def train(self):
# Check if the given dataset exists:
if not os.path.exists(self.dataset):
print ">> [Error] No Dataset Found at '%s'." % self.dataset
sys.exit(1)
# Reads the images, labels and folder_names from a given dataset. Images
# are resized to given size on the fly:
print ">> Loading Dataset <-- " + self.dataset
[images, labels,
subject_names] = self.read_images(self.dataset, self.image_size)
# Zip us a {label, name} dict from the given data:
list_of_labels = list(xrange(max(labels) + 1))
subject_dictionary = dict(zip(list_of_labels, subject_names))
# Get the model we want to compute:
model = self.get_model(image_size=self.image_size,
subject_names=subject_dictionary)
# Sometimes you want to know how good the model may perform on the data
# given, the script allows you to perform a k-fold Cross Validation before
# the Detection & Recognition part starts:
if self.numfolds is not None:
print ">> Validating Model With %s Folds.." % self.numfolds
# We want to have some log output, so set up a new logging handler
# and point it to stdout:
handler = logging.StreamHandler(sys.stdout)
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
handler.setFormatter(formatter)
# Add a handler to facerec modules, so we see what's going on inside:
logger = logging.getLogger("facerec")
logger.addHandler(handler)
logger.setLevel(logging.DEBUG)
# Perform the validation & print results:
crossval = KFoldCrossValidation(model, k=self.numfolds)
crossval.validate(images, labels)
crossval.print_results()
# Compute the model:
print ">> Computing Model.."
model.compute(images, labels)
# And save the model, which uses Pythons pickle module:
print ">> Saving Model.."
save_model(self.model_filename, model)
def train(self):
# Check if the given dataset exists:
if not os.path.exists(self.dataset):
print ">> [Error] No Dataset Found at '%s'." % self.dataset
sys.exit(1)
# Reads the images, labels and folder_names from a given dataset. Images
# are resized to given size on the fly:
print ">> Loading Dataset <-- " + self.dataset
[images, labels, subject_names] = self.read_images(self.dataset, self.image_size)
# Zip us a {label, name} dict from the given data:
list_of_labels = list(xrange(max(labels) + 1))
subject_dictionary = dict(zip(list_of_labels, subject_names))
# Get the model we want to compute:
model = self.get_model(image_size=self.image_size, subject_names=subject_dictionary)
# Sometimes you want to know how good the model may perform on the data
# given, the script allows you to perform a k-fold Cross Validation before
# the Detection & Recognition part starts:
if self.numfolds is not None:
print ">> Validating Model With %s Folds.." % self.numfolds
# We want to have some log output, so set up a new logging handler
# and point it to stdout:
handler = logging.StreamHandler(sys.stdout)
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
handler.setFormatter(formatter)
# Add a handler to facerec modules, so we see what's going on inside:
logger = logging.getLogger("facerec")
logger.addHandler(handler)
logger.setLevel(logging.DEBUG)
# Perform the validation & print results:
crossval = KFoldCrossValidation(model, k=self.numfolds)
crossval.validate(images, labels)
crossval.print_results()
# Compute the model:
print ">> Computing Model.."
model.compute(images, labels)
# And save the model, which uses Pythons pickle module:
print ">> Saving Model.."
save_model(self.model_filename, model)
