def test_idx2seq_shape(self):
b = idx2seq(encdim=self.encdim,
invocsize=self.numwords,
outvocsize=self.numchars,
seqlen=self.seqlen,
innerdim=self.innerdim)
data = np.random.randint(0, self.numwords, (self.batsize, ))
pdata = np.random.randint(0, self.numchars,
(self.batsize, self.seqlen))
p = b.predict(data, pdata)
self.assertEqual(p.shape, (self.batsize, self.seqlen, self.numchars))
def setUp(self):
wreg = 0.001
epochs = 3
numbats = 10
lr = 0.1
statedim = 70
encdim = 70
# get words
numchars = 27
embdim = 50
Glove.defaultpath = "../../../data/glove/miniglove.%dd.txt"
lm = Glove(embdim, 1000)
words = filter(lambda x: re.match("^[a-z]+$", x), lm.D.keys())
data = words2ints(words)
sdata = shiftdata(data)
wordidxs = np.arange(0, len(words))
numwords = wordidxs.shape[0]
print "random seq neg log prob %.3f" % math.log(numchars**
data.shape[1])
testneglogprob = 17
print "%.2f neg log prob for a whole sequence is %.3f prob per slot" % (
testneglogprob, math.exp(-testneglogprob * 1. / data.shape[1]))
testpred = wordidxs[:15]
testdata = data[:15]
testsdata = sdata[:15]
print testpred
print testdata
print testsdata
#testpred = words2ints(testpred)
block = idx2seq(encdim=encdim,
invocsize=numwords,
outvocsize=numchars,
innerdim=statedim,
seqlen=data.shape[1])
print np.argmax(block.predict(testpred, testsdata), axis=2)
self.block_before_training_frozen = block.freeze()
block.train([wordidxs, sdata], data).seq_cross_entropy().grad_total_norm(0.5).adagrad(lr=lr).l2(wreg)\
.autovalidate().seq_accuracy().validinter(5)\
.train(numbats=numbats, epochs=epochs)
self.block_after_training_frozen = block.freeze()
pred = block.predict(testpred, testsdata)
def setUp(self):
wreg=0.001
epochs=3
numbats=10
lr=0.1
statedim=70
encdim=70
# get words
numchars = 27
embdim = 50
Glove.defaultpath = "../../../data/glove/miniglove.%dd.txt"
lm = Glove(embdim, 1000)
words = filter(lambda x: re.match("^[a-z]+$", x), lm.D.keys())
data = words2ints(words)
sdata = shiftdata(data)
wordidxs = np.arange(0, len(words))
numwords = wordidxs.shape[0]
print "random seq neg log prob %.3f" % math.log(numchars**data.shape[1])
testneglogprob = 17
print "%.2f neg log prob for a whole sequence is %.3f prob per slot" % (testneglogprob, math.exp(-testneglogprob*1./data.shape[1]))
testpred = wordidxs[:15]
testdata = data[:15]
testsdata = sdata[:15]
print testpred
print testdata
print testsdata
#testpred = words2ints(testpred)
block = idx2seq(encdim=encdim, invocsize=numwords, outvocsize=numchars, innerdim=statedim, seqlen=data.shape[1])
print np.argmax(block.predict(testpred, testsdata), axis=2)
self.block_before_training_frozen = block.freeze()
block.train([wordidxs, sdata], data).seq_cross_entropy().grad_total_norm(0.5).adagrad(lr=lr).l2(wreg)\
.autovalidate().seq_accuracy().validinter(5)\
.train(numbats=numbats, epochs=epochs)
self.block_after_training_frozen = block.freeze()
pred = block.predict(testpred, testsdata)
def test_idx2seq_shape(self):
b = idx2seq(encdim=self.encdim, invocsize=self.numwords, outvocsize=self.numchars, seqlen=self.seqlen, innerdim=self.innerdim)
data = np.random.randint(0, self.numwords, (self.batsize, ))
pdata = np.random.randint(0, self.numchars, (self.batsize, self.seqlen))
p = b.predict(data, pdata)
self.assertEqual(p.shape, (self.batsize, self.seqlen, self.numchars))