if this model is being built for training purposes.
Returns:
LSTMSSDMetaArch based on the config.
Raises:
ValueError: If ssd_config.type is not recognized (i.e. not registered in
model_class_map), or if lstm_config.interleave_strategy is not recognized.
ValueError: If unroll_length is not specified in the config file.
"""
feature_extractor = _build_lstm_feature_extractor(
ssd_config.feature_extractor, is_training, lstm_config)
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)
num_classes = ssd_config.num_classes
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, miner, _, _) = losses_builder.build(ssd_config.loss)
normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches
encode_background_as_zeros = ssd_config.encode_background_as_zeros
negative_class_weight = ssd_config.negative_class_weight
# Extra configs for lstm unroll length.
unroll_length = None
if 'lstm' in ssd_config.feature_extractor.type:
if is_training:
unroll_length = lstm_config.train_unroll_length
else:
unroll_length = lstm_config.eval_unroll_length
if unroll_length is None:
raise ValueError('No unroll length found in the config file')
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
box_coder,
negative_class_weight=negative_class_weight)
lstm_model = lstm_ssd_meta_arch.LSTMSSDMetaArch(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=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_weight,
localization_loss_weight=localization_weight,
normalize_loss_by_num_matches=normalize_loss_by_num_matches,
hard_example_miner=miner,
unroll_length=unroll_length,
target_assigner_instance=target_assigner_instance)
return lstm_model
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
is_keras = (frcnn_config.feature_extractor.type
in FASTER_RCNN_KERAS_FEATURE_EXTRACTOR_CLASS_MAP)
if is_keras:
feature_extractor = _build_faster_rcnn_keras_feature_extractor(
frcnn_config.feature_extractor,
is_training,
inplace_batchnorm_update=frcnn_config.inplace_batchnorm_update)
else:
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor,
is_training,
inplace_batchnorm_update=frcnn_config.inplace_batchnorm_update)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
if is_keras:
first_stage_box_predictor_arg_scope_fn = (
hyperparams_builder.KerasLayerHyperparams(
frcnn_config.first_stage_box_predictor_conv_hyperparams))
else:
first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams,
is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
use_static_shapes = frcnn_config.use_static_shapes and (
frcnn_config.use_static_shapes_for_eval or is_training)
first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.first_stage_positive_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler
and use_static_shapes))
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
if (frcnn_config.first_stage_nms_iou_threshold < 0
or frcnn_config.first_stage_nms_iou_threshold > 1.0):
raise ValueError('iou_threshold not in [0, 1.0].')
if (is_training and
frcnn_config.second_stage_batch_size > first_stage_max_proposals):
raise ValueError('second_stage_batch_size should be no greater than '
'first_stage_max_proposals.')
first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=frcnn_config.first_stage_nms_score_threshold,
iou_thresh=frcnn_config.first_stage_nms_iou_threshold,
max_size_per_class=frcnn_config.first_stage_max_proposals,
max_total_size=frcnn_config.first_stage_max_proposals,
use_static_shapes=use_static_shapes,
use_partitioned_nms=frcnn_config.use_partitioned_nms_in_first_stage,
use_combined_nms=frcnn_config.use_combined_nms_in_first_stage)
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
if is_keras:
second_stage_box_predictor = box_predictor_builder.build_keras(
hyperparams_builder.KerasLayerHyperparams,
freeze_batchnorm=False,
inplace_batchnorm_update=False,
num_predictions_per_location_list=[1],
box_predictor_config=frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
else:
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.second_stage_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler
and use_static_shapes))
(second_stage_non_max_suppression_fn,
second_stage_score_conversion_fn) = post_processing_builder.build(
frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
crop_and_resize_fn = (ops.matmul_crop_and_resize
if frcnn_config.use_matmul_crop_and_resize else
ops.native_crop_and_resize)
clip_anchors_to_image = (frcnn_config.clip_anchors_to_image)
common_kwargs = {
'is_training':
is_training,
'num_classes':
num_classes,
'image_resizer_fn':
image_resizer_fn,
'feature_extractor':
feature_extractor,
'number_of_stages':
number_of_stages,
'first_stage_anchor_generator':
first_stage_anchor_generator,
'first_stage_target_assigner':
first_stage_target_assigner,
'first_stage_atrous_rate':
first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope_fn':
first_stage_box_predictor_arg_scope_fn,
'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_sampler':
first_stage_sampler,
'first_stage_non_max_suppression_fn':
first_stage_non_max_suppression_fn,
'first_stage_max_proposals':
first_stage_max_proposals,
'first_stage_localization_loss_weight':
first_stage_loc_loss_weight,
'first_stage_objectness_loss_weight':
first_stage_obj_loss_weight,
'second_stage_target_assigner':
second_stage_target_assigner,
'second_stage_batch_size':
second_stage_batch_size,
'second_stage_sampler':
second_stage_sampler,
'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':
second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner':
hard_example_miner,
'add_summaries':
add_summaries,
'crop_and_resize_fn':
crop_and_resize_fn,
'clip_anchors_to_image':
clip_anchors_to_image,
'use_static_shapes':
use_static_shapes,
'resize_masks':
frcnn_config.resize_masks,
'return_raw_detections_during_predict':
(frcnn_config.return_raw_detections_during_predict)
}
if (isinstance(second_stage_box_predictor,
rfcn_box_predictor.RfcnBoxPredictor)
or isinstance(second_stage_box_predictor,
rfcn_keras_box_predictor.RfcnKerasBoxPredictor)):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
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) = 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)
