深度信念网络python_PyBrain如何做深度信念网络训练？

我很难用Pybrain训练DBN。

首先我试着用简单的方法：net = buildNetwork(*layerDims)

所以我试着从头开始定义一个网络！在inp = LinearLayer(3 , 'visible')

hidden0 = SigmoidLayer(2 , 'hidden0')

hidden1= SigmoidLayer(2 , 'hidden1')

output = LinearLayer(2 , 'output')

bias = BiasUnit('bias')

net = Network()

net.addInputModule(inp)

net.addModule(hidden0)

net.addModule(hidden1)

net.addModule(output)

net.addModule(bias)

net.addConnection(FullConnection(inp, hidden0))

net.addConnection(FullConnection(hidden0, hidden1))

net.addConnection(FullConnection(hidden1, output))

net.addConnection(FullConnection(bias, hidden0))

net.addConnection(FullConnection(bias, hidden1))

net.addConnection(FullConnection(bias, output))

net.sortModules()

当我跑的时候：trainer = deepbelief.DeepBeliefTrainer(net1, dataset=ds)

trainer.trainEpochs(epochs)

我看到了这个错误：File "/home/WORK/Canopy_64bit/User/lib/python2.7/site-packages/PyBrain-0.3.1-py2.7.egg/pybrain/structure/connections/connection.py", line 37, in __init__

self.outSliceTo = outmod.indim

AttributeError: 'NoneType' object has no attribute 'indim'

这与相关RBM中的隐藏层有关。在

我是不是少了点什么？在