def _attach_predictions(template_name, pixels, coordinates, heatmaps,
labeller_fn, show_input_images, show_combined_heatmap,
show_individual_heatmaps, index_to_label_fn):
input_image = Image.init_from_channels_at_back(pixels)
input_image.landmarks['predictions'] = PointCloud(coordinates)
labeller(input_image, 'predictions', labeller_fn)
del input_image.landmarks['predictions']
images = []
if show_input_images:
images.append(input_image)
if show_combined_heatmap:
combined_heatmap = np.sum(heatmaps, axis=-1) * 255.0
combined_heatmap = Image(combined_heatmap)
combined_heatmap.landmarks[template_name] = input_image.landmarks[
template_name]
images.append(combined_heatmap)
if show_individual_heatmaps:
for i in range(heatmaps.shape[-1]):
heatmap = heatmaps[..., i] * 255.0
heatmap = Image(heatmap)
if index_to_label_fn is not None:
label = index_to_label_fn(i)
#print(label)
heatmap.landmarks[label] = PointCloud([coordinates[i]])
images.append(heatmap)
return images
def _visualise_predictions(input_image, heatmaps, coordinates):
group_sizes = [17, 17]
group_labels = ['Endocardium', 'Epicardium']
plt.figure()
# input image
menpo_image = Image.init_from_channels_at_back(input_image)
menpo_image.landmarks['predictions'] = PointCloud(coordinates)
labeller(menpo_image, 'predictions', left_ventricle_34)
del menpo_image.landmarks['predictions']
rasterised_image = menpo_image.rasterize_landmarks(group='lv_34')
ax_input_image = plt.subplot2grid((7, 14), (0, 0), colspan=6, rowspan=6)
ax_input_image.imshow(rasterised_image.pixels_with_channels_at_back())
index = 0
heatmap_plots = []
# plot individual predictions
for i in range(len(group_sizes)):
for j in range(group_sizes[i]):
axis = plt.subplot2grid((7, 14), (i, 7 + j))
axis.imshow(heatmaps[..., index])
index += 1
heatmap_plots.append(axis)
add_group_labels(heatmap_plots, group_labels, group_sizes)
make_ticklabels_invisible(heatmap_plots)
plt.show()
def train_aic_rlms(trainset, output, n_train_imgs=None):
training_images = []
# load landmarked images
for i in mio.import_images(Path(trainset) / '*', verbose=True, max_images=n_train_imgs):
# crop image
i = i.crop_to_landmarks_proportion(0.5)
labeller(i, 'PTS', face_ibug_68_to_face_ibug_66_trimesh)
# convert it to greyscale if needed
if i.n_channels == 3:
i = i.as_greyscale(mode='average')
# append it to the list
training_images.append(i)
offsets = np.meshgrid(range(-0, 1, 1), range(-0, 1, 1))
offsets = np.asarray([offsets[0].flatten(), offsets[1].flatten()]).T
np.seterr(divide ='ignore')
np.seterr(invalid ='ignore')
unified = UnifiedAAMCLM(training_images,
parts_shape=(17, 17),
offsets=offsets,
group = test_group,
holistic_features=fast_dsift,
diagonal=100,
scales=(1, .5),
max_appearance_components = min(50,int(n_train_imgs/2)),
verbose=True)
n_appearance=[min(25,int(n_train_imgs/2)), min(50,int(n_train_imgs/2))]
fitter = UnifiedAAMCLMFitter(unified, algorithm_cls=AICRLMS, n_shape=[3, 12], n_appearance=n_appearance)
return fitter
def process(image, crop_proportion=0.2, max_diagonal=400):
if image.n_channels == 3:
image = image.as_greyscale()
image = image.crop_to_landmarks_proportion(crop_proportion)
d = image.diagonal()
if d > max_diagonal:
image = image.rescale(float(max_diagonal) / d)
labeller(image, 'PTS', face_ibug_68_to_face_ibug_68_trimesh)
return image
def load_test_data(testset, n_test_imgs=None):
test_images = []
for i in mio.import_images(Path(testset), verbose=True, max_images=n_test_imgs):
i = i.crop_to_landmarks_proportion(0.5)
labeller(i, 'PTS', face_ibug_68_to_face_ibug_66_trimesh)
if i.n_channels == 3:
i = i.as_greyscale(mode='average')
test_images.append(i)
return test_images
def AAMModel(path, max_shape=None, max_appearance=None):
training_images = []
for img in print_progress(mio.import_images(path, verbose=True)):
labeller(img, 'PTS', face_ibug_68_to_face_ibug_68_trimesh)
training_images.append(img)
aam_model = HolisticAAM(training_images,
group='face_ibug_68_trimesh',
scales=(0.5, 1.0),
holistic_features=fast_dsift,
verbose=True,
max_shape_components=max_shape,
max_appearance_components=max_appearance)
return aam_model, training_images
def test_squared_even_patches_sample_offsets():
image = mio.import_builtin_asset('breakingbad.jpg')
image = labeller(image, 'PTS', ibug_face_68)
sample_offsets = np.array([[0, 0], [1, 0]])
patches = image.extract_patches(image.landmarks['PTS'].lms,
sample_offsets=sample_offsets)
assert_equals(len(patches), 136)
def test_squared_even_patches_sample_offsets():
image = mio.import_builtin_asset('breakingbad.jpg')
image = labeller(image, 'PTS', ibug_face_68)
sample_offsets = PointCloud([[0, 0], [1, 0]])
patches = image.extract_patches(image.landmarks['PTS'].lms,
sample_offsets=sample_offsets)
assert_equals(len(patches), 136)
def test_squared_even_patches_single_array():
image = mio.import_builtin_asset('breakingbad.jpg')
image = labeller(image, 'PTS', ibug_face_68)
patch_shape = (16, 16)
patches = image.extract_patches(image.landmarks['PTS'].lms,
as_single_array=True,
patch_size=patch_shape)
assert_equals(patches.shape, ((68, 1, 3) + patch_shape))
def loadImages(self, path_to_training_images):
training_images = []
for img in print_progress(mio.import_images(path_to_training_images, verbose=True)):
# convert to greyscale
if img.n_channels == 3:
img = img.as_greyscale()
# crop to landmarks bounding box with an extra 20% padding
img = img.crop_to_landmarks_proportion(0.2)
# rescale image if its diagonal is bigger than 400 pixels
d = img.diagonal()
if d > 400:
img = img.rescale(400.0 / d)
# define a TriMesh which will be useful for Piecewise Affine Warp of HolisticAAM
labeller(img, 'PTS', face_ibug_68_to_face_ibug_68_trimesh)
# append to list
training_images.append(img)
return training_images
def test_squared_even_patches_single_array():
image = mio.import_builtin_asset('breakingbad.jpg')
image = labeller(image, 'PTS', ibug_face_68)
patch_shape = (16, 16)
patches = image.extract_patches(image.landmarks['PTS'].lms,
as_single_array=True,
patch_size=patch_shape)
assert_equals(patches.shape, ((68, 1, 3) + patch_shape))
def test_squared_even_patches_landmarks_label():
image = mio.import_builtin_asset('breakingbad.jpg')
image = labeller(image, 'PTS', ibug_face_68)
patch_shape = (16, 16)
patches = image.extract_patches_around_landmarks('ibug_face_68',
label='nose',
patch_size=patch_shape)
assert_equals(len(patches), 9)
def test_squared_even_patches_landmarks_label():
image = mio.import_builtin_asset('breakingbad.jpg')
image = labeller(image, 'PTS', ibug_face_68)
patch_shape = (16, 16)
patches = image.extract_patches_around_landmarks('ibug_face_68',
label='nose',
patch_size=patch_shape)
assert_equals(len(patches), 9)
def load_database(path_to_images,
save_path,
db_name,
crop_percentage,
fast,
group,
verbose=False):
# create filename
if group is not None:
filename = (db_name + '_' + group.__name__ + '_crop' +
str(int(crop_percentage * 100)))
else:
filename = db_name + 'PTS' + '_crop' + str(int(crop_percentage * 100))
if fast:
filename += '_menpofast.pickle'
else:
filename += '_menpo.pickle'
save_path = os.path.join(save_path, filename)
# check if file exists
if file_exists(save_path):
if verbose:
print_dynamic('Loading images...')
images = pickle_load(save_path)
if verbose:
print_dynamic('Images Loaded.')
else:
# load images
images = []
for i in mio.import_images(path_to_images, verbose=verbose):
if fast:
i = convert_from_menpo(i)
i.crop_to_landmarks_proportion_inplace(crop_percentage,
group='PTS')
if group is not None:
labeller(i, 'PTS', group)
if i.n_channels == 3:
i = i.as_greyscale(mode='average')
images.append(i)
# save images
pickle_dump(images, save_path)
# return images
return images
def load_database(path_to_images, save_path, db_name, crop_percentage,
fast, group, verbose=False):
# create filename
if group is not None:
filename = (db_name + '_' + group.__name__ + '_crop' +
str(int(crop_percentage * 100)))
else:
filename = db_name + 'PTS' + '_crop' + str(int(crop_percentage * 100))
if fast:
filename += '_menpofast.pickle'
else:
filename += '_menpo.pickle'
save_path = os.path.join(save_path, filename)
# check if file exists
if file_exists(save_path):
if verbose:
print_dynamic('Loading images...')
images = pickle_load(save_path)
if verbose:
print_dynamic('Images Loaded.')
else:
# load images
images = []
for i in mio.import_images(path_to_images, verbose=verbose):
if fast:
i = convert_from_menpo(i)
i.crop_to_landmarks_proportion_inplace(crop_percentage, group='PTS')
if group is not None:
labeller(i, 'PTS', group)
if i.n_channels == 3:
i = i.as_greyscale(mode='average')
images.append(i)
# save images
pickle_dump(images, save_path)
# return images
return images
[247.96232402, 264.81933552], [265.63001359, 240.76240374],
[273.7321494, 219.23983464], [275.94833733, 203.23538213],
[276.43082796, 187.79108987], [271.33176225, 170.34611298],
[258.50633904, 164.92193012], [256.68032211, 190.02252505],
[253.34318274, 202.62322841], [250.64136836, 216.39925191],
[248.92192186, 254.44710508], [257.03785057, 217.075461],
[260.28050441, 202.86155077], [261.39108462,
187.78257369]])))
# load images
filenames = ['breakingbad.jpg', 'takeo.ppm', 'lenna.png', 'einstein.jpg']
training_images = []
for i in range(4):
im = mio.import_builtin_asset(filenames[i])
im.crop_to_landmarks_proportion_inplace(0.1)
labeller(im, 'PTS', ibug_68_trimesh)
if im.n_channels == 3:
im = im.as_greyscale(mode='luminosity')
training_images.append(im)
# Seed the random number generator
np.random.seed(seed=1000)
# build sdms
sdm1 = SDMTrainer(regression_type=mlr_svd,
regression_features=sparse_hog,
patch_shape=(16, 16),
feature_type=None,
normalization_diagonal=150,
n_levels=2,
downscale=1.3,
def aam_build_benchmark(training_images, training_options=None, verbose=False):
r"""
Builds an AAM model.
Parameters
----------
training_images: list of :class:MaskedImage objects
A list of the training images.
training_options: dictionary, optional
A dictionary with the parameters that will be passed in the AAMBuilder
(:class:menpo.fitmultilevel.aam.AAMBuilder).
If None, the default options will be used.
This is an example of the dictionary with the default options:
training_options = {'group': 'PTS',
'feature_type': 'igo',
'transform': PiecewiseAffine,
'trilist': None,
'normalization_diagonal': None,
'n_levels': 3,
'downscale': 2,
'scaled_shape_models': True,
'pyramid_on_features': True,
'max_shape_components': None,
'max_appearance_components': None,
'boundary': 3,
'interpolator': 'scipy'
}
For an explanation of the options, please refer to the AAMBuilder
documentation.
Default: None
verbose: boolean, optional
If True, it prints information regarding the AAM training.
Default: False
Returns
-------
aam: :class:menpo.fitmultilevel.aam.AAM object
The trained AAM model.
"""
if verbose:
print('AAM Training:')
# parse options
if training_options is None:
training_options = {}
# group option
group = training_options.pop('group', None)
# trilist option
trilist = training_options.pop('trilist', None)
if trilist is not None:
labeller(training_images[0], 'PTS', trilist)
training_options['trilist'] = \
training_images[0].landmarks[trilist.__name__].lms.trilist
# build aam
aam = AAMBuilder(**training_options).build(training_images, group=group,
verbose=verbose)
return aam
from menpo.visualize import print_progress
from menpo.landmark import labeller, face_ibug_68_to_face_ibug_68_trimesh
from pathlib import Path
import menpo.io as mio
from menpo.visualize import print_progress
path_to_images = '/home/ice/Documents/Micro-Expression/SAMM/006/006_1_2/'
training_images = []
path_to_lfpw = Path(path_to_images)
training_shapes = []
for lg in print_progress(
mio.import_landmark_files(path_to_lfpw / '*.pts', verbose=True)):
training_shapes.append(lg['all'])
for img in print_progress(mio.import_images(path_to_images, verbose=True)):
# convert to greyscale
if img.n_channels == 3:
img = img.as_greyscale()
# crop to landmarks bounding box with an extra 20% padding
img = img.crop_to_landmarks_proportion(0.2)
# rescale image if its diagonal is bigger than 400 pixels
d = img.diagonal()
if d > 400:
img = img.rescale(400.0 / d)
# define a TriMesh which will be useful for Piecewise Affine Warp of HolisticAAM
labeller(img, 'PTS', face_ibug_68_to_face_ibug_68_trimesh)
# append to list
training_images.append(img)
def load_image(i):
i = i.crop_to_landmarks_proportion(0.5)
if i.n_channels == 3:
i = i.as_greyscale()
labeller(i, 'PTS', face_ibug_68_to_face_ibug_68)
return i
[248.92192186, 254.44710508],
[257.03785057, 217.075461],
[260.28050441, 202.86155077],
[261.39108462, 187.78257369],
]
)
)
)
# load images
filenames = ["breakingbad.jpg", "takeo.ppm", "lenna.png", "einstein.jpg"]
training_images = []
for i in range(4):
im = mio.import_builtin_asset(filenames[i])
im.crop_to_landmarks_proportion_inplace(0.1)
labeller(im, "PTS", ibug_68_trimesh)
if im.n_channels == 3:
im = im.as_greyscale(mode="luminosity")
training_images.append(im)
# Seed the random number generator
np.random.seed(seed=1000)
# build sdms
sdm1 = SDMTrainer(
regression_type=mlr_svd,
regression_features=sparse_hog,
patch_shape=(16, 16),
feature_type=None,
normalization_diagonal=150,
n_levels=2,
def aam_build_benchmark(training_images, training_options=None, verbose=False):
r"""
Builds an AAM model.
Parameters
----------
training_images: list of :class:MaskedImage objects
A list of the training images.
training_options: dictionary, optional
A dictionary with the parameters that will be passed in the AAMBuilder
(:class:menpo.fitmultilevel.aam.AAMBuilder).
If None, the default options will be used.
This is an example of the dictionary with the default options:
training_options = {'group': 'PTS',
'features': 'igo',
'transform': PiecewiseAffine,
'trilist': None,
'normalization_diagonal': None,
'n_levels': 3,
'downscale': 2,
'scaled_shape_models': True,
'max_shape_components': None,
'max_appearance_components': None,
'boundary': 3
}
For an explanation of the options, please refer to the AAMBuilder
documentation.
Default: None
verbose: boolean, optional
If True, it prints information regarding the AAM training.
Default: False
Returns
-------
aam: :class:menpo.fitmultilevel.aam.AAM object
The trained AAM model.
"""
if verbose:
print('AAM Training:')
# parse options
if training_options is None:
training_options = {}
# group option
group = training_options.pop('group', None)
# trilist option
trilist = training_options.pop('trilist', None)
if trilist is not None:
labeller(training_images[0], 'PTS', trilist)
training_options['trilist'] = \
training_images[0].landmarks[trilist.__name__].lms.trilist
# build aam
aam = AAMBuilder(**training_options).build(training_images,
group=group,
verbose=verbose)
return aam
from nose.tools import raises
from StringIO import StringIO
import menpo.io as mio
from menpo.landmark import labeller, ibug_68_trimesh
from menpo.transform import PiecewiseAffine, ThinPlateSplines
from menpo.fitmultilevel.aam import AAMBuilder, PatchBasedAAMBuilder
from menpo.fitmultilevel.featurefunctions import sparse_hog
# load images
filenames = ['breakingbad.jpg', 'takeo.ppm', 'lenna.png', 'einstein.jpg']
training_images = []
for i in range(4):
im = mio.import_builtin_asset(filenames[i])
im.crop_to_landmarks_proportion_inplace(0.1)
labeller(im, 'PTS', ibug_68_trimesh)
if im.n_channels == 3:
im = im.as_greyscale(mode='luminosity')
training_images.append(im)
# build aams
aam1 = AAMBuilder(feature_type=['igo', sparse_hog, None],
transform=PiecewiseAffine,
trilist=training_images[0].landmarks['ibug_68_trimesh'].
lms.trilist,
normalization_diagonal=150,
n_levels=3,
downscale=2,
scaled_shape_models=False,
pyramid_on_features=False,
max_shape_components=[1, 2, 3],
def load_image(i):
i = i.crop_to_landmarks_proportion(0.5)
if i.n_channels == 3:
i = i.as_greyscale()
labeller(i, 'PTS', face_ibug_68_to_face_ibug_68)
return i