search

ksenia-konyushkova / LAL

This project contains code for paper Ksenia Konyushkova, Raphael Sznitman, Pascal Fua 'Learning Active Learning from Data', NIPS 2017
Apache License 2.0
85 stars 24 forks source link

why is it invalid when running the experiment? #1

Open ycw315989786 opened 6 years ago

ycw315989786 commented 6 years ago

time

nExperiments = 20 nEstimators = 50

nStart = 2

nIterations = 100

quality_metrics = ['accuracy']

dtst = DatasetCheckerboard2x2()

dtst.setStartState(nStart)

alR = ActiveLearnerRandom(dtst, nEstimators, 'random') alU = ActiveLearnerUncertainty(dtst, nEstimators, 'uncertainty') alLALindepend = ActiveLearnerLAL(dtst, nEstimators, 'lal-rand', lalModel1) alLALiterative = ActiveLearnerLAL(dtst, nEstimators, 'lal-iter', lalModel2) als = [alR, alU, alLALindepend, alLALiterative]

exp = Experiment(nIterations, nEstimators, quality_metrics, dtst, als, 'here we can put a comment about the current experiments')

res = Results(exp, nExperiments)

for i in range(nExperiments): print('\n experiment #'+str(i+1))

performance = exp.run()
res.addPerformance(performance)

exp.reset()

print() res.saveResults('checkerboard2x2-exp')

Finally,NotFittedError: Estimator not fitted, call fit before exploiting the model. Why?can you give me some advises?

kaushikpavani commented 5 years ago

Please give full error message. I am guessing you have not run the first three blocks of the jupyter notebook.