def train(tagged):
"""
Trains an SVM classifier based on the training data passed.
Mostly based on http://dlib.net/svm_binary_classifier.py.html.
:param tagged: list of TaggedFace to train on
:return: dlib.svm
"""
x = dlib.vectors() # will carry the facial encodings
y = dlib.array() # will carry the gender label
print("Preparing dataset...")
total = len(tagged)
for i, t in enumerate(tagged):
print(f"\rEncoding {t.path} ({i + 1}/{total})...", end="")
faces = encode(t.img)
x.append(dlib.vector(faces[0]))
y.append(t.tag)
img = t.img
for _ in range(5):
faces = encode(img)
if not faces:
break
x.append(dlib.vector(faces[0]))
y.append(t.tag)
img = cv2.resize(img, None, fx=0.7, fy=0.7)
print("Training SVM...")
trainer = dlib.svm_c_trainer_radial_basis()
#trainer.be_verbose()
trainer.set_c(10)
model = trainer.train(x, y)
with open(PATH_SVMFILE, "wb") as filehandle:
pickle.dump(model, filehandle)
return None
def test_array_extend():
a = array()
a.extend([0, 1, 2, 3, 4])
assert len(a) == 5
for idx, val in enumerate(a):
assert idx == val
assert type(val) == FloatType
def test_array_resize():
a = array(10)
a.resize(100)
assert len(a) == 100
for i in range(100):
assert a[i] == 0
def test_array_serialization_empty():
a = array()
# cPickle with protocol 2 required for Python 2.7
# see http://pybind11.readthedocs.io/en/stable/advanced/classes.html#custom-constructors
ser = pickle.dumps(a, 2)
deser = pickle.loads(ser)
assert a == deser
def test_array_extend():
a = array()
a.extend([0, 1, 2, 3, 4])
assert len(a) == 5
for idx, val in enumerate(a):
assert idx == val
assert type(val) == FloatType
def test_array_serialization_empty():
a = array()
# cPickle with protocol 2 required for Python 2.7
# see http://pybind11.readthedocs.io/en/stable/advanced/classes.html#custom-constructors
ser = pickle.dumps(a, 2)
deser = pickle.loads(ser)
assert a == deser
def test_array_resize():
a = array(10)
a.resize(100)
assert len(a) == 100
for i in range(100):
assert a[i] == 0
def training_data():
r = Random(0)
predictors = vectors()
sparse_predictors = sparse_vectors()
response = array()
for i in range(30):
for c in [-1, 1]:
response.append(c)
values = [r.random() + c * 0.5 for _ in range(3)]
predictors.append(vector(values))
sp = sparse_vector()
for i, v in enumerate(values):
sp.append(pair(i, v))
sparse_predictors.append(sp)
return predictors, sparse_predictors, response
def training_data():
r = Random(0)
predictors = vectors()
sparse_predictors = sparse_vectors()
response = array()
for i in range(30):
for c in [-1, 1]:
response.append(c)
values = [r.random() + c * 0.5 for _ in range(3)]
predictors.append(vector(values))
sp = sparse_vector()
for i, v in enumerate(values):
sp.append(pair(i, v))
sparse_predictors.append(sp)
return predictors, sparse_predictors, response
def test_array_init_with_list():
a = array([0, 1, 2, 3, 4])
assert len(a) == 5
for idx, val in enumerate(a):
assert idx == val
assert type(val) == FloatType
def test_array_init_with_zero():
a = array(0)
assert len(a) == 0
def test_array_serialization():
a = array([0, 1, 2, 3, 4])
ser = pickle.dumps(a, 2)
deser = pickle.loads(ser)
assert a == deser
def test_array_clear():
a = array(10)
a.clear()
assert len(a) == 0
def test_array_string_representations_empty():
a = array()
assert str(a) == ""
assert repr(a) == "array[]"
def test_array_serialization():
a = array([0, 1, 2, 3, 4])
ser = pickle.dumps(a, 2)
deser = pickle.loads(ser)
assert a == deser
def test_array_init_with_tuple():
a = array((0, 1, 2, 3, 4))
for idx, val in enumerate(a):
assert idx == val
assert type(val) == FloatType
# things run faster.
#
# Compiling dlib should work on any operating system so long as you have
# CMake and boost-python installed. On Ubuntu, this can be done easily by
# running the command:
# sudo apt-get install libboost-python-dev cmake
#
import dlib
try:
import cPickle as pickle
except ImportError:
import pickle
x = dlib.vectors()
y = dlib.array()
# Make a training dataset. Here we have just two training examples. Normally
# you would use a much larger training dataset, but for the purpose of example
# this is plenty. For binary classification, the y labels should all be either +1 or -1.
x.append(dlib.vector([1, 2, 3, -1, -2, -3]))
y.append(+1)
x.append(dlib.vector([-1, -2, -3, 1, 2, 3]))
y.append(-1)
# Now make a training object. This object is responsible for turning a
# training dataset into a prediction model. This one here is a SVM trainer
# that uses a linear kernel. If you wanted to use a RBF kernel or histogram
# intersection kernel you could change it to one of these lines:
def test_array_init_with_empty_list():
a = array([])
assert len(a) == 0
def test_array_clear():
a = array(10)
a.clear()
assert len(a) == 0
def test_array_string_representations():
a = array([1, 2, 3])
assert str(a) == "1\n2\n3"
assert repr(a) == "array[1, 2, 3]"
def test_array_string_representations_empty():
a = array()
assert str(a) == ""
assert repr(a) == "array[]"
def test_array_init_without_argument():
a = array()
assert len(a) == 0
def test_array_init_with_empty_list():
a = array([])
assert len(a) == 0
def test_array_init_without_argument():
a = array()
assert len(a) == 0
def test_array_init_with_list():
a = array([0, 1, 2, 3, 4])
assert len(a) == 5
for idx, val in enumerate(a):
assert idx == val
assert type(val) == FloatType
def test_array_init_with_zero():
a = array(0)
assert len(a) == 0
def test_array_init_with_number():
a = array(5)
assert len(a) == 5
for i in range(5):
assert a[i] == 0
assert type(a[i]) == FloatType
def test_array_init_with_negative_number():
with raises(Exception):
array(-5)
def test_array_init_with_negative_number():
with raises(Exception):
array(-5)
def test_array_string_representations():
a = array([1, 2, 3])
assert str(a) == "1\n2\n3"
assert repr(a) == "array[1, 2, 3]"
def test_array_init_with_negative_number():
with raises(MemoryError):
array(-5)
def test_array_init_with_number():
a = array(5)
assert len(a) == 5
for i in range(5):
assert a[i] == 0
assert type(a[i]) == FloatType
def test_array_init_with_tuple():
a = array((0, 1, 2, 3, 4))
for idx, val in enumerate(a):
assert idx == val
assert type(val) == FloatType
# python setup.py install
#
# Compiling dlib should work on any operating system so long as you have
# CMake installed. On Ubuntu, this can be done easily by running the
# command:
# sudo apt-get install cmake
#
import dlib
try:
import cPickle as pickle
except ImportError:
import pickle
x = dlib.vectors()
y = dlib.array()
# Make a training dataset. Here we have just two training examples. Normally
# you would use a much larger training dataset, but for the purpose of example
# this is plenty. For binary classification, the y labels should all be either +1 or -1.
x.append(dlib.vector([1, 2, 3, -1, -2, -3]))
y.append(+1)
x.append(dlib.vector([-1, -2, -3, 1, 2, 3]))
y.append(-1)
# Now make a training object. This object is responsible for turning a
# training dataset into a prediction model. This one here is a SVM trainer
# that uses a linear kernel. If you wanted to use a RBF kernel or histogram
# intersection kernel you could change it to one of these lines:
# svm = dlib.svm_c_trainer_histogram_intersection()
male_label = +1
female_label = -1
print "Retrieving males images ..."
males = glob.glob("./imdb-datasets/images/males/*.jpg")
print "Retrieved {} faces !".format(len(males))
print "Retrieving females images ..."
females = glob.glob("./imdb-datasets/images/females/*.jpg")
print "Retrieved {} faces !".format(len(females))
females = females[:max_size]
males = males[:max_size]
vectors = dlib.vectors()
labels = dlib.array()
print "Reading males images ..."
for i, male in enumerate(males):
print "Reading {} of {}\r".format(i, len(males))
face_vectors = face_vector(read_image(male))
if face_vectors is None:
continue
vectors.append(dlib.vector(face_vectors))
labels.append(male_label)
print "Reading females images ..."
for i, female in enumerate(females):
print "Reading {} of {}\r".format(i, len(females))
face_vectors = face_vector(read_image(female))
if face_vectors is None:
