def test_memory_block_with_glove_embedder_params(self):
payload = WordEmbedGlove()
original_embedding = payload.predict([6])
memb = MemoryBlock(payload, np.asarray([1, 2, 6]), outdim=payload.outdim)
memory_embedding = memb.predict([2])
self.assertTrue(np.allclose(original_embedding, memory_embedding))
print memb.output.allparams
def test_memory_block_with_glove_embedder(self):
payload = WordEmbedGlove()
original_embedding = payload.predict([6])
memb = MemoryBlock(payload,
np.asarray([1, 2, 6]),
outdim=payload.outdim)
memory_embedding = memb.predict([2])
self.assertTrue(np.allclose(original_embedding, memory_embedding))
def test_memory_block_with_seq_encoder_dynamic_fail(self):
invocabsize = 5
encdim = 13
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(IdxToOneHot(vocsize=invocabsize), gru)
dynmemb = MemoryBlock(payload, outdim=encdim)
idxs = [0, 2, 5]
#dynmemb.predict(idxs)
self.assertRaises(AssertionError, lambda: dynmemb.predict(idxs))
def test_memory_block_with_seq_encoder_static_fail(self):
invocabsize = 5
memsize = 10
seqlen = 3
encdim = 13
data = np.random.randint(0, invocabsize, (memsize, seqlen))
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(IdxToOneHot(vocsize=invocabsize), gru)
memb = MemoryBlock(payload, data, outdim=encdim)
idxs = [0, 2, 5]
self.assertRaises(AssertionError, lambda: memb.predict(idxs, data))
def test_memory_block_with_seq_encoder_dynamic_fail(self):
invocabsize = 5
encdim = 13
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(
IdxToOneHot(vocsize=invocabsize),
gru
)
dynmemb = MemoryBlock(payload, outdim=encdim)
idxs = [0, 2, 5]
#dynmemb.predict(idxs)
self.assertRaises(AssertionError, lambda: dynmemb.predict(idxs))
def test_memory_block_with_seq_encoder_static_fail(self):
invocabsize = 5
memsize = 10
seqlen = 3
encdim = 13
data = np.random.randint(0, invocabsize, (memsize, seqlen))
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(
IdxToOneHot(vocsize=invocabsize),
gru
)
memb = MemoryBlock(payload, data, outdim=encdim)
idxs = [0, 2, 5]
self.assertRaises(AssertionError, lambda: memb.predict(idxs, data))
def test_memory_block_with_seq_encoder(self):
invocabsize = 5
memsize = 10
seqlen = 3
encdim = 13
data = np.random.randint(0, invocabsize, (memsize, seqlen))
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(IdxToOneHot(vocsize=invocabsize), gru)
memb = MemoryBlock(payload, data, indim=invocabsize, outdim=encdim)
idxs = [0, 2, 5]
memory_element = memb.predict(idxs)
self.assertEqual(memory_element.shape, (len(idxs), encdim))
gruparams = set([getattr(gru, pname) for pname in gru.paramnames])
allparams = set(memb.output.allparams)
self.assertEqual(gruparams.intersection(allparams), allparams)
def init(self):
#memory
wencpg = WordEncoderPlusGlove(numchars=self.numchars, numwords=self.numwords, encdim=self.wordencdim, embdim=self.wordembdim, embtrainfrac=0.0, glovepath=self.glovepath)
self.memenco = SeqEncoder(
wencpg,
GRU(dim=self.wordembdim + self.wordencdim, innerdim=self.encinnerdim)
)
entemb = VectorEmbed(indim=self.outdim, dim=self.entembdim)
self.mempayload = ConcatBlock(entemb, self.memenco)
self.memblock = MemoryBlock(self.mempayload, self.memdata, indim=self.outdim, outdim=self.encinnerdim+self.entembdim)
#encoder
wencpg2 = WordEncoderPlusGlove(numchars=self.numchars, numwords=self.numwords, encdim=self.wordencdim, embdim=self.wordembdim, embtrainfrac=0.0, glovepath=self.glovepath)
self.enc = SeqEncoder(
wencpg2,
GRU(dim=self.wordembdim + self.wordencdim, innerdim=self.encinnerdim)
)
#decoder
entemb2 = VectorEmbed(indim=self.outdim, dim=self.entembdim)
self.softmaxoutblock = stack(self.memaddr(self.memblock, indim=self.decinnerdim, memdim=self.memblock.outdim, attdim=self.attdim), Softmax())
self.dec = SeqDecoder(
[entemb2, #self.memblock,
GRU(dim=entemb.outdim + self.encinnerdim, innerdim=self.decinnerdim), # GRU(dim=self.memblock.outdim + self.encinnerdim, innerdim=self.decinnerdim),
],
inconcat=True,
innerdim=self.decinnerdim,
softmaxoutblock=self.softmaxoutblock
)
def test_memory_block_with_seq_encoder(self):
invocabsize = 5
memsize = 10
seqlen = 3
encdim = 13
data = np.random.randint(0, invocabsize, (memsize, seqlen))
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(
IdxToOneHot(vocsize=invocabsize),
gru
)
memb = MemoryBlock(payload, data, indim=invocabsize, outdim=encdim)
idxs = [0, 2, 5]
memory_element = memb.predict(idxs)
self.assertEqual(memory_element.shape, (len(idxs), encdim))
gruparams = set([getattr(gru, pname) for pname in gru.paramnames])
allparams = set(memb.output.allparams)
self.assertEqual(gruparams.intersection(allparams), allparams)
def __init__(
self,
entembdim=50,
wordembdim=50,
wordencdim=100,
memdata=None,
attdim=100,
numchars=128, # number of different chars
numwords=4e5, # number of different words
glovepath=None,
innerdim=100, # dim of memory payload encoder output
outdim=1e4, # number of entities
memaddr=DotMemAddr,
**kw):
super(FBMemMatch, self).__init__(**kw)
self.wordembdim = wordembdim
self.wordencdim = wordencdim
self.entembdim = entembdim
self.attdim = attdim
self.encinnerdim = innerdim
self.outdim = outdim
memaddr = TransDotMemAddr
# memory encoder per word
#wencpg = WordEmbed(indim=numwords, outdim=self.wordembdim, trainfrac=1.0)
wordencoder = WordEncoderPlusGlove(numchars=numchars,
numwords=numwords,
encdim=self.wordencdim,
embdim=self.wordembdim,
embtrainfrac=0.0,
glovepath=glovepath)
# memory encoder for one cell
self.phraseencoder = SeqEncoder(
wordencoder,
GRU(dim=self.wordembdim + self.wordencdim,
innerdim=self.encinnerdim))
# entity embedder
entemb = VectorEmbed(indim=self.outdim, dim=self.entembdim)
self.entembs = entemb(
memdata[0]) #Val(np.arange(0, self.outdim, dtype="int32")))
# memory block
self.mempayload = self.phraseencoder #ConcatBlock(entemb, self.phraseencoder)
self.memblock = MemoryBlock(
self.mempayload,
memdata[1],
indim=self.outdim,
outdim=self.encinnerdim) # + self.entembdim)
# memory addressing
self.mema = memaddr(self.memblock,
memdim=self.memblock.outdim,
attdim=attdim,
indim=self.encinnerdim)
def init(self):
#MEMORY: encodes how entity is written + custom entity embeddings
wencpg = WordEncoderPlusGlove(numchars=self.numchars,
numwords=self.numwords,
encdim=self.wordencdim,
embdim=self.wordembdim,
embtrainfrac=0.0,
glovepath=self.glovepath)
self.memenco = SeqEncoder(
wencpg,
GRU(dim=self.wordembdim + self.wordencdim,
innerdim=self.encinnerdim))
entemb = VectorEmbed(indim=self.outdim, dim=self.entembdim)
self.mempayload = ConcatBlock(entemb, self.memenco)
self.memblock = MemoryBlock(self.mempayload,
self.memdata,
indim=self.outdim,
outdim=self.encinnerdim + self.entembdim)
#ENCODER: uses the same language encoder as memory
#wencpg2 = WordEncoderPlusGlove(numchars=self.numchars, numwords=self.numwords, encdim=self.wordencdim, embdim=self.wordembdim, embtrainfrac=0.0, glovepath=glovepath)
self.enc = RecStack(
wencpg,
GRU(dim=self.wordembdim + self.wordencdim,
innerdim=self.encinnerdim))
#ATTENTION
attgen = LinearGateAttentionGenerator(indim=self.encinnerdim +
self.decinnerdim,
innerdim=self.attdim)
attcon = WeightedSumAttCon()
#DECODER
#entemb2 = VectorEmbed(indim=self.outdim, dim=self.entembdim)
self.softmaxoutblock = stack(
self.memaddr(self.memblock,
indim=self.decinnerdim + self.encinnerdim,
memdim=self.memblock.outdim,
attdim=self.attdim), Softmax())
self.dec = SeqDecoder([
self.memblock,
GRU(dim=self.entembdim + self.encinnerdim,
innerdim=self.decinnerdim)
],
outconcat=True,
inconcat=False,
attention=Attention(attgen, attcon),
innerdim=self.decinnerdim + self.encinnerdim,
softmaxoutblock=self.softmaxoutblock)
def __init__(self,
memenc,
memdata,
memaddr=DotMemAddr,
memdim=None,
memattdim=100,
**kw):
assert (memenc is not None)
memblock = MemoryBlock(memenc,
memdata,
indim=memdata.shape[0],
outdim=memdim)
memstack = MemoryStack(memblock, memaddr, memattdim=memattdim)
super(MemVec2Idx, self).__init__(memstack, **kw)
def test_memory_block_with_seq_encoder_dynamic(self):
invocabsize = 5
memsize = 10
seqlen = 3
encdim = 13
data = np.random.randint(0, invocabsize, (memsize, seqlen))
gru = GRU(dim=invocabsize, innerdim=encdim)
payload = SeqEncoder(IdxToOneHot(vocsize=invocabsize), gru)
dynmemb = MemoryBlock(payload, outdim=encdim)
idxs = [0, 2, 5]
p = dynmemb.predict
memory_element = p(idxs, data)
self.assertEqual(memory_element.shape, (len(idxs), encdim))
gruparams = set([
getattr(gru, pname)
for pname in "u w b uhf whf bhf um wm bm".split()
])
allparams = set(p.outs[0].allparams)
self.assertEqual(gruparams.intersection(allparams), allparams)
statmemb = MemoryBlock(payload, data, outdim=encdim)
statpred = statmemb.predict(idxs)
self.assertTrue(np.allclose(statpred, memory_element))
