人脸识别机器学习 代码分析

# -*- coding: utf-8 -*-
"""
Created on Wed Mar 27 11:01:11 2019

@author: LIHUI
"""
from __future__ import print_function
from time import time
import logging
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_lfw_people
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import PCA
from sklearn.svm import SVC
print(__doc__)
# Display progress logs on stdout
# 在标准输出上展示 下载的进度
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')
# ###################################################################
##########
# Download the data, if not already on disk and load it as numpy arrays
# 如果没有在磁盘上就下载数据集  转载数据集 按照numpy数组的形式
lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)
# introspect the images arrays to find the shapes (for plotting)
# 内省图像数组以找到形状（用于绘图）
n_samples, h, w = lfw_people.images.shape
# for machine learning we use the 2 data directly (as relative pixel
# positions info is ignored by this model)
# 对于机器学习，我们直接使用2个数据（因为此模型忽略了相对像素位置信息）
X = lfw_people.data
n_features = X.shape[1]
# the label to predict is the id of the person
# 定义预测模型的人的iD的标签
y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]
print("Total dataset size:")
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
print("n_classes: %d" % n_classes)
# 输出所有下载的信息
# ###################################################################
##########

# Split into a training set and a test set using a stratified k fold
# 使用分层k折叠分成训练集和测试集
# split into a training and testing set
# 分成训练和测试集
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.25, random_state=42)
# ###################################################################
##########
# Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
# dataset): unsupervised feature extraction / dimensionality reduction
# 计算面部数据集上的PCA（特征脸）（视为未标记的 数据集）：无监督的特征提取/降维
n_components = 150
print("Extracting the top %d eigenfaces from %d faces"
% (n_components, X_train.shape[0]))
t0 = time()
pca = PCA(n_components=n_components, svd_solver='randomized',
whiten=True).fit(X_train)
print("done in %0.3fs" % (time() - t0))
eigenfaces = pca.components_.reshape((n_components, h, w))
print("Projecting the input data on the eigenfaces orthonormal basis")
t0 = time()
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
print("done in %0.3fs" % (time() - t0))
# ###################################################################
##########
# Train a SVM classification model
# 训练 一个 svm 分类模型
print("Fitting the classifier to the training set")
t0 = time()
param_grid = {'C': [1e3, 5e3, 1e4, 5e4, 1e5],
'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1], }
clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'),
param_grid, cv=5)
clf = clf.fit(X_train_pca, y_train)
print("done in %0.3fs" % (time() - t0))
print("Best estimator found by grid search:")
print(clf.best_estimator_)
# ###################################################################
##########
# Quantitative evaluation of the model quality on the test set
# 定量评估测试集上的模型质量
print("Predicting people's names on the test set")
t0 = time()
y_pred = clf.predict(X_test_pca)
print("done in %0.3fs" % (time() - t0))
print(classification_report(y_test, y_pred, target_names=target_names))
print(confusion_matrix(y_test, y_pred, labels=range(n_classes)))
# ###################################################################
##########
# Qualitative evaluation of the predictions using matplotlib
# 使用matplotlib对预测进行定性评估
def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
  #"""Helper function to plot a gallery of portraits"""
  plt.figure(figsize=(1.8 * n_col, 2.4 * n_row))
  plt.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace =.35)
  for i in range(n_row * n_col):
    plt.subplot(n_row, n_col, i + 1)
    plt.imshow(images[i].reshape((h, w)), cmap=plt.cm.gray)
    plt.title(titles[i], size=12)
    plt.xticks(())
    plt.yticks(())
# plot the result of the prediction on a portion of the test set
# 绘制测试集的一部分上的预测结果
def title(y_pred, y_test, target_names, i):
  pred_name = target_names[y_pred[i]].rsplit(' ', 1)[-1]
  true_name = target_names[y_test[i]].rsplit(' ', 1)[-1]
  return 'predicted: %s\ntrue: %s' % (pred_name, true_name)
prediction_titles = [title(y_pred, y_test, target_names, i)
for i in range(y_pred.shape[0])]
plot_gallery(X_test, prediction_titles, h, w)
# plot the gallery of the most significative eigenfaces
# 绘制最有意义的特征脸的画廊
eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)
plt.show()