}
DELETE_STOP_WORDS = True
DELETECHARS = ''.join([string.punctuation, string.whitespace, "\n", "\xa0", "—", "-"])
for i in range(len(data)):
for iteration in range(args.num_sample):
original = ""
if args.use_file:
original = data[i]
else:
original = str
seed = Variable(t.randn([1, parameters.latent_variable_size]))
seed = seed.cuda()
results, scores = rvae.sampler(batch_loader, batch_loader_2, 50, seed, args.use_cuda, i, beam_size, n_best)
best = " ".join([batch_loader_2.decode_word(x[0]) for x in results[0]])
if batch_loader.end_token in best:
best = best[:best.index(batch_loader.end_token)]
text_1_space = original
text_2_space = best
text_1_space_1 = get_lemmas_list(original)
text_2_space_1 = get_lemmas_list(best)
blue_1 = sentence_bleu([text_1_space_1.split(" ")], text_2_space_1.split(" "), weights=(1, 0, 0, 0))
rouge = Rouge()
article_score = rouge.get_scores(text_1_space, text_2_space)[0]
article_score_1 = rouge.get_scores(text_1_space_1, text_2_space_1)[0]
scores["ROUGE 1"].append(round(article_score_1['rouge-1']['f'], 4))
scores["ROUGE 2"].append(round(article_score_1['rouge-2']['f'], 4))
scores["ROUGE L"].append(round(article_score_1['rouge-l']['f'], 4))
scores["BLEU 1"].append(round(blue_1, 4))
else:
print("original sentence: " + text_input + "\n")
for _ in range(args.num_sample):
seed = Variable(t.randn([1, parameters.latent_variable_size]))
seed = seed.cuda()
results, scores = rvae.sampler(
batch_loader, batch_loader_2, 50, seed, args.use_cuda, index, args.beam_size, args.beam_top
)
for tt in results:
for k in range(args.beam_top):
sen = " ".join([batch_loader_2.decode_word(x[k]) for x in tt])
if batch_loader.end_token in sen:
hyp = sen[: sen.index(batch_loader.end_token)]
print("generate sentence: " + hyp)
else:
hyp = sen
print("generate sentence: " + hyp)
hyp_.append(hyp)
iteration += 1
t.save(rvae.state_dict(), save_path + f"/trained_RVAE_{iteration}")
np.save(save_path + f"/ce_result.npy".format(args.ce_result), np.array(ce_result))
np.save(save_path + f"/kld_result.npy".format(args.kld_result), np.array(kld_result))
# seed = seed*std + mu
# print 'Multiplication done'
# seed = seed.cuda()
# print seed.size
# print type(seed)
# print seed
# exit()
results, scores = rvae.sampler(batch_loader, batch_loader_2, 50,
seed, args.use_cuda, i, beam_size,
n_best)
# exit()
# print(results)
for tt in results:
for k in range(n_best):
sen = " ".join(
[batch_loader_2.decode_word(x[k]) for x in tt])
# print sen
if batch_loader.end_token in sen:
print(sen[:sen.index(batch_loader.end_token)])
else:
print(sen)
# exit()
print('\n')
# print 'words_vocab_size BatchLoader ----------->'
# print batch_loader.words_vocab_size
# print '-----------------------------------------'
# print 'words_vocab_size BatchLoader_2 ----------->'
# print batch_loader_2.words_vocab_size
# print '-----------------------------------------'