def load_data(self):
'''
Loads data to use in training.
'''
# Load data
if self.dataset == FaceRecData.Yalefaces_A:
self.instances = ImageIO.loadYalefacesImages(self.data_directory,
loud=False)
elif self.dataset == FaceRecData.Yalefaces_B:
self.instances = ImageIO.loadExtendedCroppedYalefaces(
self.data_directory, loud=False)
else:
raise RuntimeError('FaceRecTest not assigned a valid dataset')
# Sample from each class to create train/dev/test partitions
self.trn_data = list()
self.dev_data = list()
self.tst_data = list()
# Sort instances by label
classes = dict()
for instance in self.instances:
label = instance[0]
if label not in classes.keys():
classes[label] = list()
classes[label].append(instance)
num_labels = max(classes.keys()) + 1
# Calculate how many samples should be in each partition
num_trn = int((self.trn_part / 100.0) * len(self.instances))
num_dev = int((self.dev_part / 100.0) * len(self.instances))
num_tst = int((self.tst_part / 100.0) * len(self.instances))
# If any leftovers, give more to training partition
num_trn += len(self.instances) - sum((num_trn, num_dev, num_tst))
# Partition trn/dev/tst
def partition(src, dest, num):
num_labels = max(src.keys()) + 1
count = 0
i = 0
while i < num:
instances = src[count % num_labels]
if len(instances) > 0:
idx = random.randint(0, len(instances) - 1)
dest.append(instances.pop(idx))
i += 1
count += 1
partition(classes, self.trn_data, num_trn)
partition(classes, self.dev_data, num_dev)
partition(classes, self.tst_data, num_tst)
def load_data(self):
'''
Loads data to use in training.
'''
# Load data
if self.dataset == FaceRecData.Yalefaces_A:
self.instances = ImageIO.loadYalefacesImages(
self.data_directory, loud=False)
elif self.dataset == FaceRecData.Yalefaces_B:
self.instances = ImageIO.loadExtendedCroppedYalefaces(
self.data_directory, loud=False)
else:
raise RuntimeError('FaceRecTest not assigned a valid dataset')
# Sample from each class to create train/dev/test partitions
self.trn_data = list()
self.dev_data = list()
self.tst_data = list()
# Sort instances by label
classes = dict()
for instance in self.instances:
label = instance[0]
if label not in classes.keys():
classes[label] = list()
classes[label].append(instance)
num_labels = max(classes.keys())+1
# Calculate how many samples should be in each partition
num_trn = int( (self.trn_part/100.0) * len(self.instances) )
num_dev = int( (self.dev_part/100.0) * len(self.instances) )
num_tst = int( (self.tst_part/100.0) * len(self.instances) )
# If any leftovers, give more to training partition
num_trn += len(self.instances) - sum((num_trn, num_dev, num_tst))
# Partition trn/dev/tst
def partition(src, dest, num):
num_labels = max(src.keys())+1
count = 0
i = 0
while i < num:
instances = src[count % num_labels]
if len(instances) > 0:
idx = random.randint(0, len(instances)-1)
dest.append( instances.pop(idx) )
i += 1
count += 1
partition(classes, self.trn_data, num_trn)
partition(classes, self.dev_data, num_dev)
partition(classes, self.tst_data, num_tst)
def load_data(self):
'''
Loads data to use in training.
'''
self.face_instances = list()
self.non_face_instances = list()
# Load data
if self.dataset == FaceDetData.MIT_Face_Data:
self.face_instances.extend(
ImageIO.loadFaceDetectionImages(
self.data_directory + '/train/face', 1))
self.face_instances.extend(
ImageIO.loadFaceDetectionImages(
self.data_directory + '/test/face', 1))
self.non_face_instances.extend(
ImageIO.loadFaceDetectionImages(
self.data_directory + '/train/non-face', 0))
self.non_face_instances.extend(
ImageIO.loadFaceDetectionImages(
self.data_directory + '/test/non-face', 0))
else:
raise RuntimeError('FaceDetTest not assigned a valid dataset')
img_size = numpy.shape(self.face_instances[0][0])
self.face_detector = FaceDetector(self.iterations, img_size)
self.total_face_instances = len(self.face_instances)
self.total_non_face_instances = len(self.non_face_instances)
# Sample from each class to create train/dev/test partitions
self.face_trn_data = list()
self.non_face_trn_data = list()
self.face_dev_data = list()
self.non_face_dev_data = list()
self.face_tst_data = list()
self.non_face_tst_data = list()
# Calculate how many samples should be in each partition
num_face_trn = int((self.trn_part / 100.0) * len(self.face_instances))
num_non_face_trn = int(
(self.trn_part / 100.0) * len(self.non_face_instances))
num_face_dev = int((self.dev_part / 100.0) * len(self.face_instances))
num_non_face_dev = int(
(self.dev_part / 100.0) * len(self.non_face_instances))
num_face_tst = int((self.tst_part / 100.0) * len(self.face_instances))
num_non_face_tst = int(
(self.tst_part / 100.0) * len(self.non_face_instances))
# If any leftovers, give more to training partition
num_face_trn += len(self.face_instances) - sum(
(num_face_trn, num_face_dev, num_face_tst))
num_non_face_trn += len(self.non_face_instances) - sum(
(num_non_face_trn, num_non_face_dev, num_non_face_tst))
# Partition trn/dev/tst
def partition(src, dest, num):
i = 0
while i < num:
if len(src) > 0:
idx = random.randint(0, len(src) - 1)
dest.append(src.pop(idx))
i += 1
partition(self.face_instances, self.face_trn_data, num_face_trn)
partition(self.non_face_instances, self.non_face_trn_data,
num_non_face_trn)
partition(self.face_instances, self.face_dev_data, num_face_dev)
partition(self.non_face_instances, self.non_face_dev_data,
num_non_face_dev)
partition(self.face_instances, self.face_tst_data, num_face_tst)
partition(self.non_face_instances, self.non_face_tst_data,
num_non_face_tst)
def load_data(self):
'''
Loads data to use in training.
'''
self.face_instances = list()
self.non_face_instances = list()
# Load data
if self.dataset == FaceDetData.MIT_Face_Data:
self.face_instances.extend(ImageIO.loadFaceDetectionImages(self.data_directory + '/train/face', 1))
self.face_instances.extend(ImageIO.loadFaceDetectionImages(self.data_directory + '/test/face', 1))
self.non_face_instances.extend(ImageIO.loadFaceDetectionImages(self.data_directory + '/train/non-face', 0))
self.non_face_instances.extend(ImageIO.loadFaceDetectionImages(self.data_directory + '/test/non-face', 0))
else:
raise RuntimeError('FaceDetTest not assigned a valid dataset')
img_size = numpy.shape(self.face_instances[0][0])
self.face_detector = FaceDetector(self.iterations, img_size)
self.total_face_instances = len(self.face_instances)
self.total_non_face_instances = len(self.non_face_instances)
# Sample from each class to create train/dev/test partitions
self.face_trn_data = list()
self.non_face_trn_data = list()
self.face_dev_data = list()
self.non_face_dev_data = list()
self.face_tst_data = list()
self.non_face_tst_data = list()
# Calculate how many samples should be in each partition
num_face_trn = int( (self.trn_part/100.0) * len(self.face_instances) )
num_non_face_trn = int( (self.trn_part/100.0) * len(self.non_face_instances) )
num_face_dev = int( (self.dev_part/100.0) * len(self.face_instances) )
num_non_face_dev = int( (self.dev_part/100.0) * len(self.non_face_instances) )
num_face_tst = int( (self.tst_part/100.0) * len(self.face_instances) )
num_non_face_tst = int( (self.tst_part/100.0) * len(self.non_face_instances) )
# If any leftovers, give more to training partition
num_face_trn += len(self.face_instances) - sum((num_face_trn, num_face_dev, num_face_tst))
num_non_face_trn += len(self.non_face_instances) - sum((num_non_face_trn, num_non_face_dev, num_non_face_tst))
# Partition trn/dev/tst
def partition(src, dest, num):
i = 0
while i < num:
if len(src) > 0:
idx = random.randint(0, len(src)-1)
dest.append( src.pop(idx) )
i += 1
partition(self.face_instances, self.face_trn_data, num_face_trn)
partition(self.non_face_instances, self.non_face_trn_data, num_non_face_trn)
partition(self.face_instances, self.face_dev_data, num_face_dev)
partition(self.non_face_instances, self.non_face_dev_data, num_non_face_dev)
partition(self.face_instances, self.face_tst_data, num_face_tst)
partition(self.non_face_instances, self.non_face_tst_data, num_non_face_tst)