Finishing Up Persons Using Machine Learning

This example shows the use of various machine learning algorithms to complete images. The goal is to predict the lower half of the face, given its upper half.

The first column of images shows real faces. The following columns illustrate how trees (extremely randomized trees), the k-nearest neighbor method (k nearest neighbors / K-nn), linear regression (linear regression) and RidgeCV (ridge regression complete) complete the bottom half of these individuals.

# Подключаем библиотекиimport numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_olivetti_faces
from sklearn.utils.validation import check_random_state
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import RidgeCV
# Загружаем наборы данных
data = fetch_olivetti_faces()
targets = data.target
data = data.images.reshape((len(data.images), -1))
train = data[targets < 30]
test = data[targets >= 30]  # Test on independent people# Тест на подмножество людей
n_faces = 5
rng = check_random_state(4)
face_ids = rng.randint(test.shape[0], size=(n_faces, ))
test = test[face_ids, :]
n_pixels = data.shape[1]
# Верхняя половина лиц
X_train = train[:, :(n_pixels + 1) // 2]
# Нижняя половина лиц
y_train = train[:, n_pixels // 2:]
X_test = test[:, :(n_pixels + 1) // 2]
y_test = test[:, n_pixels // 2:]
# Определяем методы
ESTIMATORS = {
    "Extra trees": ExtraTreesRegressor(n_estimators=10, max_features=32,
                                       random_state=0),
    "K-nn": KNeighborsRegressor(),
    "Linear regression": LinearRegression(),
    "Ridge": RidgeCV(),
}
y_test_predict = dict()
for name, estimator in ESTIMATORS.items():
    estimator.fit(X_train, y_train)
    y_test_predict[name] = estimator.predict(X_test)
# Визуализация
image_shape = (64, 64)
n_cols = 1 + len(ESTIMATORS)
plt.figure(figsize=(2. * n_cols, 2.26 * n_faces))
plt.suptitle("Завершение изображений с помощью различных алгоритмов машинного обучения", size=16)
for i in range(n_faces):
    true_face = np.hstack((X_test[i], y_test[i]))
    if i:
        sub = plt.subplot(n_faces, n_cols, i * n_cols + 1)
    else:
        sub = plt.subplot(n_faces, n_cols, i * n_cols + 1,
                          title="true faces")
    sub.axis("off")
    sub.imshow(true_face.reshape(image_shape),
               cmap=plt.cm.gray,
               interpolation="nearest")
    for j, est in enumerate(sorted(ESTIMATORS)):
        completed_face = np.hstack((X_test[i], y_test_predict[est][i]))
        if i:
            sub = plt.subplot(n_faces, n_cols, i * n_cols + 2 + j)
        else:
            sub = plt.subplot(n_faces, n_cols, i * n_cols + 2 + j,
                              title=est)
        sub.axis("off")
        sub.imshow(completed_face.reshape(image_shape),
                   cmap=plt.cm.gray,
                   interpolation="nearest")
plt.show()