def generate_gan(sess, model, loss_type="pair", negative_size=3):
samples = []
for _index, pair in enumerate(raw):
if _index % 100 == 0:
print("have sampled %d pairs" % _index)
q = pair[2]
a = pair[3]
neg_alist_index = [i for i in range(len(alist))]
neg_alist_index.remove(_index) # remove the positive index
sampled_index = np.random.choice(neg_alist_index, size=[FLAGS.pools_size], replace=False)
pools = np.array(alist)[sampled_index]
canditates = insurance_qa_data_helpers.loadCandidateSamples(q, a, pools, vocab)
predicteds = []
for batch in insurance_qa_data_helpers.batch_iter(canditates, batch_size=FLAGS.batch_size):
feed_dict = {model.input_x_1: batch[:, 0], model.input_x_2: batch[:, 1], model.input_x_3: batch[:, 2]}
predicted = sess.run(model.gan_score, feed_dict)
predicteds.extend(predicted)
# index=np.argmax(predicteds)
# samples.append([encode_sent(vocab,item, FLAGS.max_sequence_length) for item in [q,a,pools[index]]])
exp_rating = np.exp(np.array(predicteds) * FLAGS.sampled_temperature * 1.5)
prob = exp_rating / np.sum(exp_rating)
neg_samples = np.random.choice(pools, size=negative_size, p=prob, replace=False)
for neg in neg_samples:
samples.append([encode_sent(vocab, item, FLAGS.max_sequence_length) for item in [q, a, neg]])
return samples
def generate_dns_pair(sess, model):
samples = []
for _index, pair in enumerate(raw):
if _index % 100 == 0:
print("have sampled %d pairs" % _index)
q = pair[2]
a = pair[3]
pools = np.random.choice(alist, size=[FLAGS.pools_size])
canditates = insurance_qa_data_helpers.loadCandidateSamples(
q, a, pools, vocab)
predicteds = []
for batch in insurance_qa_data_helpers.batch_iter(
canditates, batch_size=FLAGS.batch_size):
feed_dict = {
model.input_x_1: batch[:, 0],
model.input_x_2: batch[:, 1],
model.input_x_3: batch[:, 2]
}
predicted = sess.run(model.score13, feed_dict)
predicteds.extend(predicted)
index = np.argmax(predicteds)
samples.append([
encode_sent(vocab, item, FLAGS.max_sequence_length)
for item in [q, a, pools[index]]
])
return samples
def generate_dns_pair(sess, model):
samples = []
for _index, pair in enumerate(raw):
#ループ内は１組のqaについて扱う
if _index % 100 == 0:
print("have sampled %d pairs" % _index)
q = pair[2]
a = pair[3]
pools = np.random.choice(alist, size=[FLAGS.pools_size])
#1qaペアにつき、プールサイズ(100)分のneg
canditates = insurance_qa_data_helpers.loadCandidateSamples(
q, a, pools, vocab)
predicteds = []
for batch in insurance_qa_data_helpers.batch_iter(
canditates, batch_size=FLAGS.batch_size):
#batchサイズ(100)分: (q,a,neg1),...,(q,a,negバッチサイズ)
#batch[:,0]にはバッチサイズ分のq、batch[:,1]はa、batch[:.2]はneg。
feed_dict = {
model.input_x_1: batch[:, 0],
model.input_x_2: batch[:, 1],
model.input_x_3: batch[:, 2]
}
predicted = sess.run(model.score13, feed_dict) #score13はcos(q,neg)
predicteds.extend(predicted)
index = np.argmax(predicteds)
samples.append([
encode_sent(vocab, item, FLAGS.max_sequence_length)
for item in [q, a, pools[index]]
])
return samples
def generate_uniform_pair():
samples = []
for pair in raw:
q = pair[2]
a = pair[3]
index = random.randint(0, len(alist) - 1)
neg = alist[index]
samples.append([
encode_sent(vocab, item, FLAGS.max_sequence_length)
for item in [q, a, neg]
])
return samples
