SVM lfm 人脸识别

看着这个学https://www.bilibili.com/video/av54019270/?p=1

flw_数据集可能下载不成功，可以用我下载好的这个https://download.csdn.net/download/weixin_40893939/11276022，放到下载失败的那个目录下替换，就说这么多吧。。。这要是都弄不好，那就别玩了。

 

关键词：

1 rbf、gamma 和C参数：gamma值对应模型的复杂程度，越大的gamma值分类越准，但是泛化能力差。C参数意味着泛化能力越低。

2 sklearn内置lfw人脸数据集

3 pca降维

4 GridSearchCV网格搜索交叉验证选择最佳参数

5 混淆矩阵

 

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
from sklearn.datasets.samples_generator import make_blobs
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.pipeline import make_pipeline
from sklearn.datasets.samples_generator import make_circles
from sklearn.model_selection import  train_test_split

def plot_svc_decision_function(model,ax=None, plot_support=True):
    if ax is None:
        ax = plt.gca()
    xlim = ax.get_xlim()
    ylim = ax.get_ylim()

    x = np.linspace(xlim[0], xlim[1], 30)
    y = np.linspace(ylim[0], ylim[1], 30)
    Y, X = np.meshgrid(y, x)
    xy = np.vstack([X.ravel(), Y.ravel()]).T
    P = model.decision_function(xy).reshape(X.shape)

    ax.contour(X, Y, P, colors='k',
               levels=[-1, 0, 1], alpha=0.5,
               linestyles=['--', '--', '--'])

    if plot_support:
        ax.scatter(model.support_vectors_[:, 0],
                   model.support_vectors_[:, 1],
                   s=300, linewidth=1, facecolors='none')
    ax.set_xlim(xlim)
    ax.set_ylim(ylim)

def linear():
    x,y = make_blobs(n_samples=50,centers = 2,random_state=0,cluster_std=0.6)
    model = SVC(kernel='linear')
    model.fit(x,y)
    plt.scatter(x[:, 0], x[:, 1], c=y, s=50, cmap='autumn')
    plot_svc_decision_function(model)
    plt.show()

def kernel():
    x,y = make_circles(1000,factor=.1,noise =.1)
    clf = SVC(kernel='rbf',C=1E6)
    clf.fit(x,y)
    plt.scatter(x[:,0],x[:,1],c=y,s=50,cmap='autumn')

    plot_svc_decision_function(clf)
    plt.scatter(clf.support_vectors_[:,0],clf.support_vectors_[:,1],s=3,lw=1,facecolors ='none')
    plt.show()


def face():
    from sklearn.datasets import fetch_lfw_people
    faces = fetch_lfw_people(min_faces_per_person=60)
    print(faces.target_names)
    print(faces.images.shape)

    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]])
    plt.show()
    pca  = PCA(n_components=150,whiten = True,random_state=42)
    svc = SVC(kernel ='rbf',class_weight='balanced')
    model = make_pipeline(pca,svc)#make_pipeline函数是Pipeline类的简单实现，只需传入每个step的类实例即可，不需自己命名
    xtrain,xtest,ytrain,ytest =train_test_split(faces.data,faces.target,random_state=40)


    from sklearn.model_selection import GridSearchCV
    param_grid= {'svc__C':[1,5,10],'svc__gamma':[0.0001,0.0005,0.001]}
    grid =GridSearchCV(model,param_grid)
    grid_result =grid.fit(xtrain,ytrain)
    print(grid_result.best_params_)


    model = grid.best_estimator_
    yfit = model.predict(xtest)
    print(yfit.shape)

    fig, ax = plt.subplots(4, 6)
    for i, axi in enumerate(ax.flat):
        axi.imshow(xtest[i].reshape(62,47), cmap='bone')
        axi.set(xticks=[],yticks =[])
        axi.set_ylabel(faces.target_names[yfit[i]].split()[-1],color ='black'
                if yfit[i] == ytest[i] else 'red')
    fig.suptitle('Predicted Names:Incorrect Labels in Red',size=14)
    plt.show()

    from sklearn.metrics import classification_report
    print(classification_report(ytest,yfit,target_names=faces.target_names))


    from sklearn.metrics import confusion_matrix
    mat = confusion_matrix(ytest,yfit)
    sns.heatmap(mat.T,square=True,annot=True,fmt='d',cbar=False,
                xticklabels=faces.target_names,
                yticklabels=faces.target_names)
    plt.xlabel('true label')
    plt.ylabel('predicted label')
    plt.show()

linear()
kernel()
face()