Hi all, I want to learn NAB (https://github.com/numenta/NAB) recently, but have some problems when I use it. 1. My OS is ubuntu 12.04. I think I have installed NAB correctly according to README.md. But when I run the code of run.py, the random detector and skyline detector can run correctly, but numenta detector has problems. The error is showed as follows: 64: Beginning detection with numenta for artificialWithAnomaly/art_daily_nojump.csv ERR: Unknown parameter 'coincInputPoolPct' for region 'SP' of type 'py.SPRegion' Valid parameters are: stimulusThreshold columnCount potentialRadius learningMode maxBoost spatialImp topDownMode activeOutputCount breakPdb spLearningStatsStr breakKomodo inputDimensions numActiveColumnsPerInhArea minPctOverlapDutyCycle logPathOutputDense globalInhibition spInputNonZeros columnDimensions logPathInput logPathOutput localAreaDensity synPermConnected synPermInactiveDec inputWidth spVerbosity denseOutput inferenceMode dutyCyclePeriod sparseCoincidenceMatrix anomalyMode synPermActiveInc seed spOverlapDistribution minPctActiveDutyCycle spOutputNonZeros potentialPct self [/home/travis/build/numenta/nupic.core/src/nupic/engine/YAMLUtils.cpp line 279] Traceback (most recent call last): File "run.py", line 171, in <module> main(args) File "run.py", line 76, in main runner.detect(detectorConstructors) File "/newdisk/NAB/nab/runner.py", line 131, in detect self.pool.map(detectDataSet, args) File "/usr/lib/python2.7/multiprocessing/pool.py", line 227, in map return self.map_async(func, iterable, chunksize).get() File "/usr/lib/python2.7/multiprocessing/pool.py", line 528, in get raise self._value
2. I can't use data visualizer. The window of localhost:12345/nab_visualizer.html in chrome browser is like this: and it has no responce when I click the buttons. 3. What does "NAB Entry Diagram" mean mentioned in https://github.com/numenta/NAB/wiki#nab-entry-diagram? I can't open the url of "NAB Entry Diagram" and it says I need apply for access. What shoud I do? Hoping for your reply. Thank you. yajingfu
[email protected]
Description: Binary data
