def main(_):
data_dir = cfg.DATA_DIR
vocab, rev_vocab = initialize_vocab(FLAGS.vocab)
# gpu setting
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.reset_default_graph()
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder, FLAGS.embed)
with tf.Session(config=config) as sess:
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(FLAGS.ckpt)
initialize_model(sess, qa, load_train_dir)
print(
'*********************************************************************'
)
print(
"Welcome! You can use this to explore the behavior of the model.")
print(
'*********************************************************************'
)
while True:
print('-------------------')
print('Input the context: ')
print('-------------------')
sentence = raw_input()
print('-------------------')
print('Input the question: ')
print('-------------------')
query = raw_input()
raw_context = nltk.word_tokenize(sentence)
context = sentence_to_token_ids(sentence,
vocab,
tokenizer=nltk.word_tokenize)
question = sentence_to_token_ids(query,
vocab,
tokenizer=nltk.word_tokenize)
context_in = mask_input(context, cfg.context_max_len)
question_in = mask_input(question, cfg.question_max_len)
start, end = qa.answer(sess, [context_in], [question_in])
answer = ' '.join(raw_context[start[0]:end[0] + 1])
print('==========================================')
print('ANSWER: {}'.format(answer))
print('==========================================')
def embed_test(print_out=10):
vocab_path = pjoin(data_dir, 'vocab.dat')
vocab, rev_vocab = initialize_vocab(vocab_path)
# print('first {} of vocab: {}'.format(print_out, ''.join(vocab[:print_out])))
print('first {} of rev_vocab: {}'.format(print_out, rev_vocab[:print_out]))
# we use glove with 100-d in default.
embed_path = pjoin(data_dir, "glove.trimmed.100.npz")
embedding = np.load(embed_path)
for k, v in vocab.items()[:10]:
print(k, v)
print('length of embedding is {}'.format(embedding['glove'].shape))
print('length of vocab is {}'.format(len(rev_vocab)))
def read_intputs():
'''used for test, just ignore it.'''
data_dir = cfg.DATA_DIR
vocab_path = pjoin(data_dir, cfg.vocab_file)
vocab, _ = initialize_vocab(vocab_path)
# sentence = raw_input('Input the context: ')
# context = sentence_to_token_ids(sentence, vocab, tokenizer=nltk.word_tokenize)
query = raw_input('Input the query : ')
print(nltk.word_tokenize(query)[90:91])
question = sentence_to_token_ids(query, vocab, tokenizer=nltk.word_tokenize)
question_in = mask_input(question, 20)
q = [x[0] for x in [question_in]]
print(q)
def read_intputs():
'''used for test, just ignore it.'''
data_dir = cfg.DATA_DIR
vocab_path = pjoin(data_dir, cfg.vocab_file)
vocab, _ = initialize_vocab(vocab_path)
# sentence = raw_input('Input the context: ')
# context = sentence_to_token_ids(sentence, vocab, tokenizer=nltk.word_tokenize)
query = raw_input('Input the query : ')
print(nltk.word_tokenize(query)[90:91])
question = sentence_to_token_ids(query,
vocab,
tokenizer=nltk.word_tokenize)
question_in = mask_input(question, 20)
q = [x[0] for x in [question_in]]
print(q)
def main():
dataload = DataLoader()
vocab, rev_vocab = initialize_vocab(pjoin(cfg.DATA_DIR, cfg.vocab_file))
config = tf.ConfigProto(device_count={'GPU': 0})
#config.gpu_options.allow_growth = True
tf.reset_default_graph()
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder, cfg.embed_dir)
c1 = open(pjoin(cfg.DATA_DIR, 'test.context'), 'r').read().split('\n')
q1 = open(pjoin(cfg.DATA_DIR, 'test.question'), 'r').read().split('\n')
a1 = open(pjoin(cfg.DATA_DIR, 'test.answer'), 'r').read().split('\n')
with tf.Session(config=config) as sess:
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = pjoin(cfg.output, cfg.train_dir)
initialize_model(sess, qa, load_train_dir)
ans = []
f1 = []
for i, data in enumerate(c1):
print(i)
sentence = c1[i]
query = q1[i]
raw_context = nltk.word_tokenize(sentence)
len(raw_context)
context = dataload.sentence_to_token_ids(
sentence, vocab, tokenizer=nltk.word_tokenize)
question = dataload.sentence_to_token_ids(
query, vocab, tokenizer=nltk.word_tokenize)
context_in = mask_input(context, cfg.context_max_len)
question_in = mask_input(question, cfg.question_max_len)
start, end = qa.answer(sess, [context_in], [question_in],
train=False)
answer = ' '.join(raw_context[start[0]:(end[0] + 1)])
f1.append(qa.f1_score(answer, a1[i]))
print("QUESTION: " + query)
print("ANSWER: " + answer)
if i == 100:
break
ans.append(answer)
return ans, f1
def main(_):
data_dir = cfg.DATA_DIR
vocab, rev_vocab = initialize_vocab(FLAGS.vocab)
# gpu setting
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.reset_default_graph()
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder, FLAGS.embed)
with tf.Session(config=config) as sess:
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(FLAGS.ckpt)
initialize_model(sess, qa, load_train_dir)
print('*********************************************************************')
print("Welcome! You can use this to explore the behavior of the model.")
print('*********************************************************************')
while True:
print('-------------------')
print('Input the context: ')
print('-------------------')
sentence = raw_input()
print('-------------------')
print('Input the question: ')
print('-------------------')
query = raw_input()
raw_context = nltk.word_tokenize(sentence)
context = sentence_to_token_ids(sentence, vocab, tokenizer=nltk.word_tokenize)
question = sentence_to_token_ids(query, vocab, tokenizer=nltk.word_tokenize)
context_in = mask_input(context, cfg.context_max_len)
question_in = mask_input(question, cfg.question_max_len)
start, end = qa.answer(sess, [context_in], [question_in])
answer = ' '.join(raw_context[start[0]: end[0] + 1])
print('==========================================')
print('ANSWER: {}'.format(answer))
print('==========================================')
def main(_):
'''Check the Config.py to set up models pathes to be ensembled.'''
data_dir = cfg.DATA_DIR
set_names = cfg.set_names
suffixes = cfg.suffixes
dataset = mask_dataset(data_dir, set_names, suffixes)
raw_answers = read_raw_answers(data_dir)
vocab_path = pjoin(data_dir, cfg.vocab_file)
vocab, rev_vocab = initialize_vocab(vocab_path)
if not os.path.exists(cfg.log_dir):
os.makedirs(cfg.log_dir)
if not os.path.exists(cfg.cache_dir):
os.makedirs(cfg.cache_dir)
if not os.path.exists(cfg.fig_dir):
os.makedirs(cfg.fig_dir)
c_time = time.strftime('%Y%m%d_%H%M', time.localtime())
file_handler = logging.FileHandler(
pjoin(cfg.log_dir, 'ensemble_log' + c_time + '.txt'))
logging.getLogger().addHandler(file_handler)
model_pathes = cfg.model_pathes
num_m = len(model_pathes)
train_s = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
train_e = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
val_s = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
val_e = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
# gpu setting
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
for i in xrange(num_m):
tf.reset_default_graph()
with tf.Session(config=config) as sess:
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder)
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(model_pathes[i])
initialize_model(sess, qa, load_train_dir)
ts, te, vs, ve = qa.evaluate_answer(sess,
dataset,
raw_answers,
rev_vocab,
log=True,
ensemble=True,
training=True,
sample=cfg.num_eval)
train_s[:, i] = ts
train_e[:, i] = te
val_s[:, i] = vs
val_e[:, i] = ve
if i == num_m - 1:
# np.save('cache/ensemble.npy', [train_s, train_e, val_s, val_e])
train_s = bin_count(train_s)
train_e = bin_count(train_e)
val_s = bin_count(val_s)
val_e = bin_count(val_e)
qa.evaluate_answer(sess,
dataset,
raw_answers,
rev_vocab,
log=True,
training=True,
sendin=(train_s, train_e, val_s, val_e),
sample=cfg.num_eval)
def main(_):
'''Check the Config.py to set up models pathes to be ensembled.'''
data_dir = cfg.DATA_DIR
set_names = cfg.set_names
suffixes = cfg.suffixes
dataset = mask_dataset(data_dir, set_names, suffixes)
raw_answers = read_raw_answers(data_dir)
vocab_path = pjoin(data_dir, cfg.vocab_file)
vocab, rev_vocab = initialize_vocab(vocab_path)
if not os.path.exists(cfg.log_dir):
os.makedirs(cfg.log_dir)
if not os.path.exists(cfg.cache_dir):
os.makedirs(cfg.cache_dir)
if not os.path.exists(cfg.fig_dir):
os.makedirs(cfg.fig_dir)
c_time = time.strftime('%Y%m%d_%H%M', time.localtime())
file_handler = logging.FileHandler(pjoin(cfg.log_dir, 'ensemble_log' + c_time + '.txt'))
logging.getLogger().addHandler(file_handler)
model_pathes = cfg.model_pathes
num_m = len(model_pathes)
train_s = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
train_e = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
val_s = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
val_e = np.zeros((cfg.num_eval, num_m), dtype=np.int32)
# gpu setting
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
for i in xrange(num_m):
tf.reset_default_graph()
with tf.Session(config=config) as sess:
encoder = Encoder(size=2 * cfg.lstm_num_hidden)
decoder = Decoder(output_size=2 * cfg.lstm_num_hidden)
qa = QASystem(encoder, decoder)
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(model_pathes[i])
initialize_model(sess, qa, load_train_dir)
ts, te, vs, ve = qa.evaluate_answer(sess, dataset, raw_answers, rev_vocab,
log=True,
ensemble=True,
training=True,
sample=cfg.num_eval)
train_s[:, i] = ts
train_e[:, i] = te
val_s[:, i] = vs
val_e[:, i] = ve
if i == num_m - 1:
# np.save('cache/ensemble.npy', [train_s, train_e, val_s, val_e])
train_s = bin_count(train_s)
train_e = bin_count(train_e)
val_s = bin_count(val_s)
val_e = bin_count(val_e)
qa.evaluate_answer(sess, dataset, raw_answers, rev_vocab,
log=True,
training=True,
sendin=(train_s, train_e, val_s, val_e),
sample=cfg.num_eval
)