Pybrain

Question

i=0
noofclasses = 2
alldata = ClassificationDataSet(400, 1, noofclasses)
while i<len(data):
    alldata.addSample(data[i],labels[i])
    i=i+1
tstdata_temp, trndata_temp = alldata.splitWithProportion( 10 )

tstdata = ClassificationDataSet(400, 1, noofclasses) 
for n in xrange(0, tstdata_temp.getLength()):
    tstdata.addSample( tstdata_temp.getSample(n)[0], tstdata_temp.getSample(n)[1] ) 

trndata = ClassificationDataSet(400, 1, noofclasses) 

for n in xrange(0, trndata_temp.getLength()): 
    trndata.addSample( trndata_temp.getSample(n)[0], trndata_temp.getSample(n)[1] ) 

trndata._convertToOneOfMany( )
tstdata._convertToOneOfMany( )

fnn = buildNetwork( trndata.indim, 10, trndata.outdim, outclass=SoftmaxLayer )
trainer = BackpropTrainer( fnn, dataset=trndata, momentum=0.1, verbose=True, weightdecay=0.01)
trainer.trainEpochs( 20 )

我已经尝试增加 Epoch 的数量和隐藏的数量 neurons.Still 准确性没有提高。 'data' 是 400 维（20x20 图像的像素值），标签如下所示： [0,0,0,....1,1,1]

Answer 1

不好意思，加了偏置项后，准确率还不错

fnn = buildNetwork( trndata.indim, 10, trndata.outdim, bias = True, outclass=SoftmaxLayer )

Pybrain - 神经网络准确度很低

Pybrain - Neural Network Accuracy is very low

python

neural-network