def _build_shape_model(self, shapes, scale_index):
mean_aligned_shape = mean_pointcloud(align_shapes(shapes))
self.n_landmarks = mean_aligned_shape.n_points
self.reference_frame = build_reference_frame(mean_aligned_shape)
dense_shapes = densify_shapes(shapes, self.reference_frame,
self.transform)
# build dense shape model
shape_model = build_shape_model(dense_shapes)
return shape_model
def build(self, images, group=None, label=None, verbose=False):
r"""
Builds a Multilevel Constrained Local Model from a list of
landmarked images.
Parameters
----------
images : list of :map:`Image`
The set of landmarked images from which to build the AAM.
group : string, Optional
The key of the landmark set that should be used. If ``None``,
and if there is only one set of landmarks, this set will be used.
label : `string`, optional
The label of of the landmark manager that you wish to use. If
``None``, the convex hull of all landmarks is used.
verbose : `boolean`, optional
Flag that controls information and progress printing.
Returns
-------
clm : :map:`CLM`
The CLM object
"""
# compute reference_shape and normalize images size
self.reference_shape, normalized_images = \
normalization_wrt_reference_shape(
images, group, label, self.normalization_diagonal,
verbose=verbose)
# create pyramid
generators = create_pyramid(normalized_images, self.n_levels,
self.downscale, self.features,
verbose=verbose)
# build the model at each pyramid level
if verbose:
if self.n_levels > 1:
print_dynamic('- Building model for each of the {} pyramid '
'levels\n'.format(self.n_levels))
else:
print_dynamic('- Building model\n')
shape_models = []
classifiers = []
# for each pyramid level (high --> low)
for j in range(self.n_levels):
# since models are built from highest to lowest level, the
# parameters of type list need to use a reversed index
rj = self.n_levels - j - 1
if verbose:
level_str = ' - '
if self.n_levels > 1:
level_str = ' - Level {}: '.format(j + 1)
# get images of current level
feature_images = []
for c, g in enumerate(generators):
if verbose:
print_dynamic(
'{}Computing feature space/rescaling - {}'.format(
level_str,
progress_bar_str((c + 1.) / len(generators),
show_bar=False)))
feature_images.append(next(g))
# extract potentially rescaled shapes
shapes = [i.landmarks[group][label] for i in feature_images]
# define shapes that will be used for training
if j == 0:
original_shapes = shapes
train_shapes = shapes
else:
if self.scaled_shape_models:
train_shapes = shapes
else:
train_shapes = original_shapes
# train shape model and find reference frame
if verbose:
print_dynamic('{}Building shape model'.format(level_str))
shape_model = build_shape_model(
train_shapes, self.max_shape_components[rj])
# add shape model to the list
shape_models.append(shape_model)
# build classifiers
sampling_grid = build_sampling_grid(self.patch_shape)
n_points = shapes[0].n_points
level_classifiers = []
for k in range(n_points):
if verbose:
print_dynamic('{}Building classifiers - {}'.format(
level_str,
progress_bar_str((k + 1.) / n_points,
show_bar=False)))
positive_labels = []
negative_labels = []
positive_samples = []
negative_samples = []
for i, s in zip(feature_images, shapes):
max_x = i.shape[0] - 1
max_y = i.shape[1] - 1
point = (np.round(s.points[k, :])).astype(int)
patch_grid = sampling_grid + point[None, None, ...]
positive, negative = get_pos_neg_grid_positions(
patch_grid, positive_grid_size=(1, 1))
x = positive[:, 0]
y = positive[:, 1]
x[x > max_x] = max_x
y[y > max_y] = max_y
x[x < 0] = 0
y[y < 0] = 0
positive_sample = i.pixels[positive[:, 0],
positive[:, 1], :]
positive_samples.append(positive_sample)
positive_labels.append(np.ones(positive_sample.shape[0]))
x = negative[:, 0]
y = negative[:, 1]
x[x > max_x] = max_x
y[y > max_y] = max_y
x[x < 0] = 0
y[y < 0] = 0
negative_sample = i.pixels[x, y, :]
negative_samples.append(negative_sample)
negative_labels.append(-np.ones(negative_sample.shape[0]))
positive_samples = np.asanyarray(positive_samples)
positive_samples = np.reshape(positive_samples,
(-1, positive_samples.shape[-1]))
positive_labels = np.asanyarray(positive_labels).flatten()
negative_samples = np.asanyarray(negative_samples)
negative_samples = np.reshape(negative_samples,
(-1, negative_samples.shape[-1]))
negative_labels = np.asanyarray(negative_labels).flatten()
X = np.vstack((positive_samples, negative_samples))
t = np.hstack((positive_labels, negative_labels))
clf = self.classifier_trainers[rj](X, t)
level_classifiers.append(clf)
# add level classifiers to the list
classifiers.append(level_classifiers)
if verbose:
print_dynamic('{}Done\n'.format(level_str))
# reverse the list of shape and appearance models so that they are
# ordered from lower to higher resolution
shape_models.reverse()
classifiers.reverse()
n_training_images = len(images)
from .base import CLM
return CLM(shape_models, classifiers, n_training_images,
self.patch_shape, self.features, self.reference_shape,
self.downscale, self.scaled_shape_models)
def _build_shape_model(self, shapes, scale_index):
return build_shape_model(shapes)
def build(self, shapes, template, group=None, label=None, verbose=False):
r"""
Builds a Multilevel Active Template Model given a list of shapes and a
template image.
Parameters
----------
shapes : list of :map:`PointCloud`
The set of shapes from which to build the shape model of the ATM.
template : :map:`Image` or subclass
The image to be used as template.
group : `string`, optional
The key of the landmark set of the template that should be used. If
``None``, and if there is only one set of landmarks, this set will
be used.
label : `string`, optional
The label of the landmark manager of the template that you wish to
use. If ``None`` is passed, the convex hull of all landmarks is
used.
verbose : `boolean`, optional
Flag that controls information and progress printing.
Returns
-------
atm : :map:`ATM`
The ATM object. Shape and appearance models are stored from lowest
to highest level.
"""
# compute reference_shape
self.reference_shape = compute_reference_shape(
shapes, self.normalization_diagonal, verbose=verbose)
# normalize the template size using the reference_shape scaling
if verbose:
print_dynamic('- Normalizing template size')
normalized_template = template.rescale_to_reference_shape(
self.reference_shape, group=group, label=label)
# create pyramid for template image
if verbose:
print_dynamic('- Creating template pyramid')
generator = create_pyramid([normalized_template], self.n_levels,
self.downscale, self.features)
# build the model at each pyramid level
if verbose:
if self.n_levels > 1:
print_dynamic('- Building model for each of the {} pyramid '
'levels\n'.format(self.n_levels))
else:
print_dynamic('- Building model\n')
shape_models = []
warped_templates = []
# for each pyramid level (high --> low)
for j in range(self.n_levels):
# since models are built from highest to lowest level, the
# parameters in form of list need to use a reversed index
rj = self.n_levels - j - 1
if verbose:
level_str = ' - '
if self.n_levels > 1:
level_str = ' - Level {}: '.format(j + 1)
# rescale shapes if required
if j > 0 and self.scaled_shape_models:
scale_transform = Scale(scale_factor=1.0 / self.downscale,
n_dims=2)
shapes = [scale_transform.apply(s) for s in shapes]
# train shape model and find reference frame
if verbose:
print_dynamic('{}Building shape model'.format(level_str))
shape_model = build_shape_model(shapes,
self.max_shape_components[rj])
reference_frame = self._build_reference_frame(shape_model.mean())
# add shape model to the list
shape_models.append(shape_model)
# get template's feature image of current level
if verbose:
print_dynamic('{}Warping template'.format(level_str))
feature_template = next(generator[0])
# compute transform
transform = self.transform(reference_frame.landmarks['source'].lms,
feature_template.landmarks[group][label])
# warp template to reference frame
warped_templates.append(
feature_template.warp_to_mask(reference_frame.mask, transform))
# attach reference_frame to template's source shape
warped_templates[j].landmarks['source'] = \
reference_frame.landmarks['source']
if verbose:
print_dynamic('{}Done\n'.format(level_str))
# reverse the list of shape and appearance models so that they are
# ordered from lower to higher resolution
shape_models.reverse()
warped_templates.reverse()
n_training_shapes = len(shapes)
return self._build_atm(shape_models, warped_templates,
n_training_shapes)
def build(self, images, group=None, label=None, verbose=False):
r"""
Builds a Multilevel Active Appearance Model from a list of
landmarked images.
Parameters
----------
images : list of :map:`MaskedImage`
The set of landmarked images from which to build the AAM.
group : `string`, optional
The key of the landmark set that should be used. If ``None``,
and if there is only one set of landmarks, this set will be used.
label : `string`, optional
The label of of the landmark manager that you wish to use. If no
label is passed, the convex hull of all landmarks is used.
verbose : `boolean`, optional
Flag that controls information and progress printing.
Returns
-------
aam : :map:`AAM`
The AAM object. Shape and appearance models are stored from lowest
to highest level
"""
# compute reference_shape and normalize images size
self.reference_shape, normalized_images = \
normalization_wrt_reference_shape(images, group, label,
self.normalization_diagonal,
verbose=verbose)
# create pyramid
generators = create_pyramid(normalized_images, self.n_levels,
self.downscale, self.features,
verbose=verbose)
# build the model at each pyramid level
if verbose:
if self.n_levels > 1:
print_dynamic('- Building model for each of the {} pyramid '
'levels\n'.format(self.n_levels))
else:
print_dynamic('- Building model\n')
shape_models = []
appearance_models = []
# for each pyramid level (high --> low)
for j in range(self.n_levels):
# since models are built from highest to lowest level, the
# parameters in form of list need to use a reversed index
rj = self.n_levels - j - 1
if verbose:
level_str = ' - '
if self.n_levels > 1:
level_str = ' - Level {}: '.format(j + 1)
# get feature images of current level
feature_images = []
for c, g in enumerate(generators):
if verbose:
print_dynamic(
'{}Computing feature space/rescaling - {}'.format(
level_str,
progress_bar_str((c + 1.) / len(generators),
show_bar=False)))
feature_images.append(next(g))
# extract potentially rescaled shapes
shapes = [i.landmarks[group][label] for i in feature_images]
# define shapes that will be used for training
if j == 0:
original_shapes = shapes
train_shapes = shapes
else:
if self.scaled_shape_models:
train_shapes = shapes
else:
train_shapes = original_shapes
# train shape model and find reference frame
if verbose:
print_dynamic('{}Building shape model'.format(level_str))
shape_model = build_shape_model(
train_shapes, self.max_shape_components[rj])
reference_frame = self._build_reference_frame(shape_model.mean())
# add shape model to the list
shape_models.append(shape_model)
# compute transforms
if verbose:
print_dynamic('{}Computing transforms'.format(level_str))
# Create a dummy initial transform
s_to_t_transform = self.transform(
reference_frame.landmarks['source'].lms,
reference_frame.landmarks['source'].lms)
# warp images to reference frame
warped_images = []
for c, i in enumerate(feature_images):
if verbose:
print_dynamic('{}Warping images - {}'.format(
level_str,
progress_bar_str(float(c + 1) / len(feature_images),
show_bar=False)))
# Setting the target can be significantly faster for transforms
# such as CachedPiecewiseAffine
s_to_t_transform.set_target(i.landmarks[group][label])
warped_images.append(i.warp_to_mask(reference_frame.mask,
s_to_t_transform))
# attach reference_frame to images' source shape
for i in warped_images:
i.landmarks['source'] = reference_frame.landmarks['source']
# build appearance model
if verbose:
print_dynamic('{}Building appearance model'.format(level_str))
appearance_model = PCAModel(warped_images)
# trim appearance model if required
if self.max_appearance_components[rj] is not None:
appearance_model.trim_components(
self.max_appearance_components[rj])
# add appearance model to the list
appearance_models.append(appearance_model)
if verbose:
print_dynamic('{}Done\n'.format(level_str))
# reverse the list of shape and appearance models so that they are
# ordered from lower to higher resolution
shape_models.reverse()
appearance_models.reverse()
n_training_images = len(images)
return self._build_aam(shape_models, appearance_models,
n_training_images)
def build(self, images, group=None, label=None, verbose=False):
r"""
Builds a Multilevel Active Appearance Model from a list of
landmarked images.
Parameters
----------
images : list of :map:`MaskedImage`
The set of landmarked images from which to build the AAM.
group : `string`, optional
The key of the landmark set that should be used. If ``None``,
and if there is only one set of landmarks, this set will be used.
label : `string`, optional
The label of of the landmark manager that you wish to use. If no
label is passed, the convex hull of all landmarks is used.
verbose : `boolean`, optional
Flag that controls information and progress printing.
Returns
-------
aam : :map:`AAM`
The AAM object. Shape and appearance models are stored from lowest
to highest level
"""
# compute reference_shape and normalize images size
self.reference_shape, normalized_images = \
normalization_wrt_reference_shape(images, group, label,
self.normalization_diagonal,
verbose=verbose)
# create pyramid
generators = create_pyramid(normalized_images,
self.n_levels,
self.downscale,
self.features,
verbose=verbose)
# build the model at each pyramid level
if verbose:
if self.n_levels > 1:
print_dynamic('- Building model for each of the {} pyramid '
'levels\n'.format(self.n_levels))
else:
print_dynamic('- Building model\n')
shape_models = []
appearance_models = []
# for each pyramid level (high --> low)
for j in range(self.n_levels):
# since models are built from highest to lowest level, the
# parameters in form of list need to use a reversed index
rj = self.n_levels - j - 1
if verbose:
level_str = ' - '
if self.n_levels > 1:
level_str = ' - Level {}: '.format(j + 1)
# get feature images of current level
feature_images = []
for c, g in enumerate(generators):
if verbose:
print_dynamic(
'{}Computing feature space/rescaling - {}'.format(
level_str,
progress_bar_str((c + 1.) / len(generators),
show_bar=False)))
feature_images.append(next(g))
# extract potentially rescaled shapes
shapes = [i.landmarks[group][label] for i in feature_images]
# define shapes that will be used for training
if j == 0:
original_shapes = shapes
train_shapes = shapes
else:
if self.scaled_shape_models:
train_shapes = shapes
else:
train_shapes = original_shapes
# train shape model and find reference frame
if verbose:
print_dynamic('{}Building shape model'.format(level_str))
shape_model = build_shape_model(train_shapes,
self.max_shape_components[rj])
reference_frame = self._build_reference_frame(shape_model.mean())
# add shape model to the list
shape_models.append(shape_model)
# compute transforms
if verbose:
print_dynamic('{}Computing transforms'.format(level_str))
transforms = [
self.transform(reference_frame.landmarks['source'].lms,
i.landmarks[group][label])
for i in feature_images
]
# warp images to reference frame
warped_images = []
for c, (i, t) in enumerate(zip(feature_images, transforms)):
if verbose:
print_dynamic('{}Warping images - {}'.format(
level_str,
progress_bar_str(float(c + 1) / len(feature_images),
show_bar=False)))
warped_images.append(i.warp_to_mask(reference_frame.mask, t))
# attach reference_frame to images' source shape
for i in warped_images:
i.landmarks['source'] = reference_frame.landmarks['source']
# build appearance model
if verbose:
print_dynamic('{}Building appearance model'.format(level_str))
appearance_model = PCAModel(warped_images)
# trim appearance model if required
if self.max_appearance_components[rj] is not None:
appearance_model.trim_components(
self.max_appearance_components[rj])
# add appearance model to the list
appearance_models.append(appearance_model)
if verbose:
print_dynamic('{}Done\n'.format(level_str))
# reverse the list of shape and appearance models so that they are
# ordered from lower to higher resolution
shape_models.reverse()
appearance_models.reverse()
n_training_images = len(images)
return self._build_aam(shape_models, appearance_models,
n_training_images)
def build(self, images, group=None, label=None, verbose=False):
r"""
Builds a Multilevel Constrained Local Model from a list of
landmarked images.
Parameters
----------
images : list of :map:`Image`
The set of landmarked images from which to build the AAM.
group : string, Optional
The key of the landmark set that should be used. If ``None``,
and if there is only one set of landmarks, this set will be used.
label : `string`, optional
The label of of the landmark manager that you wish to use. If
``None``, the convex hull of all landmarks is used.
verbose : `boolean`, optional
Flag that controls information and progress printing.
Returns
-------
clm : :map:`CLM`
The CLM object
"""
# compute reference_shape and normalize images size
self.reference_shape, normalized_images = \
normalization_wrt_reference_shape(
images, group, label, self.normalization_diagonal,
verbose=verbose)
# create pyramid
generators = create_pyramid(normalized_images,
self.n_levels,
self.downscale,
self.features,
verbose=verbose)
# build the model at each pyramid level
if verbose:
if self.n_levels > 1:
print_dynamic('- Building model for each of the {} pyramid '
'levels\n'.format(self.n_levels))
else:
print_dynamic('- Building model\n')
shape_models = []
classifiers = []
# for each pyramid level (high --> low)
for j in range(self.n_levels):
# since models are built from highest to lowest level, the
# parameters of type list need to use a reversed index
rj = self.n_levels - j - 1
if verbose:
level_str = ' - '
if self.n_levels > 1:
level_str = ' - Level {}: '.format(j + 1)
# get images of current level
feature_images = []
for c, g in enumerate(generators):
if verbose:
print_dynamic(
'{}Computing feature space/rescaling - {}'.format(
level_str,
progress_bar_str((c + 1.) / len(generators),
show_bar=False)))
feature_images.append(next(g))
# extract potentially rescaled shapes
shapes = [i.landmarks[group][label] for i in feature_images]
# define shapes that will be used for training
if j == 0:
original_shapes = shapes
train_shapes = shapes
else:
if self.scaled_shape_models:
train_shapes = shapes
else:
train_shapes = original_shapes
# train shape model and find reference frame
if verbose:
print_dynamic('{}Building shape model'.format(level_str))
shape_model = build_shape_model(train_shapes,
self.max_shape_components[rj])
# add shape model to the list
shape_models.append(shape_model)
# build classifiers
sampling_grid = build_sampling_grid(self.patch_shape)
n_points = shapes[0].n_points
level_classifiers = []
for k in range(n_points):
if verbose:
print_dynamic('{}Building classifiers - {}'.format(
level_str,
progress_bar_str((k + 1.) / n_points, show_bar=False)))
positive_labels = []
negative_labels = []
positive_samples = []
negative_samples = []
for i, s in zip(feature_images, shapes):
max_x = i.shape[0] - 1
max_y = i.shape[1] - 1
point = (np.round(s.points[k, :])).astype(int)
patch_grid = sampling_grid + point[None, None, ...]
positive, negative = get_pos_neg_grid_positions(
patch_grid, positive_grid_size=(1, 1))
x = positive[:, 0]
y = positive[:, 1]
x[x > max_x] = max_x
y[y > max_y] = max_y
x[x < 0] = 0
y[y < 0] = 0
positive_sample = i.pixels[positive[:, 0], positive[:,
1], :]
positive_samples.append(positive_sample)
positive_labels.append(np.ones(positive_sample.shape[0]))
x = negative[:, 0]
y = negative[:, 1]
x[x > max_x] = max_x
y[y > max_y] = max_y
x[x < 0] = 0
y[y < 0] = 0
negative_sample = i.pixels[x, y, :]
negative_samples.append(negative_sample)
negative_labels.append(-np.ones(negative_sample.shape[0]))
positive_samples = np.asanyarray(positive_samples)
positive_samples = np.reshape(positive_samples,
(-1, positive_samples.shape[-1]))
positive_labels = np.asanyarray(positive_labels).flatten()
negative_samples = np.asanyarray(negative_samples)
negative_samples = np.reshape(negative_samples,
(-1, negative_samples.shape[-1]))
negative_labels = np.asanyarray(negative_labels).flatten()
X = np.vstack((positive_samples, negative_samples))
t = np.hstack((positive_labels, negative_labels))
clf = self.classifier_trainers[rj](X, t)
level_classifiers.append(clf)
# add level classifiers to the list
classifiers.append(level_classifiers)
if verbose:
print_dynamic('{}Done\n'.format(level_str))
# reverse the list of shape and appearance models so that they are
# ordered from lower to higher resolution
shape_models.reverse()
classifiers.reverse()
n_training_images = len(images)
from .base import CLM
return CLM(shape_models, classifiers, n_training_images,
self.patch_shape, self.features, self.reference_shape,
self.downscale, self.scaled_shape_models)
def _train_batch(self, image_batch, increment=False, group=None,
verbose=False):
r"""
"""
# normalize images
image_batch = rescale_images_to_reference_shape(
image_batch, group, self.reference_shape, verbose=verbose)
# build models at each scale
if verbose:
print_dynamic('- Training models\n')
# for each level (low --> high)
for i in range(self.n_scales):
if verbose:
if self.n_scales > 1:
prefix = ' - Scale {}: '.format(i)
else:
prefix = ' - '
else:
prefix = None
# Handle holistic features
if i == 0 and self.holistic_features[i] == no_op:
# Saves a lot of memory
feature_images = image_batch
elif i == 0 or self.holistic_features[i] is not self.holistic_features[i - 1]:
# compute features only if this is the first pass through
# the loop or the features at this scale are different from
# the features at the previous scale
feature_images = compute_features(image_batch,
self.holistic_features[i],
prefix=prefix,
verbose=verbose)
# handle scales
if self.scales[i] != 1:
# scale feature images only if scale is different than 1
scaled_images = scale_images(feature_images,
self.scales[i],
prefix=prefix,
verbose=verbose)
else:
scaled_images = feature_images
# extract scaled shapes
scaled_shapes = [image.landmarks[group].lms
for image in scaled_images]
# train shape model
if verbose:
print_dynamic('{}Training shape model'.format(prefix))
# TODO: This should be cleaned up by defining shape model classes
if increment:
increment_shape_model(
self.shape_models[i], scaled_shapes,
max_components=self.max_shape_components[i],
forgetting_factor=self.shape_forgetting_factor,
prefix=prefix, verbose=verbose)
else:
shape_model = build_shape_model(
scaled_shapes, max_components=self.max_shape_components[i],
prefix=prefix, verbose=verbose)
self.shape_models.append(shape_model)
# train expert ensemble
if verbose:
print_dynamic('{}Training expert ensemble'.format(prefix))
if increment:
self.expert_ensembles[i].increment(scaled_images,
scaled_shapes,
prefix=prefix,
verbose=verbose)
else:
expert_ensemble = self.expert_ensemble_cls[i](scaled_images,
scaled_shapes,
prefix=prefix,
verbose=verbose)
self.expert_ensembles.append(expert_ensemble)
if verbose:
print_dynamic('{}Done\n'.format(prefix))