def testReturnsCorrectAnchorWiseLossWithHighLogitScaleSetting(self):
"""At very high logit_scale, all predictions will be ~0.33."""
# TODO(yonib): Also test logit_scale with anchorwise=False.
logit_scale = 10e16
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[0, 1, 0],
[1, 0, 0],
[1, 0, 0],
[0, 0, 1]],
[[0, 0, 1],
[0, 1, 0],
[0, 1, 0],
[1, 0, 0]]], tf.float32)
weights = tf.constant([[1, 1, 1, 1],
[1, 1, 1, 1]], tf.float32)
loss_op = losses.WeightedSoftmaxClassificationLoss(logit_scale=logit_scale)
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
uniform_distribution_loss = - math.log(.33333333333)
exp_loss = np.matrix([[uniform_distribution_loss] * 4,
[uniform_distribution_loss] * 4])
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss)
def testReturnsCorrectLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[0, 0, -100],
[-100, -100, 100]],
[[-100, 0, 0],
[-100, 100, -100],
[-100, 100, -100],
[100, -100, -100]]], tf.float32)
target_tensor = tf.constant([[[0, 1, 0],
[1, 0, 0],
[1, 0, 0],
[0, 0, 1]],
[[0, 0, 1],
[0, 1, 0],
[0, 1, 0],
[1, 0, 0]]], tf.float32)
weights = tf.constant([[1, 1, .5, 1],
[1, 1, 1, 0]], tf.float32)
loss_op = losses.WeightedSoftmaxClassificationLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
exp_loss = - 1.5 * math.log(.5)
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss)
def _build_classification_loss(loss_config):
"""Builds a classification loss based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError(
'loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
print('hello', loss_type)
if loss_type == 'weighted_sigmoid':
return losses.WeightedSigmoidClassificationLoss()
if loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
alpha = None
if config.HasField('alpha'):
alpha = config.alpha
return losses.SigmoidFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_logits_softmax':
config = loss_config.weighted_logits_softmax
return losses.WeightedSoftmaxClassificationAgainstLogitsLoss(
logit_scale=config.logit_scale)
if loss_type == 'bootstrapped_sigmoid':
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'))
if loss_type == 'bounded_sigmoid':
config = loss_config.bounded_sigmoid
return losses.BoundedSigmoidCrossEntropyLoss()
if loss_type == 'quadratic_bounded_sigmoid':
config = loss_config.quadratic_bounded_sigmoid
return losses.QuadraticBoundedSigmoidCrossEntropyLoss()
if loss_type == 'soft_target_sigmoid':
config = loss_config.soft_target_sigmoid
return losses.SoftTargetSigmoidCrossEntropyLoss()
raise ValueError('Empty loss config.')
def _build_classification_loss(loss_config):
"""Builds a classification loss based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError(
'loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
return losses.WeightedSigmoidClassificationLoss()
elif loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
alpha = None
if config.HasField('alpha'):
alpha = config.alpha
return losses.SigmoidFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
elif loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
elif loss_type == 'weighted_logits_softmax':
config = loss_config.weighted_logits_softmax
return losses.WeightedSoftmaxClassificationAgainstLogitsLoss(
logit_scale=config.logit_scale)
elif loss_type == 'bootstrapped_sigmoid':
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'))
elif loss_type == 'penalty_reduced_logistic_focal_loss':
config = loss_config.penalty_reduced_logistic_focal_loss
return losses.PenaltyReducedLogisticFocalLoss(alpha=config.alpha,
beta=config.beta)
elif loss_type == 'weighted_dice_classification_loss':
config = loss_config.weighted_dice_classification_loss
return losses.WeightedDiceClassificationLoss(
squared_normalization=config.squared_normalization,
is_prediction_probability=config.is_prediction_probability)
else:
raise ValueError('Empty loss config.')
def build(self):
super(FasterRCNNFirstStageLoss, self).build()
self._proposal_target_assigner = (
target_assigner.create_target_assigner('FasterRCNN', 'proposal'))
self._sampler = (
balanced_positive_negative_sampler.BalancedPositiveNegativeSampler(
positive_fraction=self.positive_balance_fraction,
is_static=False))
self._localization_loss = od_losses.WeightedSmoothL1LocalizationLoss()
self._objectness_loss = od_losses.WeightedSoftmaxClassificationLoss()
return self
def build_faster_rcnn_classification_loss(loss_config):
"""Builds a classification loss for Faster RCNN based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError(
'loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
return losses.WeightedSigmoidClassificationLoss()
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_logits_softmax':
config = loss_config.weighted_logits_softmax
return losses.WeightedSoftmaxClassificationAgainstLogitsLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
alpha = None
if config.HasField('alpha'):
alpha = config.alpha
return losses.SigmoidFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
# By default, Faster RCNN second stage classifier uses Softmax loss
# with anchor-wise outputs.
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
def _build_classification_loss(loss_config):
"""Builds a classification loss based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError(
'loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
config = loss_config.weighted_sigmoid
return losses.WeightedSigmoidClassificationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'confidence_weighted_sigmoid':
config = loss_config.confidence_weighted_sigmoid
return losses.ConfidenceWeightedSigmoidClassificationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
alpha = None
if config.HasField('alpha'):
alpha = config.alpha
return losses.SigmoidFocalClassificationLoss(
anchorwise_output=config.anchorwise_output,
gamma=config.gamma,
alpha=alpha)
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
anchorwise_output=config.anchorwise_output,
logit_scale=config.logit_scale)
if loss_type == 'bootstrapped_sigmoid':
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'),
anchorwise_output=config.anchorwise_output)
raise ValueError('Empty loss config.')
def build_loss(loss_type):
"""Builds the desired type of loss
Args:
loss_type: loss type (e.g. 'berHu', 'smooth_l1')
Returns:
Class of the specified loss_type
"""
if loss_type == 'berHu':
return losses_custom.WeightedBerHu()
elif loss_type == 'chamfer_dist':
return losses_custom.ChamferDistance()
elif loss_type == 'emd':
return losses_custom.EarthMoversDistance()
elif loss_type == 'smooth_l1':
return losses.WeightedSmoothL1LocalizationLoss()
elif loss_type == 'smooth_l1_nonzero':
return losses_custom.WeightedNonZeroSmoothL1LocalizationLoss()
elif loss_type == 'softmax':
return losses.WeightedSoftmaxClassificationLoss()
elif loss_type == 'focal':
return losses.SigmoidFocalClassificationLoss()
elif loss_type == 'softmax_temp':
return losses.WeightedSoftmaxClassificationLoss(0.5)
elif loss_type == 'sigmoid_ce':
return losses_custom.SigmoidClassificationLoss()
else:
raise ValueError('Invalid loss type', loss_type)
def _build_classification_loss(loss_config):
"""Builds a classification loss based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError(
'loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
config = loss_config.weighted_sigmoid
return losses.WeightedSigmoidClassificationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'bootstrapped_sigmoid':
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'),
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_l2':
config = loss_config.weighted_l2
return losses.WeightedL2LocalizationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_smooth_l1':
config = loss_config.weighted_smooth_l1
return losses.WeightedSmoothL1LocalizationLoss(
anchorwise_output=config.anchorwise_output)
raise ValueError('Empty loss config.')
def _build_classification_loss(loss_config):
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError('loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
return losses.WeightedSigmoidClassificationLoss()
if loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
alpha = None
if config.HasField('alpha'):
alpha = config.alpha
return losses.SigmoidFocalClassificationLoss(
gamma=config.gamma,
alpha=alpha)
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
if loss_type == 'weighted_logits_softmax':
config = loss_config.weighted_logits_softmax
return losses.WeightedSoftmaxClassificationAgainstLogitsLoss(
logit_scale=config.logit_scale)
if loss_type == 'bootstrapped_sigmoid':
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'))
raise ValueError('Empty loss config.')
def _build_model(self,
is_training,
number_of_stages,
second_stage_batch_size,
first_stage_max_proposals=8,
num_classes=2,
hard_mining=False,
softmax_second_stage_classification_loss=True,
predict_masks=False,
pad_to_max_dimension=None,
masks_are_class_agnostic=False,
use_matmul_crop_and_resize=False,
clip_anchors_to_image=False,
use_matmul_gather_in_matcher=False,
use_static_shapes=False,
calibration_mapping_value=None,
share_box_across_classes=False,
return_raw_detections_during_predict=False):
use_keras = tf_version.is_tf2()
def image_resizer_fn(image, masks=None):
"""Fake image resizer function."""
resized_inputs = []
resized_image = tf.identity(image)
if pad_to_max_dimension is not None:
resized_image = tf.image.pad_to_bounding_box(
image, 0, 0, pad_to_max_dimension, pad_to_max_dimension)
resized_inputs.append(resized_image)
if masks is not None:
resized_masks = tf.identity(masks)
if pad_to_max_dimension is not None:
resized_masks = tf.image.pad_to_bounding_box(
tf.transpose(masks, [1, 2, 0]), 0, 0,
pad_to_max_dimension, pad_to_max_dimension)
resized_masks = tf.transpose(resized_masks, [2, 0, 1])
resized_inputs.append(resized_masks)
resized_inputs.append(tf.shape(image))
return resized_inputs
# anchors in this test are designed so that a subset of anchors are inside
# the image and a subset of anchors are outside.
first_stage_anchor_scales = (0.001, 0.005, 0.1)
first_stage_anchor_aspect_ratios = (0.5, 1.0, 2.0)
first_stage_anchor_strides = (1, 1)
first_stage_anchor_generator = grid_anchor_generator.GridAnchorGenerator(
first_stage_anchor_scales,
first_stage_anchor_aspect_ratios,
anchor_stride=first_stage_anchor_strides)
first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=use_matmul_gather_in_matcher)
if use_keras:
fake_feature_extractor = FakeFasterRCNNKerasFeatureExtractor()
else:
fake_feature_extractor = FakeFasterRCNNFeatureExtractor()
first_stage_box_predictor_hyperparams_text_proto = """
op: CONV
activation: RELU
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
}
}
"""
if use_keras:
first_stage_box_predictor_arg_scope_fn = (
self._build_keras_layer_hyperparams(
first_stage_box_predictor_hyperparams_text_proto))
else:
first_stage_box_predictor_arg_scope_fn = (
self._build_arg_scope_with_hyperparams(
first_stage_box_predictor_hyperparams_text_proto,
is_training))
first_stage_box_predictor_kernel_size = 3
first_stage_atrous_rate = 1
first_stage_box_predictor_depth = 512
first_stage_minibatch_size = 3
first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=0.5, is_static=use_static_shapes)
first_stage_nms_score_threshold = -1.0
first_stage_nms_iou_threshold = 1.0
first_stage_max_proposals = first_stage_max_proposals
first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=first_stage_nms_score_threshold,
iou_thresh=first_stage_nms_iou_threshold,
max_size_per_class=first_stage_max_proposals,
max_total_size=first_stage_max_proposals,
use_static_shapes=use_static_shapes)
first_stage_localization_loss_weight = 1.0
first_stage_objectness_loss_weight = 1.0
post_processing_config = post_processing_pb2.PostProcessing()
post_processing_text_proto = """
score_converter: IDENTITY
batch_non_max_suppression {
score_threshold: -20.0
iou_threshold: 1.0
max_detections_per_class: 5
max_total_detections: 5
use_static_shapes: """ + '{}'.format(use_static_shapes) + """
}
"""
if calibration_mapping_value:
calibration_text_proto = """
calibration_config {
function_approximation {
x_y_pairs {
x_y_pair {
x: 0.0
y: %f
}
x_y_pair {
x: 1.0
y: %f
}}}}""" % (calibration_mapping_value, calibration_mapping_value)
post_processing_text_proto = (post_processing_text_proto + ' ' +
calibration_text_proto)
text_format.Merge(post_processing_text_proto, post_processing_config)
second_stage_non_max_suppression_fn, second_stage_score_conversion_fn = (
post_processing_builder.build(post_processing_config))
second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=use_matmul_gather_in_matcher)
second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=1.0, is_static=use_static_shapes)
second_stage_localization_loss_weight = 1.0
second_stage_classification_loss_weight = 1.0
if softmax_second_stage_classification_loss:
second_stage_classification_loss = (
losses.WeightedSoftmaxClassificationLoss())
else:
second_stage_classification_loss = (
losses.WeightedSigmoidClassificationLoss())
hard_example_miner = None
if hard_mining:
hard_example_miner = losses.HardExampleMiner(
num_hard_examples=1,
iou_threshold=0.99,
loss_type='both',
cls_loss_weight=second_stage_classification_loss_weight,
loc_loss_weight=second_stage_localization_loss_weight,
max_negatives_per_positive=None)
crop_and_resize_fn = (ops.matmul_crop_and_resize
if use_matmul_crop_and_resize else
ops.native_crop_and_resize)
common_kwargs = {
'is_training':
is_training,
'num_classes':
num_classes,
'image_resizer_fn':
image_resizer_fn,
'feature_extractor':
fake_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_localization_loss_weight,
'first_stage_objectness_loss_weight':
first_stage_objectness_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_weight':
second_stage_classification_loss_weight,
'second_stage_classification_loss':
second_stage_classification_loss,
'hard_example_miner':
hard_example_miner,
'crop_and_resize_fn':
crop_and_resize_fn,
'clip_anchors_to_image':
clip_anchors_to_image,
'use_static_shapes':
use_static_shapes,
'resize_masks':
True,
'return_raw_detections_during_predict':
return_raw_detections_during_predict
}
return self._get_model(
self._get_second_stage_box_predictor(
num_classes=num_classes,
is_training=is_training,
use_keras=use_keras,
predict_masks=predict_masks,
masks_are_class_agnostic=masks_are_class_agnostic,
share_box_across_classes=share_box_across_classes),
**common_kwargs)
def __init__(self, desc):
"""Init faster rcnn.
:param desc: config dict
"""
super(FasterRCNN, self).__init__()
self.num_classes = int(desc.num_classes)
self.number_of_stages = int(desc.number_of_stages)
# Backbone for feature extractor
self.feature_extractor = NetworkDesc(desc.backbone).to_model()
# First stage anchor generator
self.first_stage_anchor_generator = NetworkDesc(
desc["first_stage_anchor_generator"]).to_model()
# First stage target assigner
self.use_matmul_gather_in_matcher = False # Default
self.first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=self.use_matmul_gather_in_matcher)
# First stage box predictor
self.first_stage_box_predictor_arg_scope_fn = scope_generator.get_hyper_params_scope(
desc.first_stage_box_predictor_conv_hyperparams)
self.first_stage_atrous_rate = 1 # Default: 1
self.first_stage_box_predictor_kernel_size = 3 # Default
self.first_stage_box_predictor_depth = 512 # Default
self.first_stage_minibatch_size = 256 # Default
# First stage sampler
self.first_stage_positive_balance_fraction = 0.5 # Default
self.use_static_balanced_label_sampler = False # Default
self.use_static_shapes = False # Default
self.first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=self.first_stage_positive_balance_fraction,
is_static=(self.use_static_balanced_label_sampler
and self.use_static_shapes))
# First stage NMS
self.first_stage_nms_score_threshold = 0.0
self.first_stage_nms_iou_threshold = 0.7
self.first_stage_max_proposals = 300
self.use_partitioned_nms_in_first_stage = True # Default
self.use_combined_nms_in_first_stage = False # Default
self.first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=self.first_stage_nms_score_threshold,
iou_thresh=self.first_stage_nms_iou_threshold,
max_size_per_class=self.first_stage_max_proposals,
max_total_size=self.first_stage_max_proposals,
use_static_shapes=self.use_static_shapes,
use_partitioned_nms=self.use_partitioned_nms_in_first_stage,
use_combined_nms=self.use_combined_nms_in_first_stage)
# First stage localization loss weight
self.first_stage_localization_loss_weight = 2.0
# First stage objectness loss weight
self.first_stage_objectness_loss_weight = 1.0
# Second stage target assigner
self.second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=self.use_matmul_gather_in_matcher)
# Second stage sampler
self.second_stage_batch_size = 64 # Default
self.second_stage_balance_fraction = 0.25 # Default
self.second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=self.second_stage_balance_fraction,
is_static=(self.use_static_balanced_label_sampler
and self.use_static_shapes))
# Second stage box predictor
self.second_stage_box_predictor = NetworkDesc(
desc.mask_rcnn_box).to_model()
# Second stage NMS function
self.second_stage_non_max_suppression_fn, self.second_stage_score_conversion_fn = \
post_processing_util.get_post_processing_fn(desc.second_stage_post_processing)
# Second stage mask prediction loss weight
self.second_stage_mask_prediction_loss_weight = 1.0 # default
# Second stage localization loss weight
self.second_stage_localization_loss_weight = 2.0
# Second stage classification loss weight
self.second_stage_classification_loss_weight = 1.0
# Second stage classification loss
self.logit_scale = 1.0 # Default
self.second_stage_classification_loss = losses.WeightedSoftmaxClassificationLoss(
logit_scale=self.logit_scale)
self.hard_example_miner = None
self.add_summaries = True
# Crop and resize function
self.use_matmul_crop_and_resize = False # Default
self.crop_and_resize_fn = (
spatial_ops.multilevel_matmul_crop_and_resize
if self.use_matmul_crop_and_resize else
spatial_ops.native_crop_and_resize)
self.clip_anchors_to_image = False # Default
self.resize_masks = True # Default
self.return_raw_detections_during_predict = False # Default
self.output_final_box_features = False # Default
# Image resizer function
self.image_resizer_fn = image_resizer_util.get_image_resizer(
desc.image_resizer)
self.initial_crop_size = 14
self.maxpool_kernel_size = 2
self.maxpool_stride = 2
# Real model to be called
self.model = None
