基于支持向量机（svm）的人脸识别

注意：本文引用自专业人工智能社区Venus AI

数据集加载与可视化

from sklearn.datasets import fetch_lfw_people
faces = fetch_lfw_people(min_faces_per_person=60)

# Check out sample images
import matplotlib.pyplot as plt
fig, ax = plt.subplots(3, 5)
for i, axi in enumerate(ax.flat):axi.imshow(faces.images[i], cmap='bone')axi.set(xticks=[], yticks=[], xlabel=faces.target_names[faces.target[i]])

使用 PCA 和 SVC 构建模型

from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline

pca = PCA(n_components=150, whiten=True, random_state=42)
svc = SVC(kernel='rbf', class_weight='balanced')model = make_pipeline(pca, svc)

# train, test
from sklearn.model_selection import train_test_splitX_train, X_test, y_train, y_test = train_test_split(faces['data'], faces['target'], test_size=0.2, random_state=42)

使用网格搜索 CV 查找最佳模型

from sklearn.model_selection import GridSearchCVparam_grid ={'svc__C': [1, 5, 10, 15],'svc__gamma': [0.0001, 0.0005, 0.001, 0.005],
}

grid = GridSearchCV(model, param_grid=param_grid, cv=5)
%time grid.fit(X_train, y_train)

{'svc__C': 1, 'svc__gamma': 0.005}

grid.best_params_

grid.best_estimator_

使用最佳模型进行预测

final_model = grid.best_estimator_
y_pred = final_model.predict(X_test)

可视化数据

fig, ax = plt.subplots(4, 6)
for i, axi in enumerate(ax.flat):axi.imshow(X_test[i].reshape(62, 47), cmap='bone')axi.set(xticks=[], yticks=[])axi.set_ylabel(faces.target_names[y_pred[i]].split()[-1], color='black' if y_pred[i] == y_test[i] # correct labelelse 'red') # incorrect labelfig.suptitle('Predicted Names; Incorrected Labels in Red', size=14);

模型评估指标

from sklearn.metrics import classification_report

print(classification_report(y_test, y_pred, target_names=faces.target_names))

                   precision    recall  f1-score   supportAriel Sharon       0.90      0.75      0.82        12Colin Powell       0.72      0.94      0.81        51Donald Rumsfeld       0.88      0.88      0.88        25George W Bush       0.97      0.88      0.92        98
Gerhard Schroeder       0.88      0.71      0.79        21Hugo Chavez       0.85      0.73      0.79        15
Junichiro Koizumi       1.00      1.00      1.00        10Tony Blair       0.90      0.92      0.91        38accuracy                           0.87       270macro avg       0.89      0.85      0.86       270weighted avg       0.89      0.87      0.88       270

from sklearn.metrics import confusion_matrixcm = confusion_matrix(y_test, y_pred)
cm = cm.Tprint(cm)

import seaborn as sns
sns.heatmap(data=cm, square=True, annot=True, cbar=False,xticklabels=faces.target_names,yticklabels=faces.target_names);plt.xlabel('True Labels')
plt.ylabel('Predicted Labels');