def get_trained_ann(dataset, ann=None, test_train_prop=0.25, max_epochs=50):
tstdata, trndata = dataset.splitWithProportion(test_train_prop)
trndata._convertToOneOfMany()
tstdata._convertToOneOfMany()
if not ann:
ann = build_ann(trndata.indim, trndata.outdim)
# ann = build_exp_ann(trndata.indim, trndata.outdim)
# trainer = RPropMinusTrainer(ann)
trainer = BackpropTrainer(ann, dataset=trndata,learningrate=0.01, momentum=0.5, verbose=True)
trnresult = tstresult = 0
# for i in range(10):
trainer.trainUntilConvergence(maxEpochs=max_epochs, verbose=True)
trnresult = percentError( trainer.testOnClassData(), trndata['class'] )
tstresult = percentError( trainer.testOnClassData(dataset=tstdata ), tstdata['class'] )
# print trnresult, tstresult
return ann, trnresult, tstresult
def get_trained_ann(dataset, ann=None, test_train_prop=0.25, max_epochs=50):
tstdata, trndata = dataset.splitWithProportion(test_train_prop)
trndata._convertToOneOfMany()
tstdata._convertToOneOfMany()
if not ann:
ann = build_ann(trndata.indim, trndata.outdim)
# ann = build_exp_ann(trndata.indim, trndata.outdim)
# trainer = RPropMinusTrainer(ann)
trainer = BackpropTrainer(ann,
dataset=trndata,
learningrate=0.01,
momentum=0.5,
verbose=True)
trnresult = tstresult = 0
# for i in range(10):
trainer.trainUntilConvergence(maxEpochs=max_epochs, verbose=True)
trnresult = percentError(trainer.testOnClassData(), trndata['class'])
tstresult = percentError(trainer.testOnClassData(dataset=tstdata),
tstdata['class'])
# print trnresult, tstresult
return ann, trnresult, tstresult
# 将数据扁平化
X = datasets.reshape((datasets.shape[0], datasets.shape[1] * datasets.shape[2]))
X_train ,X_test, y_train, y_test = train_test_split(X, y, train_size=0.9)
# 添加数据到数据格式中
training =SupervisedDataSet(X.shape[1], y.shape[1])
for i in range(X_train.shape[0]):
training.addSample(X_train[i], y_train[i])
testing = SupervisedDataSet(X.shape[1], y.shape[1])
for i in range(X_test.shape[0]):
testing.addSample(X_test[i], y_test[i])
# 搭建三层网络
net = buildNetwork(X.shape[1], 150, y.shape[1] ,bias=True)
# 使用BP算法
trainer = BackpropTrainer(net, training ,weightdecay=0.01)
# 训练步数
trainer.trainEpochs(epochs=50)
# 保存模型
# model_filename = open('CAPTCHA_predictor.model','wb')
# pickle.dump(trainer,model_filename,0)
# model_filename.close()
predictions = trainer.testOnClassData(dataset=testing)
from sklearn.metrics import f1_score,classification_report
print(classification_report(y_test.argmax(axis=1), predictions))
trainer = BackpropTrainer(fnn, dataset=traindata, momentum=0.1, verbose=True, weightdecay=0.01)
ticks = arange(-3., 6., 0.2)
X, Y = meshgrid(ticks, ticks)
griddata = ClassificationDataSet(2, 1, nb_classes=3)
for i in range(X.size):
griddata.addSample([X.ravel()[i],Y.ravel()[i]], [0])
griddata._convertToOneOfMany()
for i in range(20):
trainer.trainEpochs(1) # usually 5
trainresult = percentError(trainer.testOnClassData(), traindata["class"])
testresult = percentError(trainer.testOnClassData(), testdata["class"])
print("epoch %4d" % trainer.totalepochs, "trainerror %5.2f%%" % trainresult, "testerror %5.2f%%" % testresult)
out = fnn.activateOnDataset(griddata)
out = out.argmax(axis=1)
out = out.reshape(X.shape)
figure(1)
# might be the wrong import for the following lines
ioff()
clf()
hold(True)
for c in [0,1,2]:
here, _ = where(testdata["class"]==c)
irisData = datasets.load_iris()
dataFeatures = irisData.data
dataTargets = irisData.target
#plt.matshow(irisData.images[11], cmap=cm.Greys_r)
#plt.show()
#print dataTargets[11]
#print dataFeatures.shape
dataSet = ClassificationDataSet(4, 1 , nb_classes=3)
for i in range(len(dataFeatures)):
dataSet.addSample(np.ravel(dataFeatures[i]), dataTargets[i])
trainingData, testData = splitWithProportion(dataSet,0.7)
trainingData._convertToOneOfMany()
testData._convertToOneOfMany()
neuralNetwork = buildNetwork(trainingData.indim, 7, trainingData.outdim, outclass=SoftmaxLayer)
trainer = BackpropTrainer(neuralNetwork, dataset=trainingData, momentum=0.01, learningrate=0.05, verbose=True)
trainer.trainEpochs(10000)
print('Error (test dataset): ' , percentError(trainer.testOnClassData(dataset=testData), testData['class']))
print('\n\n')
counter = 0
for input in dataFeatures:
print(counter," output is according to the NN: ", neuralNetwork.activate(input))
counter = counter + 1
alldata = ClassificationDataSet(dim, 1, nb_classes=2)
(data,label,items) = BinReader.readData(ur'F:\AliRecommendHomeworkData\1212新版\train15_17.expand.samp.norm.bin')
#(train,label,data) = BinReader.readData(r'C:\data\small\norm\train1217.bin')
for i in range(len(data)):
alldata.addSample(data[i],label[i])
tstdata, trndata = alldata.splitWithProportion(0.25)
trainer = BackpropTrainer(n,trndata,momentum=0.1,verbose=True,weightdecay=0.01)
print 'start'
#trainer.trainEpochs(1)
trainer.trainUntilConvergence(maxEpochs=2)
trnresult = percentError(trainer.testOnClassData(),trndata['class'])
tstresult = percentError(trainer.testOnClassData(dataset=tstdata), tstdata['class'])
print "epoch: %4d" % trainer.totalepochs, \
" train error: %5.2f%%" % trnresult, \
" test error: %5.2f%%" % tstresult
print 'get result'
#trainer.trainUntilConvergence()
#out = ClassificationDataSet(37,1)
#(test,label,items) = BinReader.readData(r'C:\data\homework\1218t5w.bin')
##(test,label,data) = BinReader.readData(r'C:\data\small\norm\test1218.bin')
#for i in range(len(test)):
# temp = [0]
test.addSample(test_t.getSample(k)[0], test_t.getSample(k)[1])
for k in xrange(0, training_t.getLength()):
training.addSample(training_t.getSample(k)[0], training_t.getSample(k)[1])
print(training.getLength())
print(test.getLength())
print(test.indim)
print(test.outdim)
print(training.indim)
print(training.outdim)
fnn = buildNetwork(training.indim, 64, training.outdim, outclass=SoftmaxLayer)
trainer = BackpropTrainer(fnn,
dataset=training,
momentum=0.1,
learningrate=0.01,
verbose=True,
weightdecay=0.01)
trainer.trainEpochs(10)
print(percentError(trainer.testOnClassData(), training['class']))
print(percentError(trainer.testOnClassData(dataset=test), test['class']))
plt.imshow(digits.images[0], cmap=plt.cm.gray_r, interpolation='nearest')
plt.show()
for i in range(0, 10):
print(fnn.activate(X[i]))
