特征脸

特征脸

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_lfw_people

faces = fetch_lfw_people()

faces.keys()

dict_keys(['data', 'images', 'target', 'target_names', 'DESCR'])

faces.data.shape

(13233, 2914)

faces.target_names

array(['AJ Cook', 'AJ Lamas', 'Aaron Eckhart', ..., 'Zumrati Juma',
'Zurab Tsereteli', 'Zydrunas Ilgauskas'], dtype='<U35')

faces.images.shape

(13233, 62, 47)

random_indexes = np.random.permutation(len(faces.data))
X = faces.data[random_indexes]
example_faces = X[:36,:]
example_faces.shape

(36, 2914)

def plot_faces(faces):
    
    fig, axes = plt.subplots(6, 6, figsize=(10, 10),
                         subplot_kw={'xticks':[], 'yticks':[]},
    gridspec_kw=dict(hspace=0.1, wspace=0.1)) 
    for i, ax in enumerate(axes.flat):
        ax.imshow(faces[i].reshape(62, 47), cmap='bone')
    plt.show()
    
plot_faces(example_faces)

特征脸

%%time
from sklearn.decomposition import PCA 
pca = PCA(svd_solver='randomized')
pca.fit(X)

Wall time: 33.3 s
PCA(copy=True, iterated_power='auto', n_components=None, random_state=None,
svd_solver='randomized', tol=0.0, whiten=False) # 随机的方式求解， 没有指定主成分n，都要

pca.components_.shape # 所有的主成分

(2914, 2914)

plot_faces(pca.components_[:36,:])  # 前面比较笼统， 人脸就是大概这个位置，每一个脸都是特征脸的，线性组合