# 问题1、
ModuleNotFoundError: No module named ‘sklearn.cross_validation’

这个错是导入

from sklearn.cross_validation import train_test_split

报的错。主要是因为这个模块有更改，将这一句改为下面即可：

from sklearn.model_selection import train_test_split

问题2、

ModuleNotFoundError: No module named ‘sklearn.grid_search’
这个是由于导入

from sklearn.grid_search import GridSearchCV

报的错，需要将此句改为：

from sklearn.model_selection import GridSearchCV

问题3、

ImportError: cannot import name ‘RandomizedPCA’
需要将此句改为下面这句即可：

from sklearn.decomposition import PCA as RandomizedPCA

问题4、

ValueError: min_faces_per_person=70 is too restrictive

这个是因为有数据没有下载完整而报的错误，下载到的目录（我的是window系统，在）下载好复制到这个目录就行，必须先将lfw_home目录下所有内容删除，再运行即可。

C:\Users\自己的用户名字\scikit_learn_data\lfw_home

可以手动下载下面这几个，将不完整的删除。
https://ndownloader.figshare.com/files/5976018 #lfw.tgz
https://ndownloader.figshare.com/files/5976015 #lfw-funneled.tgz
https://ndownloader.figshare.com/files/5976012 #pairsDevTrain.txt
https://ndownloader.figshare.com/files/5976009 #pairsDevTest.txt
https://ndownloader.figshare.com/files/5976006 #pairs.txt

问题5、

ValueError: class_weight must be dict, ‘balanced’, or None, got: ‘auto’

定位到是这一句：

clf = GridSearchCV(SVC(kernel='rbf', class_weight='auto'), param_grid)

意思是需要的需要是个字典，字典必须是 ‘balanced’, or None，却得到了‘auto’，所以需要改为：

clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)

或者

clf = GridSearchCV(SVC(kernel='rbf', class_weight=None), param_grid)

到此结束了。

问题6、

FutureWarning: You should specify a value for ‘cv’ instead of relying on the default value. The default value will change from 3 to 5 in version 0.22.
warnings.warn(CV_WARNING, FutureWarning)
能够运行，但是却有这个警告，The default value will change from 3 to 5 in version 0.22.这个意思默认cv改为3至5，经过测试，cv为3，4，5都可以。

clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)

这一句，加个参数即可，

clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid,cv=4)

下面是默认的cv=’warn’.

{% image /imgs/20190409101355250.png '在这里插入图片描述' '' %}

完整代码：

官方完整代码：
https://scikit-learn.org/stable/auto_examples/applications/plot_face_recognition.html#sphx-glr-auto-examples-applications-plot-face-recognition-py

from __future__ import print_function

from time import time
import logging
import matplotlib.pyplot as plt

# from sklearn.cross_validation import train_test_split
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_lfw_people
# from sklearn.grid_search import GridSearchCV
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
# from sklearn.decomposition import RandomizedPCA
from sklearn.decomposition import PCA as RandomizedPCA
from sklearn.svm import SVC


print(__doc__)

# Display progress logs on stdout
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')


###############################################################################
# Download the data, if not already on disk and load it as numpy arrays

lfw_people = fetch_lfw_people(min_faces_per_person=70, resize=0.4)

# introspect the images arrays to find the shapes (for plotting)
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)
X = lfw_people.data
n_features = X.shape[1]

# the label to predict is the id of the person
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)


###############################################################################
# Split into a training set and a test set using a stratified k fold

# split into a training and testing set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25)


###############################################################################
# Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
# dataset): unsupervised feature extraction / dimensionality reduction
n_components = 150

print("Extracting the top %d eigenfaces from %d faces"
      % (n_components, X_train.shape[0]))
t0 = time()
pca = RandomizedPCA(n_components=n_components, 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

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='auto'), param_grid)
clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)
clf = GridSearchCV(SVC(kernel='rbf', class_weight=None), param_grid)
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

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

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

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 r'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

eigenface_titles = ["eigenface %d" % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)

plt.show()

scikit-learn 关于svm进行人脸识别使用报错的问题

2019-04-09
python模块
scikit_learn

scikit-learn 关于svm进行人脸识别使用报错的问题

问题2、

问题3、

问题4、

问题5、

问题6、

完整代码：

scikit-learn 关于svm进行人脸识别使用报错的问题

问题2、

问题3、

问题4、

问题5、

问题6、

完整代码：

谢谢大爷~