• Keras官方Example里Mnist-cnn的调试运行


    问题:老板让测试运行Keras官网里的Mnist-cnn.py,结果从下载数据就是一路坑……

    当前环境:Ubuntu12.04、python2.7、Keras 1.1.1(不知道这个版本号对不对,在启动文件里查到的)

    按遇到问题的先后逐个出解决方案:

    1、load_data数据,下载老是报Errno 104 Connection reset by peer

    解决:

      ①因为无论是否翻墙下载都很慢,下载数据到本地并解压出pkl文件,绝对路径中不能有中文,

      ②重写数据加载函数,后面上代码,

    2、运行代码时报错:

    OverflowError: Range exceeds valid bounds
    从异常跑出的栈里看是numpy的random函数有越界,
    解决:有两种方法,就试了种简单的,另一种没试,
    文件前面初始化设置:
    from keras import backend
    backend.set_image_dim_ordering('th')
    查看具体解释。


    下面是修改后的代码:如有问题还望能评论指出,谢谢,至少现在是能跑的,
    import gzip
    
    from six.moves import cPickle
    
    from keras import backend
    backend.set_image_dim_ordering('th')
    
    batch_size = 128
    nb_classes = 10
    nb_epoch = 12
    
    # input image dimensions
    img_rows, img_cols = 28, 28
    # number of convolutional filters to use
    nb_filters = 32
    # size of pooling area for max pooling
    nb_pool = 2
    # convolution kernel size
    nb_conv = 3
    
    def load_data(path='mnist.pkl.gz'):
    #    path = get_file(path, origin='https://s3.amazonaws.com/img-datasets/mnist.pkl.gz')
        path = r'/home/wh/mnist.pkl'
    
        if path.endswith('.gz'):
            f = gzip.open(path, 'rb')
        else:
            f = open(path, 'rb')
        f = open(path, 'rb')   
        data = cPickle.load(f)
    f.close() return data # (X_train, y_train), (X_test, y_test) # the data, shuffled and split between train and test sets #(X_train, y_train), (X_test, y_test) = mnist.load_data() (X_train, y_train), (X_test, y_test) = load_data()

      

    时间戳:2016-12-5 20:50:13

      

      

  • 相关阅读:
    QString::toStdString() crashes
    Consolas 字体
    Mesh BRep Shapes
    PyOpenCL库安装
    全国精确到乡镇的行政边界、路网水系建筑poi等矢量shp免费下载
    DEM数据(ASTER GDEM|SRTM|GLS2005|ALOS DEM)下载
    IDL基础
    辐射定标与FLAASH大气校正
    Circos绘图—基础
    R-散点密度图
  • 原文地址:https://www.cnblogs.com/1394htw/p/6135456.html
Copyright © 2020-2023  润新知