default='',
metavar='TD',
help='name of saved model (default: '
')')
args = parser.parse_args()
batch_loader = BatchLoader('',
custom_index=True,
train_data_name=args.sample_data)
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('./trained_model/{}'.format(args.model_name)))
if args.use_cuda:
rvae = rvae.cuda()
sampler = rvae.latent_sampler(batch_loader)
zs = {}
for i in range(
0,
int(batch_loader.total_lines('train') / args.batch_size) + 1):
indexes = np.array(
range(
i * args.batch_size,
min((i + 1) * args.batch_size,
batch_loader.total_lines('train'))))
type=bool,
default=True,
metavar='CUDA',
help='use cuda (default: True)')
parser.add_argument('--num-sample',
type=int,
default=100,
metavar='NS',
help='num samplings (default: 10)')
args = parser.parse_args()
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('trained_RVAE_code'))
if args.use_cuda:
rvae = rvae.cuda()
with open("code_sampling_100.txt", 'w') as cs:
for iteration in range(args.num_sample):
seed = np.random.normal(size=[1, parameters.latent_variable_size])
result = rvae.sample(batch_loader, 50, seed, args.use_cuda)
# print(result)
# print()
cs.write(result + '\n')
'data/super/characters_vocab_2.pkl']
tensor_files = [['data/super/train_word_tensor_2.npy'],
['data/super/train_character_tensor_2.npy']]
batch_loader_2 = BatchLoader(data_files, idx_files, tensor_files)
parameters_2 = Parameters(batch_loader_2.max_word_len,
batch_loader_2.max_seq_len,
batch_loader_2.words_vocab_size,
batch_loader_2.chars_vocab_size)
'''======================================== RVAE loading ==================================================
'''
print ('Started loading')
start_time = time.time()
rvae = RVAE(parameters,parameters_2)
rvae.load_state_dict(t.load(args.save_model))
if args.use_cuda:
rvae = rvae.cuda()
loading_time=time.time() - start_time
print ('Time elapsed in loading model =' , loading_time)
print ('Finished loading')
''' ==================================== Parameters Initialising ===========================================
'''
n_best = args.beam_top
beam_size =args.beam_size
assert n_best <= beam_size
use_cuda = args.use_cuda
parser.add_argument('--use-trained', type=bool, default=False, metavar='UT',
help='load pretrained model (default: False)')
parser.add_argument('--ce-result', default='', metavar='CE',
help='ce result path (default: '')')
parser.add_argument('--kld-result', default='', metavar='KLD',
help='ce result path (default: '')')
args = parser.parse_args()
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)
if args.use_trained:
rvae.load_state_dict(t.load('trained_RVAE'))
if args.use_cuda:
rvae = rvae.cuda()
optimizer = Adam(rvae.learnable_parameters(), args.learning_rate)
train_step = rvae.trainer(optimizer, batch_loader)
validate = rvae.validater(batch_loader)
ce_result = []
kld_result = []
for iteration in range(args.num_iterations):
path + 'data/super/valid_word_tensor_2.npy'
],
[
path + 'data/super/train_character_tensor_2.npy',
path + 'data/super/valid_character_tensor_2.npy'
]]
batch_loader_2 = BatchLoader(data_files, idx_files, tensor_files, path)
parameters_2 = Parameters(batch_loader_2.max_word_len,
batch_loader_2.max_seq_len,
batch_loader_2.words_vocab_size,
batch_loader_2.chars_vocab_size)
'''======================================== RVAE creation ==================================================
'''
rvae = RVAE(parameters, parameters_2)
rvae.load_state_dict(t.load('trained_RVAE'))
if args.use_cuda:
rvae = rvae.cuda()
n_best = 3
beam_size = 10
assert n_best <= beam_size
for i in range(args.num_sentence):
'''================================================== Input Encoder-1 ========================================================
'''
use_cuda = 1
input = batch_loader.next_batch(1, 'valid', i)
input = [Variable(t.from_numpy(var)) for var in input]
#load data
data = 0
with open('train.txt', 'r') as f:
data = f.readlines()
preprocess = Preprocess(embedding_model)
input = preprocess.to_sequence(data)
# embedding=preprocess.embedding()
# np.save('embedding',embedding)
batch_loader = Batch(input, 0.7)
params=Parameter(word_embed_size=300,encode_rnn_size=600,latent_variable_size=1400,\
decode_rnn_size=600,vocab_size=preprocess.vocab_size,embedding_path='embedding.npy')
model = RVAE(params)
model = model.cuda()
optimizer = Adam(model.learnable_parameters(), 1e-3)
train_step = model.trainer(optimizer)
use_cuda = t.cuda.is_available()
ce_list = []
kld_list = []
coef_list = []
test_batch = batch_loader.test_next_batch(1)
for i, batch in enumerate(batch_loader.train_next_batch(1)):
# if i%20==0:
# sample=next(test_batch)
# sentence=model.sample(10,sample,use_cuda)
# sentence=[preprocess.index_to_word(i) for i in sentence]
# help='ce result path (default: '')')
# parser.add_argument('--kld-result', default='', metavar='KLD',
# help='ce result path (default: '')')
args = parser.parse_args()
batch_loader = BatchLoader(path='',
custom_index=False,
train_data_name=args.train_data)
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)
optimizer = Adam(rvae.learnable_parameters(), args.learning_rate)
if args.use_trained:
rvae.load_state_dict(
t.load('./trained_model/{}_trained_{}'.format(
args.train_data.split('.')[0], args.start_epoch)))
optimizer.load_state_dict(
t.load('./trained_model/{}_trained_optimizer_{}'.format(
args.train_data.split('.')[0], args.start_epoch)))
if args.use_cuda:
rvae = rvae.cuda()
train_step = rvae.trainer(optimizer, batch_loader)
validate = rvae.validater(batch_loader)
metavar='TD',
help='load custom training dataset (default: '
')')
args = parser.parse_args()
batch_loader = BatchLoader(path='',
custom_index=False,
train_data_name=args.train_data)
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('./trained_model/{}'.format(args.model_name)))
if args.use_cuda:
rvae = rvae.cuda()
sents = []
seeds = {}
for iteration in range(args.num_sample):
seed = np.random.normal(size=[1, parameters.latent_variable_size])
sent = rvae.sample(batch_loader, 50, seed, args.use_cuda)
print(sent)
sents.append(sent)
seeds[sent] = seed.flatten()
with open(
path + 'data/super/train_word_tensor_2.npy',
path + 'data/super/valid_word_tensor_2.npy'
],
[
path + 'data/super/train_character_tensor_2.npy',
path + 'data/super/valid_character_tensor_2.npy'
]]
batch_loader_2 = BatchLoader(data_files, idx_files, tensor_files, path)
parameters_2 = Parameters(batch_loader_2.max_word_len,
batch_loader_2.max_seq_len,
batch_loader_2.words_vocab_size,
batch_loader_2.chars_vocab_size)
'''=================================================================================================
'''
rvae = RVAE(parameters, parameters_2)
if args.use_trained:
rvae.load_state_dict(t.load('trained_RVAE'))
if args.use_cuda:
rvae = rvae.cuda()
optimizer = Adam(rvae.learnable_parameters(), args.learning_rate)
train_step = rvae.trainer(optimizer, batch_loader, batch_loader_2)
validate = rvae.validater(batch_loader, batch_loader_2)
ce_result = []
kld_result = []
start_index = 0
# start_index_2 = 0
metavar='UT',
help='load pretrained model (default: False)')
parser.add_argument('--model-name',
default='',
metavar='MN',
help='name of model to save (default: '
')')
args = parser.parse_args()
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)
ce_result = []
kld_result = []
if args.use_trained:
rvae.load_state_dict(
t.load('saved_models/trained_RVAE_' + args.model_name))
ce_result = list(
np.load('saved_models/ce_result_{}.npy'.format(args.model_name)))
kld_result = list(
np.load('saved_models/kld_result_npy_{}.npy'.format(
args.model_name)))
if args.use_cuda:
rvae = rvae.cuda()
parser.add_argument('--use-trained', type=bool, default=False, metavar='UT',
help='load pretrained model (default: False)')
parser.add_argument('--ce-result', default='', metavar='CE',
help='ce result path (default: '')')
parser.add_argument('--kld-result', default='', metavar='KLD',
help='ce result path (default: '')')
args = parser.parse_args()
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)
if args.use_trained:
rvae.load_state_dict(t.load('trained_RVAE'))
if args.use_cuda:
rvae = rvae.cuda()
optimizer = Adam(rvae.learnable_parameters(), args.learning_rate)
train_step = rvae.trainer(optimizer)
# validate = rvae.validater()
ce_result = []
kld_result = []
# training_data = batch_loader.training_data('train')
# validation_data = batch_loader.training_data('valid')
parser.add_argument('--model-name',
default='',
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))
type=bool,
default=True,
metavar='CUDA',
help='use cuda (default: True)')
# parser.add_argument('--num-sample', type=int, default=10, metavar='NS',
# help='num samplings (default: 10)')
args = parser.parse_args()
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(torch.load('trained_RVAE'))
if args.use_cuda:
rvae = rvae.cuda()
seq_len = 50
seed = np.random.normal(size=[1, parameters.latent_variable_size])
data = [["how are you ?"], ["how are you doing"]]
data_words = [[line.split() for line in target] for target in data]
word_tensor = np.array(
[[list(map(batch_loader.word_to_idx.get, line)) for line in target]
for target in data_words])
character_tensor = np.array(
[[list(map(batch_loader.encode_characters, line)) for line in target]
