zoukankan      html  css  js  c++  java
  • 数据分析之KNN数字识别手写

    import numpy as np
    # bmp 图片后缀
    import matplotlib.pyplot as plt
    %matplotlib inline
    
    from sklearn.neighbors import KNeighborsClassifier

      提炼样本数据

    img_arr = plt.imread('./data/3/3_100.bmp')
    plt.imshow(img_arr)

      读出所有的数据

    feature = []
    target = []
    for i in range(0,10):
        for j in range(1,501):
            img_path = './data/'+str(i)+'/'+str(i)+'_'+str(j+1)+'.bmp'
            img_arr = plt.imread(img_path)
            feature.append(img_arr)
            target.append(i)

      样本数据的提取

    feature = np.array(featrue)
    target = np.array(target)
    feature.shape
    
    target.shape
    #feature是一个三维数组(执行将维操作)
    feature = feature.reshape(5000,28*28)
    
    feature.shape

      将样本数据打乱

    np.random.seed(3)
    np.random.shuffle(feature)
    np.random.seed(3)
    np.random.shuffle(target)

      获取训练数据和测试数据

    x_train = feature[:4950]
    y_train = target[:4950]
    x_test = feature[-50:]
    y_test = target[-50:]

      实例化模型对象,训练

    knn = KNeighborsClassifier(n_neighbors=30)
    knn.fit(x_train,y_train)
    knn.score(x_train,y_train)

      

    print('预测分类:',knn.predict(x_test))
    print('真实数据:',y_test)

      模型的保存

    from sklearn.externals import joblib
    
    joblib.dump(knn,"./knn.m"

      读取模型

    knn = joblib.load("./knn.m")

      让模型进行外部图片的识别

    img_arr = plt.imread('./数字.jpg')
    plt.imshow(img_arr)

      利用切片取值

    five_arr = img_arr[95:150,85:1305]
    plt.imshow(new_arr)
    #five数组是三维的,需要进行降维,舍弃第三个表示颜色的维度
    five_arr = five_arr.mean(axis=2)
    five_arr.shape

     

    import scipy.ndimage as ndimage
    five = ndimage.zoom(five_arr,zoom = (28/65,28/55))
    knn.predict(five.reshape(1,784))
  • 相关阅读:
    毕设进度21
    毕设进度20
    Javascript高级程序设计第三版-笔记
    前端踩过的坑
    thinkphp笔记
    PHP 发邮件《转》
    smarty笔记
    jquery笔记
    JS笔记
    php万年历
  • 原文地址:https://www.cnblogs.com/chenxi67/p/10511429.html
Copyright © 2011-2022 走看看