如何格式化Deep Belief神经网络的训练/测试集

发布时间：2020-12-20 13:06:25 所属栏目：Python 来源：网络整理

导读：我正在尝试使用实现 this page的代码.但我无法弄清楚如何正确格式化数据(训练集/测试集).我的代码： numpy_rng = numpy.random.RandomState(123) dbn = DBN(numpy_rng=numpy_rng,n_ins=2,hidden_layers_sizes=[50,50,50],n_outs=1) train_set_x = [ ([1,2],[

我正在尝试使用实现 this page的代码.但我无法弄清楚如何正确格式化数据(训练集/测试集).我的代码：

numpy_rng = numpy.random.RandomState(123)
    dbn = DBN(numpy_rng=numpy_rng,n_ins=2,hidden_layers_sizes=[50,50,50],n_outs=1)

    train_set_x = [
        ([1,2],[2,]),#first element in the tuple is the input,the second is the output
        ([4,5],[5,])
    ]

    testing_set_x = [
        ([6,1],[3,#same format as the training set
    ]

    #when I looked at the load_data function found elsewhere in the tutorial (I'll show the code they used at the bottom for ease) I found it rather confusing,but this was my first attempt at recreating what they did
    train_set_xPrime = [theano.shared(numpy.asarray(train_set_x[0][0],dtype=theano.config.floatX),borrow=True),theano.shared(numpy.asarray(train_set_x[0][1],borrow=True)]

    pretraining_fns = dbn.pretraining_functions(train_set_x=train_set_xPrime,batch_size=10,k=1)

产生了这个错误：

Traceback (most recent call last):
      File "/Users/spudzee1111/Desktop/Code/NNChatbot/DeepBeliefScratch.command",line 837,in <module>
        pretraining_fns = dbn.pretraining_functions(train_set_x=train_set_xPrime,k=1)
      File "/Users/spudzee1111/Desktop/Code/NNChatbot/DeepBeliefScratch.command",line 532,in pretraining_functions
        n_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
    AttributeError: 'list' object has no attribute 'get_value'

我无法弄清楚输入应该如何格式化.我尝试在列表中使用theano.shared,因此它将是：

train_set_xPrime = theano.shared([theano.shared(numpy.asarray(train_set_x[0][0],borrow=True)],borrow=True)

但后来它说：

Traceback (most recent call last):
      File "/Users/spudzee1111/Desktop/Code/NNChatbot/DeepBeliefScratch.command",line 834,in <module>
        train_set_xPrime = theano.shared([theano.shared(numpy.asarray(train_set_x[0][0],borrow=True) #,numpy.asarray(train_set_x[0][1],borrow=True))
      File "/Library/Frameworks/Python.framework/Versions/3.4/lib/python3.4/site-packages/theano/compile/sharedvalue.py",line 228,in shared
        (value,kwargs))
    TypeError: No suitable SharedVariable constructor could be found. Are you sure all kwargs are supported? We do not support the parameter dtype or type. value="[<TensorType(float64,vector)>,<TensorType(float64,vector)>]". parameters="{'borrow': True}"

我尝试了其他组合,但没有一个有效.

解决方法

这应该工作

numpy_rng = numpy.random.RandomState(123)
dbn = DBN(numpy_rng=numpy_rng,n_outs=1)

train_set = [
    ([1,([4,])
]

train_set_x = [train_set[i][0] for i in range(len(train_set))]
nparray = numpy.asarray(train_set_x,dtype=theano.config.floatX)
train_set_x = theano.shared(nparray,borrow=True)

pretraining_fns = dbn.pretraining_functions(train_set_x=train_set_x,k=1)

pretraining_fns方法期望作为输入的大小共享变量(样本数,输入维度).您可以通过查看MNIST数据集的形状来检查这一点,该数据集是此示例的标准输入

它不会将列表作为输入,因为此方法仅适用于预训练功能. DBN使用无监督学习算法进行预训练,因此使用标签没有意??义

此外,使您的numpy数组的输入列表没有意义. train_set_x [0] [0]仅产生第一个训练示例.您希望train_set_xPrime拥有所有培训示例.即使你做了train_set_x [0],你也会得到第一个训练样例但是有标签

（编辑：李大同）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!