Getting Exception in thread "main" java.lang.ArrayIndexOutOfBoundsException while retraining the stanford sentiment RNN -


i trying retrain stanford sentiment rnn own dataset have converted ptb format using buildbinarizeddataset stanford-core-nlp jar (3.8)

here first few lines of training data:

(9 (9 (5 very) (7 well)) (5 handled))

(7 (6 engineers) (4 (4 to) (5 (6 answer) (6 (5 very) (3 carefully)))))

(9 (9 (9 (8 fast) (5 and)) (9 reliable)) (9 (4 response) (9 great)))

(8 (7 prompt) (7 (5 responses) (8 (5 fixed) (1 (4 the) (0 issue)))))

this command used :

java -cp "*"

-mx8g edu.stanford.nlp.sentiment.sentimenttraining

-gradientcheck

-trainpath train_s.txt -equivalenceclasses 0,1,2,3,4,5;6,7,8,9,10

-equivalenceclassnames negative,neutral,positive

-numhid 25

-batchsize 78

-numclasses 2

-classnames negative,positive

-train

-model modeltrial.ser.gz

and exception:

exception in thread "main" java.lang.arrayindexoutofboundsexception: 9

   @ org.ejml.data.d1matrix64f.set(unknown source)     @ org.ejml.simple.simplebase.set(unknown source)     @ edu.stanford.nlp.sentiment.sentimentcostandgradient.backpropderivativesanderror(sentimentcostandgradient.java:376)     @ edu.stanford.nlp.sentiment.sentimentcostandgradient.backpropderivativesanderror(sentimentcostandgradient.java:354)     @ edu.stanford.nlp.sentiment.sentimentcostandgradient.scorederivatives(sentimentcostandgradient.java:223)     @ edu.stanford.nlp.sentiment.sentimentcostandgradient.calculate(sentimentcostandgradient.java:249)     @ edu.stanford.nlp.optimization.abstractcachingdifffunction.ensure(abstractcachingdifffunction.java:140)     @ edu.stanford.nlp.optimization.abstractcachingdifffunction.derivativeat(abstractcachingdifffunction.java:151)     @ edu.stanford.nlp.optimization.abstractcachingdifffunction.gradientcheck(abstractcachingdifffunction.java:39)     @ edu.stanford.nlp.sentiment.sentimenttraining.rungradientcheck(sentimenttraining.java:129)     @ edu.stanford.nlp.sentiment.sentimenttraining.main(sentimenttraining.java:226)

these options working with

general options

randomseed=1659449035

wordvectors=null

unkword=unk

randomwordvectors=true

numhid=25

numclasses=2

lowercasewordvectors=false

usetensors=true

simplifiedmodel=true

combineclassification=true

classnames=negative,positive

equivalenceclasses=0,1,2,3,4,5;6,7,8,9,10

equivalenceclassnames=negative,neutral,positive

train options

batchsize=78

epochs=400

debugoutputepochs=8

maxtraintimeseconds=86400

learningrate=0.01

scalingforinit=1.0

classweights=null

regtransformmatrix=0.001

regtransformtensor=0.001

regclassification=1.0e-4

regwordvector=1.0e-4

initialadagradweight=0.0

adagradresetfrequency=1

shufflematrices=true

initialmatrixlogpath=null

nthreads=1

test options

ngramrecordsize=0

ngramrecordmaximumlength=0

printlengthaccuracies=false

my training data has around 4800 sentences. first time working stanford core nlp , far no other links have helped me.


Comments

Post a Comment

Popular posts from this blog

python - Selenium remoteWebDriver (& SauceLabs) Firefox moseMoveTo action exception -

while performing simple hover test on firefox through selenium (3.4.0) python bindings (3.4.3) using of available os in saucelabs (except linux, latest available firefox version old), performing following actionchain: hover = actionchains(driver) hover.move_to_element(elm_men_menu).perform() it throws following error: taceback: file [...] in testhover hover.perform() file "/usr/local/lib/python2.7/dist-packages/selenium/webdriver/common/action_chains.py", line 80, in perform action() file "/usr/local/lib/python2.7/dist-packages/selenium/webdriver/common/action_chains.py", line 290, in <lambda> command.move_to, {'element': to_element.id})) file "/usr/local/lib/python2.7/dist-packages/selenium/webdriver/remote/webdriver.py", line 256, in execute self.error_handler.check_response(response) file "/usr/local/lib/python2.7/...
Read more

html - How to custom Bootstrap grid height? -

why bootstrap grid has height 591.067 ? did height came ? .main-post { padding: 20px; background-color: #fff; border: 1px solid #d8d8d8; margin-bottom: 100px; } .main-post .post-categories { margin-bottom: 10px } .main-post h3 { margin: 0 0 10px; color: #777; letter-spacing: -1px; font-weight: bold } .main-post .post-author, .main-post .post-date, .main-post .post-comments { font-size: 12px } .main-post img { display: block; margin: 10px 0; } .main-post .post-summary { line-height: 1.7; color: #888 } .main-post { color: #999 } <div class="col-sm-6"> <div class="main-post"> <h3 class="post-title"> <a href="#"> post title </a> </...
Read more

transpose - Maple isnt executing function but prints function term -

im using maple im in worksheetmode tried using maple input , 2d input , want transpose matrix a: := `<|>`(`<,>`(1, .5, -2), `<,>`(.5, 9/4+b, 5+3*b), `<,>`(-2, 5+3*b, 18+9*b+4*a)); b:= transpose(a); when exectute sheet dont translated values, there same input. matrix looks same input matrix plus function term. you can see picture in following link: why arent functions executed? meanwhile b:=a^+ doing right way , transposed matrix. other functions return function body instead needed values... if using 2d input mode (the default) space you've got between transpose , bracketed (b) interpreted multiplcation. rid of such space. also, either load package @ start of document like, with(linearalgebra): before calling transpose command package, or call it's full name like, linearalgebra:-transpose(b);
Read more