print('dropout = ', args.dropout)
for i in range(3):
target_sentence, predicted_sentence = validation_sample(
args.use_cuda)
print(' target : ', target_sentence)
print('sample : ', predicted_sentence)
print('------------------------------')
ce_result += [cross_entropy]
kld_result += [kld]
# generate sample
if iteration % 300 == 0:
source = 'she should control the speed of her car'
result = rvae.conditioned_sample(source, batch_loader, args)
print('\n')
print('------------SAMPLE------------')
print('------------------------------')
print('source : ', source)
print('sample : ', result)
print('------------------------------')
# save model
if iteration % 1000 == 0 or iteration == (args.num_iterations - 1):
t.save(rvae.state_dict(),
'saved_models/trained_RVAE_' + args.model_name)
np.save('saved_models/ce_result_{}.npy'.format(args.model_name),
np.array(ce_result))
np.save('saved_models/kld_result_npy_{}'.format(args.model_name),
np.array(kld_result))
metavar='MN',
help='name of model to save (default: '
')')
args = parser.parse_args()
assert os.path.exists('saved_models/trained_RVAE_' + args.model_name), \
'trained model not found'
batch_loader = BatchLoader('')
parameters = Parameters(batch_loader.max_word_len,
batch_loader.max_seq_len,
batch_loader.words_vocab_size,
batch_loader.chars_vocab_size)
rvae = RVAE(parameters)
rvae.load_state_dict(t.load('saved_models/trained_RVAE_' +
args.model_name))
if args.use_cuda:
rvae = rvae.cuda()
with open(args.input_file) as f:
source_phrases = f.readlines()
source_phrases = [x.strip() for x in source_phrases]
for input_phrase in source_phrases:
# embed
print('input: ', input_phrase)
print('sampled: ')
for iteration in range(args.num_sample):
print(rvae.conditioned_sample(input_phrase, batch_loader, args))
print()