def beam_search_pick(prime, width):
"""Returns the beam search pick."""
if not len(prime) or prime == ' ':
prime = random.choice(list(vocab.keys()))
prime_labels = [vocab.get(word, 0) for word in prime.split()]
bs = BeamSearch(beam_search_predict,
sess.run(self.cell.zero_state(1, tf.float32)),
prime_labels)
samples, scores = bs.search(None, None, k=width, maxsample=num)
return samples[np.argmin(scores)]
def beam_search_pick(prime, width):
"""Returns the beam search pick."""
if not len(prime) or prime == ' ':
prime = random.choice(list(vocab.keys()))
prime_labels = [vocab.get(word, 0) for word in prime.split()]
bs = BeamSearch(beam_search_predict,
sess.run(self.cell.zero_state(1, tf.float32)),
prime_labels)
samples, scores = bs.search(None, None, k=width, maxsample=num)
return samples[np.argmin(scores)]
def test_multiple_beams(self):
bs = BeamSearch(naive_predict, self.initial_state, self.prime_labels)
samples, scores = bs.search(None, None, k=4, maxsample=5)
self.assertIn([0, 1, 4, 4, 4], samples)
# All permutations of this form must be in the results.
self.assertIn([0, 1, 4, 4, 3], samples)
self.assertIn([0, 1, 4, 3, 4], samples)
self.assertIn([0, 1, 3, 4, 4], samples)
# Make sure that the best beam has the lowest score.
self.assertEqual(samples[np.argmin(scores)], [0, 1, 4, 4, 4])
def test_multiple_beams(self):
bs = BeamSearch(naive_predict, self.initial_state, self.prime_labels)
samples, scores = bs.search(None, None, k=4, maxsample=5)
self.assertIn([0, 1, 4, 4, 4], samples)
# All permutations of this form must be in the results.
self.assertIn([0, 1, 4, 4, 3], samples)
self.assertIn([0, 1, 4, 3, 4], samples)
self.assertIn([0, 1, 3, 4, 4], samples)
# Make sure that the best beam has the lowest score.
self.assertEqual(samples[np.argmin(scores)], [0, 1, 4, 4, 4])
def beam_search_pick(prime_labels,
width,
initial_state,
tokens=False,
attention_key_words=None,
keywords_count=None):
"""Returns the beam search pick."""
bs = BeamSearch(beam_search_predict, initial_state, prime_labels,
attention_key_words, keywords_count)
eos = vocab.get('</s>', 0) if tokens else None
oov = vocab.get('<unk>', None)
samples, scores = bs.search(oov, eos, k=width, maxsample=num)
# returning the best sequence
return samples[np.argmin(scores)]
class MetricEvaluator(object):
def __init__(self, loader, beam_search=False, beam_width=4, batch_size=64):
self.batch_size = batch_size
self.loader = loader
# Dumping essential params
self.word2idx = loader.corpus.trg_params['word2idx']
self.idx2word = loader.corpus.trg_params['idx2word']
self.sos = loader.corpus.trg_params['word2idx']['<s>']
self.beam_search = None
if beam_search:
self.beam_search = BeamSearch(self.word2idx, beam_width=beam_width)
def compute_scores(self, model, split, compute_ppl=False):
itr = self.loader.create_epoch_iterator(split, self.batch_size)
model.eval()
refs = []
hyps = []
costs = []
for i, (src, src_lengths, trg) in tqdm(enumerate(itr)):
if compute_ppl:
loss = model.score(src, src_lengths, trg)
costs.append(loss.data[0])
if self.beam_search is None:
out = model.inference(src, src_lengths, sos=self.sos)
out = out.cpu().data.tolist()
else:
src = model.encoder(src, src_lengths)
out = self.beam_search.search(model.decoder, src)
trg = trg.cpu().data.tolist()
for ref, hyp in zip(trg, out):
refs.append(self.loader.corpus.idx2sent(self.idx2word, ref))
hyps.append(self.loader.corpus.idx2sent(self.idx2word, hyp))
score = compute_bleu(refs, hyps)
return score, costs
def test_single_beam(self):
bs = BeamSearch(naive_predict, self.initial_state, self.prime_labels)
samples, scores = bs.search(None, None, k=1, maxsample=5)
self.assertEqual(samples, [[0, 1, 4, 4, 4]])
def test_single_beam(self):
bs = BeamSearch(naive_predict, self.initial_state, self.prime_labels)
samples, scores = bs.search(None, None, k=1, maxsample=5)
self.assertEqual(samples, [[0, 1, 4, 4, 4]])