• 概述

神經(jīng)網(wǎng)路顧名思義將生物的神經(jīng)系統(tǒng)中的興奮與抑制比作計(jì)算機(jī)中的0和1

知識(shí)點(diǎn)：

1. 神經(jīng)網(wǎng)絡(luò)原理
2. 神經(jīng)網(wǎng)絡(luò)中的非線性矯正
3. 神經(jīng)網(wǎng)絡(luò)參數(shù)設(shè)置

• 參數(shù)設(shè)置

重要參數(shù)：

activation：隱藏單元進(jìn)行非線性化的方法，一共4總：identity，logistic，tanh，relu

alpha：正則化參數(shù)，默認(rèn)為0.0001，參數(shù)越大算法越簡(jiǎn)單

hidden_layer_size:設(shè)置隱藏層的結(jié)點(diǎn)和層數(shù)：[10,10]表示2層，每層結(jié)點(diǎn)為10? ? ? ?

?

• 圖像分析

            
              import numpy as np
from sklearn.neural_network import MLPClassifier
from sklearn.datasets import load_wine

from sklearn.model_selection import train_test_split
wine = load_wine()
X = wine.data[:,:2]#只取前2個(gè)屬性
y = wine.target
X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=0)

mlp = MLPClassifier(solver = 'lbfgs',hidden_layer_sizes=[100,100],activation='tanh',alpha=1)
mlp.fit(X_train,y_train)

import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap

cmap_light = ListedColormap(['#FFAAAA','#AAFFAA','#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000','#00FF00','#0000FF'])
                            
x_min, x_max = X[:,0].min() -1,X[:,0].max()+1
y_min, y_max = X[:,1].min() -1,X[:,1].max()+1
xx,yy = np.meshgrid(np.arange(x_min,x_max,.02),np.arange(y_min,y_max,.02))
z = mlp.predict(np.c_[xx.ravel(),yy.ravel()])
z = z.reshape(xx.shape)

plt.figure()
plt.pcolormesh(xx,yy,z,cmap=cmap_light)

plt.scatter(X[:,0],X[:,1],c=y,cmap=cmap_bold,edgecolor='k',s=20)
plt.xlim(xx.min(),xx.max())
plt.ylim(yy.min(),yy.max())

plt.show()

print("訓(xùn)練得分：{:.2f}".format(mlp.score(X_train,y_train)))
print("測(cè)試得分：{:.2f}".format(mlp.score(X_test,y_test)))
            
          

通過(guò)內(nèi)置紅酒數(shù)據(jù)集可畫出神經(jīng)網(wǎng)絡(luò)算法圖：

將正則化參數(shù)恢復(fù)為默認(rèn)后：

mlp = MLPClassifier(solver = 'lbfgs',hidden_layer_sizes=[100,100],activation='tanh')

可見參數(shù)對(duì)效果的影響。

?

• 實(shí)例--手寫識(shí)別

使用內(nèi)置數(shù)據(jù)集“l(fā)oad_digits

查看參數(shù):

            
              print(digits.keys())#數(shù)據(jù)集中的建
print(digits.data[0])#第一個(gè)數(shù)據(jù)
print(digits.target[0])#第一個(gè)數(shù)據(jù)的類型
print(digits.DESCR)#描述
            
          

            
              dict_keys(['data', 'target', 'target_names', 'images', 'DESCR'])
[ 0.  0.  5. 13.  9.  1.  0.  0.  0.  0. 13. 15. 10. 15.  5.  0.  0.  3.
 15.  2.  0. 11.  8.  0.  0.  4. 12.  0.  0.  8.  8.  0.  0.  5.  8.  0.
  0.  9.  8.  0.  0.  4. 11.  0.  1. 12.  7.  0.  0.  2. 14.  5. 10. 12.
  0.  0.  0.  0.  6. 13. 10.  0.  0.  0.]
0
.. _digits_dataset:

Optical recognition of handwritten digits dataset
--------------------------------------------------

**Data Set Characteristics:**

    :Number of Instances: 5620
    :Number of Attributes: 64
    :Attribute Information: 8x8 image of integer pixels in the range 0..16.
    :Missing Attribute Values: None
    :Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)
    :Date: July; 1998

This is a copy of the test set of the UCI ML hand-written digits datasets
https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits

The data set contains images of hand-written digits: 10 classes where
each class refers to a digit.

Preprocessing programs made available by NIST were used to extract
normalized bitmaps of handwritten digits from a preprinted form. From a
total of 43 people, 30 contributed to the training set and different 13
to the test set. 32x32 bitmaps are divided into nonoverlapping blocks of
4x4 and the number of on pixels are counted in each block. This generates
an input matrix of 8x8 where each element is an integer in the range
0..16. This reduces dimensionality and gives invariance to small
distortions.

For info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G.
T. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C.
L. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469,
1994.

.. topic:: References

  - C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their
    Applications to Handwritten Digit Recognition, MSc Thesis, Institute of
    Graduate Studies in Science and Engineering, Bogazici University.
  - E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.
  - Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.
    Linear dimensionalityreduction using relevance weighted LDA. School of
    Electrical and Electronic Engineering Nanyang Technological University.
    2005.
  - Claudio Gentile. A New Approximate Maximal Margin Classification
    Algorithm. NIPS. 2000.
            
          

通過(guò)描述幸喜可以發(fā)現(xiàn)圖片為8*8的大小

完整代碼：

            
              #MNIST數(shù)據(jù)集
from sklearn.datasets import load_digits
digits = load_digits()
X=digits.data
y=digits.target
X_train,X_test,y_train,y_test = train_test_split(X,y,random_state=0)

mlp = MLPClassifier(solver = 'lbfgs',hidden_layer_sizes=[100,100],activation='relu',random_state=62)
mlp.fit(X_train,y_train)

print(X_train.shape,y_train.shape,X_test.shape,y_test.shape)
print("訓(xùn)練得分：{:.2f}".format(mlp.score(X_train,y_train)))
print("測(cè)試得分：{:.2f}".format(mlp.score(X_test,y_test)))
#導(dǎo)入圖像處理工具
from PIL import Image

image = Image.open('1.png').convert('F')
image = image.resize((8,8))
arr = []

for i in range(8):
    for j in range(8):
        pixel = 1.0 - float(image.getpixel((j,i)))/255
        arr.append(pixel)
        
arr1 = np.array(arr).reshape(1,-1)

for i in range(10):
    print('{}的概率為：{}'.format(i,mlp.predict_proba(arr1)[0][i]))
print('結(jié)果為：{}'.format(mlp.predict(arr1)[0]))