def __init__(self, images, group=None, bounding_box_group_glob=None,
reference_shape=None, sd_algorithm_cls=Newton,
holistic_features=no_op, patch_features=no_op,
patch_shape=(17, 17), diagonal=None, scales=(0.5, 1.0),
n_iterations=6, n_perturbations=30,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
batch_size=None, verbose=False):
# check parameters
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
patch_features = checks.check_features(patch_features, n_scales)
holistic_features = checks.check_features(holistic_features, n_scales)
patch_shape = checks.check_patch_shape(patch_shape, n_scales)
# set parameters
self.algorithms = []
self.reference_shape = reference_shape
self._sd_algorithm_cls = sd_algorithm_cls
self.holistic_features = holistic_features
self.patch_features = patch_features
self.patch_shape = patch_shape
self.diagonal = diagonal
self.scales = scales
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
# set up algorithms
self._setup_algorithms()
# Now, train the model!
self._train(images,increment=False, group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose, batch_size=batch_size)
def __init__(self, images, group=None, verbose=False, reference_shape=None,
holistic_features=no_op,
transform=DifferentiablePiecewiseAffine, diagonal=None,
scales=(0.5, 1.0), shape_model_cls=OrthoPDM,
max_shape_components=None, max_appearance_components=None,
batch_size=None):
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
shape_model_cls = checks.check_callable(shape_model_cls, n_scales)
max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
max_appearance_components = checks.check_max_components(
max_appearance_components, n_scales, 'max_appearance_components')
self.holistic_features = holistic_features
self.transform = transform
self.diagonal = diagonal
self.scales = scales
self.max_shape_components = max_shape_components
self.max_appearance_components = max_appearance_components
self.reference_shape = reference_shape
self._shape_model_cls = shape_model_cls
self.shape_models = []
self.appearance_models = []
# Train AAM
self._train(images, increment=False, group=group, verbose=verbose,
batch_size=batch_size)
def __init__(self, images, group=None, holistic_features=no_op,
reference_shape=None, diagonal=None, scales=(0.5, 1),
patch_shape=(17, 17), patch_normalisation=no_op,
context_shape=(34, 34), cosine_mask=True, sample_offsets=None,
shape_model_cls=OrthoPDM,
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
max_shape_components=None, verbose=False, batch_size=None):
self.scales = checks.check_scales(scales)
n_scales = len(scales)
self.diagonal = checks.check_diagonal(diagonal)
self.holistic_features = checks.check_callable(holistic_features,
n_scales)
self.expert_ensemble_cls = checks.check_callable(expert_ensemble_cls,
n_scales)
self._shape_model_cls = checks.check_callable(shape_model_cls,
n_scales)
self.max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
self.reference_shape = reference_shape
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
self.patch_normalisation = patch_normalisation
self.context_shape = checks.check_patch_shape(context_shape, n_scales)
self.cosine_mask = cosine_mask
self.sample_offsets = sample_offsets
self.shape_models = []
self.expert_ensembles = []
# Train CLM
self._train(images, increment=False, group=group, verbose=verbose,
batch_size=batch_size)
def __init__(
self,
template,
group=None,
holistic_features=no_op,
transform_cls=DifferentiableAlignmentAffine,
diagonal=None,
scales=(0.5, 1.0),
algorithm_cls=InverseCompositional,
residual_cls=SSD,
):
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
holistic_features = checks.check_callable(holistic_features, len(scales))
self.holistic_features = holistic_features
self.transform_cls = transform_cls
self.diagonal = diagonal
self.scales = list(scales)
# Make template masked for warping
template = template.as_masked(copy=False)
if self.diagonal:
template = template.rescale_landmarks_to_diagonal_range(self.diagonal, group=group)
self.reference_shape = template.landmarks[group].lms
self.templates, self.sources = self._prepare_template(template, group=group)
self._set_up(algorithm_cls, residual_cls)
def __init__(self, template, shapes, group=None, verbose=False,
reference_shape=None, holistic_features=no_op,
transform=DifferentiablePiecewiseAffine, diagonal=None,
scales=(0.5, 1.0), max_shape_components=None,
batch_size=None):
checks.check_diagonal(diagonal)
n_scales = len(scales)
scales = checks.check_scales(scales)
holistic_features = checks.check_features(holistic_features, n_scales)
max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
self.holistic_features = holistic_features
self.transform = transform
self.diagonal = diagonal
self.scales = scales
self.max_shape_components = max_shape_components
self.reference_shape = reference_shape
self.shape_models = []
self.warped_templates = []
# Train ATM
self._train(template, shapes, increment=False, group=group,
verbose=verbose, batch_size=batch_size)
def __init__(self, images, group=None, verbose=False, batch_size=None,
diagonal=None, scales=(0.5, 1), holistic_features=no_op,
# shape_model_cls=build_normalised_pca_shape_model,
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
max_shape_components=None, reference_shape=None,
shape_forgetting_factor=1.0):
self.diagonal = checks.check_diagonal(diagonal)
self.scales = checks.check_scales(scales)
self.holistic_features = checks.check_features(holistic_features,
self.n_scales)
# self.shape_model_cls = checks.check_algorithm_cls(
# shape_model_cls, self.n_scales, ShapeModel)
self.expert_ensemble_cls = checks.check_algorithm_cls(
expert_ensemble_cls, self.n_scales, ExpertEnsemble)
self.max_shape_components = checks.check_max_components(
max_shape_components, self.n_scales, 'max_shape_components')
self.shape_forgetting_factor = shape_forgetting_factor
self.reference_shape = reference_shape
self.shape_models = []
self.expert_ensembles = []
# Train CLM
self._train(images, increment=False, group=group, verbose=verbose,
batch_size=batch_size)
def __init__(self, template, shapes, group=None, holistic_features=no_op,
reference_shape=None, diagonal=None, scales=(0.5, 1.0),
transform=DifferentiablePiecewiseAffine,
shape_model_cls=OrthoPDM, max_shape_components=None,
verbose=False, batch_size=None):
# Check arguments
checks.check_diagonal(diagonal)
n_scales = len(scales)
scales = checks.check_scales(scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
shape_model_cls = checks.check_callable(shape_model_cls, n_scales)
# Assign attributes
self.holistic_features = holistic_features
self.transform = transform
self.diagonal = diagonal
self.scales = scales
self.max_shape_components = max_shape_components
self.reference_shape = reference_shape
self.shape_models = []
self.warped_templates = []
self._shape_model_cls = shape_model_cls
# Train ATM
self._train(template, shapes, increment=False, group=group,
verbose=verbose, batch_size=batch_size)
def __init__(self, images, group=None, bounding_box_group_glob=None,
verbose=False, reference_shape=None, diagonal=None,
scales=(0.5, 1.0), n_perturbations=30, n_dlib_perturbations=1,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
n_iterations=10, feature_padding=0, n_pixel_pairs=400,
distance_prior_weighting=0.1, regularisation_weight=0.1,
n_split_tests=20, n_trees=500, n_tree_levels=5):
checks.check_diagonal(diagonal)
self.diagonal = diagonal
self.scales = checks.check_scales(scales)
self.holistic_features = checks.check_features(no_op, self.n_scales)
self.reference_shape = reference_shape
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, self.n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
self._setup_dlib_options(feature_padding, n_pixel_pairs,
distance_prior_weighting,
regularisation_weight, n_split_tests, n_trees,
n_dlib_perturbations, n_tree_levels)
self._setup_algorithms()
# Train DLIB over multiple scales
self._train(images, group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose)
def __init__(self,
template,
group=None,
holistic_features=no_op,
transform_cls=DifferentiableAlignmentAffine,
diagonal=None,
scales=(0.5, 1.0),
algorithm_cls=InverseCompositional,
residual_cls=SSD):
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
holistic_features = checks.check_callable(holistic_features,
len(scales))
self.holistic_features = holistic_features
self.transform_cls = transform_cls
self.diagonal = diagonal
self.scales = list(scales)
# Make template masked for warping
template = template.as_masked(copy=False)
if self.diagonal:
template = template.rescale_landmarks_to_diagonal_range(
self.diagonal, group=group)
self.reference_shape = template.landmarks[group].lms
self.templates, self.sources = self._prepare_template(template,
group=group)
self._set_up(algorithm_cls, residual_cls)
def __init__(self, images, group=None, verbose=False, batch_size=None,
diagonal=None, scales=(0.5, 1), holistic_features=no_op,
shape_model_cls=OrthoPDM,
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
max_shape_components=None, reference_shape=None):
scales = checks.check_scales(scales)
n_scales = len(scales)
self.diagonal = checks.check_diagonal(diagonal)
self.scales = scales
self.holistic_features = checks.check_callable(holistic_features,
self.n_scales)
self.expert_ensemble_cls = checks.check_algorithm_cls(
expert_ensemble_cls, self.n_scales, ExpertEnsemble)
shape_model_cls = checks.check_callable(shape_model_cls, n_scales)
self.max_shape_components = checks.check_max_components(
max_shape_components, self.n_scales, 'max_shape_components')
self.reference_shape = reference_shape
self.shape_models = []
self._shape_model_cls = shape_model_cls
self.expert_ensembles = []
# Train CLM
self._train(images, increment=False, group=group, verbose=verbose,
batch_size=batch_size)
def __init__(self,
images,
group=None,
verbose=False,
batch_size=None,
diagonal=None,
scales=(0.5, 1),
holistic_features=no_op,
shape_model_cls=OrthoPDM,
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
max_shape_components=None,
reference_shape=None):
scales = checks.check_scales(scales)
n_scales = len(scales)
self.diagonal = checks.check_diagonal(diagonal)
self.scales = scales
self.holistic_features = checks.check_callable(holistic_features,
self.n_scales)
self.expert_ensemble_cls = checks.check_algorithm_cls(
expert_ensemble_cls, self.n_scales, ExpertEnsemble)
shape_model_cls = checks.check_callable(shape_model_cls, n_scales)
self.max_shape_components = checks.check_max_components(
max_shape_components, self.n_scales, 'max_shape_components')
self.reference_shape = reference_shape
self.shape_models = []
self._shape_model_cls = shape_model_cls
self.expert_ensembles = []
# Train CLM
self._train(images,
increment=False,
group=group,
verbose=verbose,
batch_size=batch_size)
def __init__(self,
images,
group=None,
holistic_features=no_op,
reference_shape=None,
diagonal=None,
scales=(0.5, 1.0),
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
patch_shape=(17, 17),
context_shape=(34, 34),
sample_offsets=None,
transform=DifferentiablePiecewiseAffine,
shape_model_cls=OrthoPDM,
max_shape_components=None,
max_appearance_components=None,
sigma=None,
boundary=3,
response_covariance=2,
patch_normalisation=no_op,
cosine_mask=True,
verbose=False):
# Check parameters
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
shape_model_cls = checks.check_callable(shape_model_cls, n_scales)
max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
max_appearance_components = checks.check_max_components(
max_appearance_components, n_scales, 'max_appearance_components')
# Assign attributes
self.expert_ensemble_cls = checks.check_callable(
expert_ensemble_cls, n_scales)
self.expert_ensembles = []
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
self.context_shape = checks.check_patch_shape(context_shape, n_scales)
self.holistic_features = holistic_features
self.transform = transform
self.diagonal = diagonal
self.scales = scales
self.max_shape_components = max_shape_components
self.max_appearance_components = max_appearance_components
self.reference_shape = reference_shape
self.shape_model_cls = shape_model_cls
self.sigma = sigma
self.boundary = boundary
self.sample_offsets = sample_offsets
self.response_covariance = response_covariance
self.patch_normalisation = patch_normalisation
self.cosine_mask = cosine_mask
self.shape_models = []
self.appearance_models = []
self.expert_ensembles = []
self._train(images=images, group=group, verbose=verbose)
def __init__(self,
images,
group=None,
bounding_box_group_glob=None,
reference_shape=None,
diagonal=None,
scales=(0.5, 1.0),
n_perturbations=30,
n_dlib_perturbations=1,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
n_iterations=10,
feature_padding=0,
n_pixel_pairs=400,
distance_prior_weighting=0.1,
regularisation_weight=0.1,
n_split_tests=20,
n_trees=500,
n_tree_levels=5,
verbose=False):
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
# Dummy option that is required by _prepare_image of MultiFitter.
holistic_features = checks.check_callable(no_op, n_scales)
# Call superclass
super(DlibERT, self).__init__(scales=scales,
reference_shape=reference_shape,
holistic_features=holistic_features,
algorithms=[])
# Set parameters
self.diagonal = diagonal
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
# DLib options
self._setup_dlib_options(feature_padding, n_pixel_pairs,
distance_prior_weighting,
regularisation_weight, n_split_tests, n_trees,
n_dlib_perturbations, n_tree_levels)
# Set-up algorithms
for j in range(self.n_scales):
self.algorithms.append(
DlibAlgorithm(self._dlib_options_templates[j],
n_iterations=self.n_iterations[j]))
# Train DLIB over multiple scales
self._train(images,
group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose)
def __init__(
self,
images,
group=None,
bounding_box_group_glob=None,
reference_shape=None,
sd_algorithm_cls=None,
holistic_features=no_op,
patch_features=no_op,
patch_shape=(17, 17),
diagonal=None,
scales=(0.5, 1.0),
n_iterations=3,
n_perturbations=30,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
batch_size=None,
verbose=False,
):
if batch_size is not None:
raise NotImplementedError("Training an SDM with a batch size " "(incrementally) is not implemented yet.")
# check parameters
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
patch_features = checks.check_callable(patch_features, n_scales)
sd_algorithm_cls = checks.check_callable(sd_algorithm_cls, n_scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
patch_shape = checks.check_patch_shape(patch_shape, n_scales)
# set parameters
self.algorithms = []
self.reference_shape = reference_shape
self._sd_algorithm_cls = sd_algorithm_cls
self.holistic_features = holistic_features
self.patch_features = patch_features
self.patch_shape = patch_shape
self.diagonal = diagonal
self.scales = scales
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
# set up algorithms
self._setup_algorithms()
# Now, train the model!
self._train(
images,
increment=False,
group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose,
batch_size=batch_size,
)
def __init__(self, images, group=None, appearance_graph=None,
shape_graph=None, deformation_graph=None,
holistic_features=no_op, reference_shape=None, diagonal=None,
scales=(0.5, 1.0), patch_shape=(17, 17),
patch_normalisation=no_op, use_procrustes=True,
precision_dtype=np.float32, max_shape_components=None,
n_appearance_components=None, can_be_incremented=False,
verbose=False, batch_size=None):
# Check parameters
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
patch_shape = checks.check_patch_shape(patch_shape, n_scales)
patch_normalisation = checks.check_callable(patch_normalisation,
n_scales)
max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
n_appearance_components = checks.check_max_components(
n_appearance_components, n_scales, 'n_appearance_components')
# Assign attributes
self.diagonal = diagonal
self.scales = scales
self.holistic_features = holistic_features
self.patch_shape = patch_shape
self.patch_normalisation = patch_normalisation
self.reference_shape = reference_shape
self.use_procrustes = use_procrustes
self.is_incremental = can_be_incremented
self.precision_dtype = precision_dtype
self.max_shape_components = max_shape_components
self.n_appearance_components = n_appearance_components
# Check provided graphs
self.appearance_graph = checks.check_graph(
appearance_graph, UndirectedGraph, 'appearance_graph', n_scales)
self.shape_graph = checks.check_graph(shape_graph, UndirectedGraph,
'shape_graph', n_scales)
self.deformation_graph = checks.check_graph(
deformation_graph, [DirectedGraph, Tree], 'deformation_graph',
n_scales)
# Initialize models' lists
self.shape_models = []
self.appearance_models = []
self.deformation_models = []
# Train APS
self._train(images, increment=False, group=group, batch_size=batch_size,
verbose=verbose)
def __init__(self,
images,
group=None,
bounding_box_group_glob=None,
reference_shape=None,
sd_algorithm_cls=None,
holistic_features=no_op,
patch_features=no_op,
patch_shape=(17, 17),
diagonal=None,
scales=(0.5, 1.0),
n_iterations=3,
n_perturbations=30,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
batch_size=None,
verbose=False):
if batch_size is not None:
raise NotImplementedError(
'Training an SDM with a batch size '
'(incrementally) is not implemented yet.')
# check parameters
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
patch_features = checks.check_callable(patch_features, n_scales)
sd_algorithm_cls = checks.check_callable(sd_algorithm_cls, n_scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
patch_shape = checks.check_patch_shape(patch_shape, n_scales)
# set parameters
self.algorithms = []
self.reference_shape = reference_shape
self._sd_algorithm_cls = sd_algorithm_cls
self.holistic_features = holistic_features
self.patch_features = patch_features
self.patch_shape = patch_shape
self.diagonal = diagonal
self.scales = scales
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
# set up algorithms
self._setup_algorithms()
# Now, train the model!
self._train(images,
increment=False,
group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose,
batch_size=batch_size)
def __init__(self, images, group=None, verbose=False, reference_shape=None,
holistic_features=no_op, diagonal=None, scales=(0.5, 1.0),
patch_shape=(17, 17), max_shape_components=None,
max_appearance_components=None, batch_size=None):
n_scales = len(checks.check_scales(scales))
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
super(LinearMaskedAAM, self).__init__(
images, group=group, verbose=verbose,
reference_shape=reference_shape,
holistic_features=holistic_features,
transform=DifferentiableThinPlateSplines, diagonal=diagonal,
scales=scales, max_shape_components=max_shape_components,
max_appearance_components=max_appearance_components,
batch_size=batch_size)
def __init__(self, images, group=None, verbose=False, reference_shape=None,
holistic_features=no_op, diagonal=None, scales=(0.5, 1.0),
patch_shape=(17, 17), max_shape_components=None,
max_appearance_components=None,
shape_model_cls=OrthoPDM, batch_size=None):
n_scales = len(checks.check_scales(scales))
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
super(LinearMaskedAAM, self).__init__(
images, group=group, verbose=verbose,
reference_shape=reference_shape,
holistic_features=holistic_features,
transform=DifferentiableThinPlateSplines, diagonal=diagonal,
scales=scales, max_shape_components=max_shape_components,
max_appearance_components=max_appearance_components,
shape_model_cls=shape_model_cls, batch_size=batch_size)
def __init__(self, images, group=None, verbose=False, reference_shape=None,
holistic_features=no_op, patch_normalisation=no_op,
diagonal=None, scales=(0.5, 1.0), patch_shape=(17, 17),
max_shape_components=None, max_appearance_components=None,
batch_size=None):
n_scales = len(checks.check_scales(scales))
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
self.patch_normalisation = patch_normalisation
super(PatchAAM, self).__init__(
images, group=group, verbose=verbose,
reference_shape=reference_shape,
holistic_features=holistic_features, transform=None,
diagonal=diagonal, scales=scales,
max_shape_components=max_shape_components,
max_appearance_components=max_appearance_components,
batch_size=batch_size)
def __init__(
self,
images,
group=None,
holistic_features=no_op,
reference_shape=None,
diagonal=None,
scales=(1, ), # scales=(0.5, 1)
patch_shape=(8, 8),
patch_normalisation=no_op,
context_shape=(8, 8),
cosine_mask=True,
sample_offsets=None,
shape_model_cls=OrthoPDM,
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
max_shape_components=None,
verbose=False,
batch_size=None):
self.scales = checks.check_scales(scales)
n_scales = len(scales)
self.diagonal = checks.check_diagonal(diagonal)
self.holistic_features = checks.check_callable(holistic_features,
n_scales)
self.expert_ensemble_cls = checks.check_callable(
expert_ensemble_cls, n_scales)
self._shape_model_cls = checks.check_callable(shape_model_cls,
n_scales)
self.max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
self.reference_shape = reference_shape
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
self.patch_normalisation = patch_normalisation
self.context_shape = checks.check_patch_shape(context_shape, n_scales)
self.cosine_mask = cosine_mask
self.sample_offsets = sample_offsets
self.shape_models = []
self.expert_ensembles = []
# Train CLM
self._train(images,
increment=False,
group=group,
verbose=verbose,
batch_size=batch_size)
def __init__(self, images, group=None, holistic_features=no_op,
reference_shape=None, diagonal=None, scales=(0.5, 1.0),
expert_ensemble_cls=CorrelationFilterExpertEnsemble,
patch_shape=(17, 17), context_shape=(34, 34),
sample_offsets=None, transform=DifferentiablePiecewiseAffine,
shape_model_cls=OrthoPDM, max_shape_components=None,
max_appearance_components=None, sigma=None, boundary=3,
response_covariance=2, patch_normalisation=no_op,
cosine_mask=True, verbose=False):
# Check parameters
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
holistic_features = checks.check_callable(holistic_features, n_scales)
shape_model_cls = checks.check_callable(shape_model_cls, n_scales)
max_shape_components = checks.check_max_components(
max_shape_components, n_scales, 'max_shape_components')
max_appearance_components = checks.check_max_components(
max_appearance_components, n_scales, 'max_appearance_components')
# Assign attributes
self.expert_ensemble_cls = checks.check_callable(expert_ensemble_cls,
n_scales)
self.expert_ensembles = []
self.patch_shape = checks.check_patch_shape(patch_shape, n_scales)
self.context_shape = checks.check_patch_shape(context_shape, n_scales)
self.holistic_features = holistic_features
self.transform = transform
self.diagonal = diagonal
self.scales = scales
self.max_shape_components = max_shape_components
self.max_appearance_components = max_appearance_components
self.reference_shape = reference_shape
self.shape_model_cls = shape_model_cls
self.sigma = sigma
self.boundary = boundary
self.sample_offsets = sample_offsets
self.response_covariance = response_covariance
self.patch_normalisation = patch_normalisation
self.cosine_mask = cosine_mask
self.shape_models = []
self.appearance_models = []
self.expert_ensembles = []
self._train(images=images, group=group, verbose=verbose)
def __init__(self,
template,
group=None,
holistic_features=no_op,
diagonal=None,
transform=DifferentiableAlignmentAffine,
scales=(0.5, 1.0),
algorithm_cls=InverseCompositional,
residual_cls=SSD):
# Check arguments
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
holistic_features = checks.check_callable(holistic_features,
len(scales))
# Assign attributes
self.transform_cls = transform
self.diagonal = diagonal
# Make template masked for warping
template = template.as_masked(copy=False)
# Get reference shape
if self.diagonal:
template = template.rescale_landmarks_to_diagonal_range(
self.diagonal, group=group)
reference_shape = template.landmarks[group]
# Call superclass
super(LucasKanadeFitter,
self).__init__(scales=list(scales),
reference_shape=reference_shape,
holistic_features=holistic_features,
algorithms=[])
# Create templates
self.templates, self.sources = self._prepare_template(template,
group=group)
# Get list of algorithm objects per scale
self.algorithms = []
for j, (t, s) in enumerate(zip(self.templates, self.sources)):
transform = self.transform_cls(s, s)
residual = residual_cls()
self.algorithms.append(algorithm_cls(t, transform, residual))
def __init__(self,
images,
group=None,
bounding_box_group_glob=None,
verbose=False,
reference_shape=None,
diagonal=None,
scales=(0.5, 1.0),
n_perturbations=30,
n_dlib_perturbations=1,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
n_iterations=10,
feature_padding=0,
n_pixel_pairs=400,
distance_prior_weighting=0.1,
regularisation_weight=0.1,
n_split_tests=20,
n_trees=500,
n_tree_levels=5):
checks.check_diagonal(diagonal)
self.diagonal = diagonal
self.scales = checks.check_scales(scales)
self.holistic_features = checks.check_callable(no_op, self.n_scales)
self.reference_shape = reference_shape
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, self.n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
self._setup_dlib_options(feature_padding, n_pixel_pairs,
distance_prior_weighting,
regularisation_weight, n_split_tests, n_trees,
n_dlib_perturbations, n_tree_levels)
self._setup_algorithms()
# Train DLIB over multiple scales
self._train(images,
group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose)
def __init__(self, images, group=None, bounding_box_group_glob=None,
reference_shape=None, diagonal=None, scales=(0.5, 1.0),
n_perturbations=30, n_dlib_perturbations=1,
perturb_from_gt_bounding_box=noisy_shape_from_bounding_box,
n_iterations=10, feature_padding=0, n_pixel_pairs=400,
distance_prior_weighting=0.1, regularisation_weight=0.1,
n_split_tests=20, n_trees=500, n_tree_levels=5, verbose=False):
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
n_scales = len(scales)
# Dummy option that is required by _prepare_image of MultiFitter.
holistic_features = checks.check_callable(no_op, n_scales)
# Call superclass
super(DlibERT, self).__init__(
scales=scales, reference_shape=reference_shape,
holistic_features=holistic_features, algorithms=[])
# Set parameters
self.diagonal = diagonal
self.n_perturbations = n_perturbations
self.n_iterations = checks.check_max_iters(n_iterations, n_scales)
self._perturb_from_gt_bounding_box = perturb_from_gt_bounding_box
# DLib options
self._setup_dlib_options(feature_padding, n_pixel_pairs,
distance_prior_weighting,
regularisation_weight, n_split_tests, n_trees,
n_dlib_perturbations, n_tree_levels)
# Set-up algorithms
for j in range(self.n_scales):
self.algorithms.append(DlibAlgorithm(
self._dlib_options_templates[j],
n_iterations=self.n_iterations[j]))
# Train DLIB over multiple scales
self._train(images, group=group,
bounding_box_group_glob=bounding_box_group_glob,
verbose=verbose)
def __init__(self, template, group=None, holistic_features=no_op,
diagonal=None, transform=DifferentiableAlignmentAffine,
scales=(0.5, 1.0), algorithm_cls=InverseCompositional,
residual_cls=SSD):
# Check arguments
checks.check_diagonal(diagonal)
scales = checks.check_scales(scales)
holistic_features = checks.check_callable(holistic_features,
len(scales))
# Assign attributes
self.transform_cls = transform
self.diagonal = diagonal
# Make template masked for warping
template = template.as_masked(copy=False)
# Get reference shape
if self.diagonal:
template = template.rescale_landmarks_to_diagonal_range(
self.diagonal, group=group)
reference_shape = template.landmarks[group]
# Call superclass
super(LucasKanadeFitter, self).__init__(
scales=list(scales), reference_shape=reference_shape,
holistic_features=holistic_features, algorithms=[])
# Create templates
self.templates, self.sources = self._prepare_template(template,
group=group)
# Get list of algorithm objects per scale
self.algorithms = []
for j, (t, s) in enumerate(zip(self.templates, self.sources)):
transform = self.transform_cls(s, s)
residual = residual_cls()
self.algorithms.append(algorithm_cls(t, transform, residual))