def run_func():
config = Config()
# ========= Load Dataset =========
# You can change this code to load dataset in your own way
vocab, rev_vocab = initialize_vocab(config.vocab_path)
dev_path = "data/squad/fuse.json"
dev_dirname = os.path.dirname(os.path.abspath(dev_path))
dev_filename = os.path.basename(dev_path)
context_data, question_data, question_uuid_data = prepare_dev(
dev_dirname, dev_filename, vocab)
ques_len = len(question_data)
answers = [[0, 0] for _ in xrange(ques_len)]
dataset = [question_data, context_data, answers]
embed_path = config.embed_path
embeddings = get_trimmed_glove_vectors(embed_path)
encoder = Encoder(config.hidden_state_size)
decoder = Decoder(config.hidden_state_size)
qa = QASystem(encoder, decoder, embeddings, config)
with tf.Session() as sess:
qa.initialize_model(sess, config.train_dir)
answers, _ = generate_answers(sess, qa, dataset, question_uuid_data,
rev_vocab)
# write to json file to root dir
with io.open('temp/fuse-answer.json', 'w', encoding='utf-8') as f:
f.write(unicode(json.dumps(answers, ensure_ascii=False)))
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
train_data, val_data = load_preprocess_data(FLAGS.data_dir,
FLAGS.max_context_len,
FLAGS.max_question_len)
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
embeddings = tf.constant(load_embeddings(embed_path), tf.float32)
encoder = Encoder(FLAGS.state_size, FLAGS.summary_flag,
FLAGS.max_context_len, FLAGS.max_question_len)
decoder = Decoder(FLAGS.state_size, FLAGS.summary_flag)
qa = QASystem(encoder, decoder, FLAGS, embeddings, rev_vocab)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, train_data, val_data, save_train_dir)
def run_func2(dataset, config):
vocab, rev_vocab = initialize_vocab(config.vocab_path)
q, c, a = zip(*[[_q, _c, _a] for (_q, _c, _a) in dataset])
dataset = [q, c, a]
embed_path = config.embed_path
embeddings = get_trimmed_glove_vectors(embed_path)
encoder = Encoder(config.hidden_state_size)
decoder = Decoder(config.hidden_state_size)
qa = QASystem(encoder, decoder, embeddings, config)
question_uuid_data = [i for i in xrange(len(a))]
with tf.Session() as sess:
qa.initialize_model(sess, config.train_dir)
answers, answers_canonical = generate_answers(sess, qa, dataset,
question_uuid_data,
rev_vocab)
# write to json file to root dir
with io.open('dev-prediction.txt', 'w', encoding='utf-8') as f:
for i in xrange(len(a)):
curr_ans = unicode(answers[i], "utf-8")
f.write("%s\n" % (curr_ans))
def main(_):
vocab, rev_vocab = initialize_vocab(FLAGS.vocab_path)
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
dev_dirname = os.path.dirname(os.path.abspath(FLAGS.dev_path))
dev_filename = os.path.basename(FLAGS.dev_path)
context_data, question_data, question_uuid_data, context_text = prepare_dev(
dev_dirname, dev_filename, vocab)
dataset = (context_data, question_data, question_uuid_data)
idx_word = data_utils.invert_map(vocab)
qa = QASystem(FLAGS, embed_path, idx_word, False, 0, True)
with tf.Session() as sess:
initialize_model(sess, qa, FLAGS.train_dir)
start, end = qa.test(sess, dataset)
answers = generate_answers(sess, qa, dataset, rev_vocab, context_text,
idx_word)
with io.open('dev-prediction_2.json', 'w', encoding='utf-8') as f:
f.write(unicode(json.dumps(answers, ensure_ascii=False)))
def run_func():
config = Config()
vocab, rev_vocab = initialize_vocab(config.vocab_path)
dev_path = "download/squad/test.json"
dev_dirname = os.path.dirname(os.path.abspath(dev_path))
dev_filename = os.path.basename(dev_path)
context_data, question_data, question_uuid_data = prepare_dev(
dev_dirname, dev_filename, vocab)
ques_len = len(question_data)
answers = [[0, 0] for _ in xrange(ques_len)]
dataset = [question_data, context_data, answers]
embed_path = config.embed_path
embeddings = get_trimmed_glove_vectors(embed_path)
encoder = Encoder(config.hidden_state_size)
decoder = Decoder(config.hidden_state_size)
qa = QASystem(encoder, decoder, embeddings, config)
data = "Id,Answer\n"
with tf.Session() as sess:
qa.initialize_model(sess, config.train_dir)
answers, _ = generate_answers(sess, qa, dataset, question_uuid_data,
rev_vocab)
for a in answers:
ans = answers[a]
data += a + "," + normalize_answer(ans).replace(" s ", "s ") + "\n"
with open('submission.csv', 'wb') as file:
file.write(data)
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
# load all in once, maybe better to try batch by batch
question_path = "./data/squad/train.ids.question"
context_path = "./data/squad/train.ids.context"
answer_path = "./data/squad/train.span"
val_q = "./data/squad/val.ids.question"
val_c = "./data/squad/val.ids.context"
val_a = "./data/squad/val.span"
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
# embeddings is a matrix of shape [vocab_size, embedding_size]
embeddings = np.load(embed_path)['glove'].astype(np.float32)
val_data = load_and_pad_val_data(val_q, val_c, val_a)
# vocab is the mapping from word -> token id
# rev_vocab is the reverse mapping, from id -> word
vocab, rev_vocab = initialize_vocab(vocab_path)
# someone posted that the max length of question is 766
info = (question_path, context_path, answer_path, FLAGS.batch_size,
FLAGS.max_length, FLAGS.output_size)
'''
batch_gen = batch_generator(question_path, context_path, answer_path, FLAGS.batch_size, FLAGS.max_length, FLAGS.output_size)
i = 0;
while True:
batch_gen.next()
i += 1
logging.info(i)
'''
encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
decoder = Decoder(output_size=FLAGS.output_size)
qa = QASystem(encoder, decoder, FLAGS, embeddings)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, batch_generator, info, save_train_dir, val_data,
rev_vocab)
def predict(model_name):
qa = QASystem(model_name)
with tf.Session() as sess:
qa.initialize_model(sess)
while True:
question = input("Ask a question: ")
for answer, confidence, doc in answer_question(qa, sess, question, best_n=10):
print('{:.2f}:\t{} ({})'.format(confidence, answer, doc))
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
#dataset = load_data(FLAGS.data_dir) # None
dataset = {}
num_train = load_data_dq(dataset, 'train', FLAGS.data_dir)
num_val = load_data_dq(dataset, 'val', FLAGS.data_dir)
load_data_sa(dataset, 'train', FLAGS.data_dir, num_train)
load_data_sa(dataset, 'val', FLAGS.data_dir, num_val)
trim(dataset['train'])
trim(dataset['val'])
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
decoder = Decoder(output_size=FLAGS.output_size)
# Session moved upfront to set the ifgpu flag before QASystem
with tf.Session() as sess:
pass
local_device_protos = device_lib.list_local_devices() # 38559755
for x in local_device_protos:
if x.device_type == 'GPU':
FLAGS.ifgpu = True
break
qa = QASystem(encoder, decoder, embed_path, rev_vocab)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
#print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
# tfdbg
#with tf.Session() as sess:
# pass
#sess = tfdbg.LocalCLIDebugWrapperSession(sess)
#sess.add_tensor_filter("has_inf_or_nan", tfdbg.has_inf_or_nan)
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, dataset, save_train_dir)
#qa.evaluate_answer(sess, dataset, vocab, FLAGS.evaluate, log=True)
sess.close() #tfdbg
def main(_):
dataset = {}
question_max_len = 40
context_max_len = 600
# Preprocess and collect small test data
test_q_path = pjoin(FLAGS.data_dir, "test.ids.question")
test_q_data, test_q_seq_len = pad_sentences(test_q_path, question_max_len)
assert not any(
test_q_seq_len > test_q_data.shape[1]
), 'Some questions have length greater than max question length'
test_c_path = pjoin(FLAGS.data_dir, "test.ids.context")
test_c_data, test_c_seq_len = pad_sentences(test_c_path, context_max_len)
assert not any(
test_c_seq_len > test_c_data.shape[1]
), 'Some contexts have length greater than max context length'
test_s_path = pjoin(FLAGS.data_dir, "test.span")
test_s_e_id = get_answer_span(test_s_path, context_max_len)
dataset['test'] = [
test_q_data, test_q_seq_len, test_c_data, test_c_seq_len, test_s_e_id
]
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
encoder = Encoder(state_size=FLAGS.state_size,
vocab_dim=FLAGS.embedding_size)
decoder = Decoder(state_size=FLAGS.state_size)
qa = QASystem(encoder, decoder, question_max_len, context_max_len,
embed_path, FLAGS.learning_rate, FLAGS.batch_size,
FLAGS.dropout, FLAGS.optimizer,
FLAGS.max_gradient_norm) # try without dropout
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, dataset['test'], save_train_dir,
small_data_test=True) #
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(_):
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
logger = logging.getLogger()
# Do what you need to load datasets from FLAGS.data_dir
dataset = None
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
train_data = zip(*load_data(FLAGS.data_dir, "train"))
val_data = zip(*load_data(FLAGS.data_dir, "val"))
dev_data = zip(*load_data(FLAGS.data_dir, "dev"))
#model_train_data = train_data + val_data + dev_data
model_train_data = train_data
model_eval_data = val_data
global_train_dir = '/tmp/cs224n-squad-train'
# Adds symlink to {train_dir} from /tmp/cs224n-squad-train to canonicalize the
# file paths saved in the checkpoint. This allows the model to be reloaded even
# if the location of the checkpoint files has moved, allowing usage with CodaLab.
# This must be done on both train.py and qa_answer.py in order to work.
if os.path.exists(global_train_dir):
os.unlink(global_train_dir)
if not os.path.exists(FLAGS.train_dir):
os.makedirs(FLAGS.train_dir)
os.symlink(os.path.abspath(FLAGS.train_dir), global_train_dir)
train_dir = global_train_dir
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Graph().as_default():
with tf.Session() as sess:
logger.info("Loading embeddings")
embeddings = np.load(FLAGS.data_dir + '/glove.trimmed.' +
str(FLAGS.embedding_size) + '.npz')
pretrained_embeddings = embeddings['glove']
logger.info("Embeddings loaded with shape: %s %s" %
(pretrained_embeddings.shape))
qa = QASystem(FLAGS,
pretrained_embeddings,
vocab_dim=len(vocab.keys()))
initialize_model(sess, qa, train_dir)
qa.train(sess, model_train_data, model_eval_data)
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
# use .readlines() to load file ourselves
# use python generator
question_path = pjoin(FLAGS.data_dir, "data_train/train_tokenH.txt")
paragraph_path = pjoin(FLAGS.data_dir, "data_train/train_tokenP.txt")
answer_path = pjoin(FLAGS.data_dir, "data_train/train_index.txt")
val_question_path = pjoin(FLAGS.data_dir, "data_dev/dev_tokenH.txt")
val_paragraph_path = pjoin(FLAGS.data_dir, "data_dev/dev_tokenP.txt")
val_answer_path = pjoin(FLAGS.data_dir, "data_dev/dev_index.txt")
# for testing
# dataset = [(1,1,1), (1,1,1)]
dataset = load_dataset(question_path, paragraph_path, answer_path,
FLAGS.batch_size)
val_dataset = load_dataset(val_question_path, val_paragraph_path,
val_answer_path, FLAGS.batch_size)
#generate_histograms(dataset)
#generate_histograms(val_dataset)
# loads embedding
FLAGS.embed_path = FLAGS.embed_path or pjoin("data", "sgns.merge.word.npz")
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.txt")
vocab, rev_vocab = initialize_vocab(
vocab_path) # one is list and one is dict
encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
decoder = Decoder(size=FLAGS.state_size, output_size=FLAGS.output_size)
qa = QASystem(encoder, decoder, FLAGS)
# log file
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
# start training
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, dataset, val_dataset, save_train_dir, rev_vocab)
def run_func():
config = Config()
train = squad_dataset(config.question_train, config.context_train,
config.answer_train)
dev = squad_dataset(config.question_dev, config.context_dev,
config.answer_dev)
# print(config.question_train)
embed_path = config.embed_path
vocab_path = config.vocab_path
# print(config.embed_path, config.vocab_path)
vocab, rev_vocab = initialize_vocab(vocab_path)
embeddings = get_trimmed_glove_vectors(embed_path)
encoder = Encoder(config.hidden_size)
decoder = Decoder(config.hidden_size)
qa = QASystem(encoder, decoder, embeddings, config)
with tf.Session() as sess:
# ====== Load a pretrained model if it exists or create a new one if no pretrained available ======
qa.initialize_model(sess, config.train_dir)
# train process
# qa.train(sess, [train, dev], config.train_dir)
# em = qa.evaluate_model(sess, dev)
# run process
while True:
question = input('please input question: ')
if question == 'exit':
break
raw_context = input('please input context: ')
if raw_context == 'exit':
break
question = [
vocab[x] if x in vocab.keys() else 2 for x in question.split()
]
context = [
vocab[x] if x in vocab.keys() else 2
for x in raw_context.split()
]
test = [[question], [context], [[1, 2]]]
a_s, a_e = qa.answer(sess, test)
if a_e == a_s:
print("answer: ", raw_context.split()[a_s[0]])
else:
print("answer: ",
' '.join(raw_context.split()[a_s[0]:a_e[0] + 1]))
def main(_):
vocab, rev_vocab = initialize_vocab(FLAGS.vocab_path)
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
# ========= Load Dataset =========
# You can change this code to load dataset in your own way
dev_dirname = os.path.dirname(os.path.abspath(FLAGS.dev_path))
dev_filename = os.path.basename(FLAGS.dev_path)
context_data, question_data, question_uuid_data = prepare_dev(
dev_dirname, dev_filename, vocab)
context_ids, ctx_mask = pad(context_data, FLAGS.output_size)
question_ids, q_mask = pad(question_data, FLAGS.question_size)
for i in range(0, len(context_ids)):
context_ids[i] = context_ids[i][:FLAGS.output_size]
for j in range(0, len(question_ids)):
question_ids[j] = question_ids[j][:FLAGS.question_size]
context_ids = np.array(context_ids)
question_ids = np.array(question_ids)
ctx_mask = np.array(ctx_mask)
q_mask = np.array(q_mask)
answer_span = np.array(
[(0, 0)] * len(context_ids)
) #Need this because minibatches is expecting it this way
dataset = [
context_ids, question_ids, answer_span, ctx_mask, q_mask,
question_uuid_data
]
embeddings = initialize_embeddings(embed_path)
# ========= Model-specific =========
# You must change the following code to adjust to your model
#encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
#decoder = Decoder(output_size=FLAGS.output_size)
#qa = QASystem(pretrained_embeddings=embeddings,flags=FLAGS)
qa = QASystem(pretrained_embeddings=embeddings, flags=FLAGS)
with tf.Session() as sess:
train_dir = get_normalized_train_dir(FLAGS.train_dir)
initialize_model(sess, qa, train_dir)
answers = generate_answers(sess, qa, dataset, rev_vocab)
# write to json file to root dir
with io.open('dev-prediction.json', 'w', encoding='utf-8') as f:
f.write(unicode(json.dumps(answers, ensure_ascii=False)))
def main(_):
vocab, rev_vocab = initialize_vocab(FLAGS.vocab_path)
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
# ========= Load Dataset =========
# You can change this code to load dataset in your own way
dev_dirname = os.path.dirname(os.path.abspath(FLAGS.dev_path))
dev_filename = os.path.basename(FLAGS.dev_path)
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
embeddings = load_glove_embeddings(embed_path)
raw_embed_path = pjoin(
"data", "squad", "glove.untrimmed.{}.npz".format(FLAGS.embedding_size))
raw_glove_data = np.load(raw_embed_path)
raw_glove = raw_glove_data['glove']
raw_glove_vocab = raw_glove_data['glove_vocab_dict'][()]
# expand vocab
vocab, rev_vocab, embeddings = expand_vocab(dev_dirname, dev_filename,
vocab, embeddings, raw_glove,
raw_glove_vocab)
context_data, question_data, question_uuid_data = prepare_dev(
dev_dirname, dev_filename, vocab)
context_len_data = [len(context.split()) for context in context_data]
mydata = preprocessing(context_data, question_data, FLAGS.context_maxlen,
FLAGS.question_maxlen)
dataset = (mydata, context_data, context_len_data, question_uuid_data)
# ========= Model-specific =========
# You must change the following code to adjust to your model
#encoder = Encoder(vocab_dim=FLAGS.embedding_size, state_size = FLAGS.encoder_state_size)
#decoder = Decoder(output_size=FLAGS.output_size, hidden_size = FLAGS.decoder_hidden_size, state_size = FLAGS.decoder_state_size)
qa = QASystem(embeddings, FLAGS)
with tf.Session() as sess:
train_dir = get_normalized_train_dir(FLAGS.train_dir)
initialize_model(sess, qa, train_dir)
answers = generate_answers(sess, qa, dataset, rev_vocab)
# write to json file to root dir
with io.open('dev-prediction.json', 'w', encoding='utf-8') as f:
f.write(unicode(json.dumps(answers, ensure_ascii=False)))
def main(_):
#======Fill the model name=============
train_dir = "train/test"
#======================================
vocab, rev_vocab = initialize_vocab(FLAGS.vocab_path)
embed_path = FLAGS.embed_path or pjoin("data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
# ========= Load Dataset =========
train_data,val_data = load_and_preprocess_data(FLAGS.data_dir, FLAGS.max_context_len, FLAGS.max_question_len, size = FLAGS.train_size)
# ========= Model-specific =========
# You must change the following code to adjust to your model
embed_path = FLAGS.embed_path or pjoin("data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
embedding = tf.constant(load_embeddings(embed_path), dtype = tf.float32)
encoder = Encoder(FLAGS.state_size, FLAGS.max_context_len, FLAGS.max_question_len, FLAGS.embedding_size, FLAGS.summary_flag, FLAGS.filter_flag)
decoder = Decoder(FLAGS.state_size, FLAGS.max_context_len, FLAGS.max_question_len, FLAGS.output_size, FLAGS.summary_flag)
qa = QASystem(encoder, decoder, FLAGS, embedding, rev_vocab)
with tf.Session() as sess:
train_dir = get_normalized_train_dir(train_dir)
qa = initialize_model(sess, qa, train_dir)
output_list, output_dict = generate_answers(sess, qa, val_data, rev_vocab)
store_result(output_list, output_dict, train_dir)
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
dataset = load_dataset()
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
encoder = Encoder(state_size=FLAGS.state_size,
embedding_size=FLAGS.embedding_size,
output_size=FLAGS.output_size)
decoder = Decoder(state_size=FLAGS.state_size,
output_size=FLAGS.output_size)
qa_args = {
"embed_path": embed_path,
"embedding_size": FLAGS.embedding_size,
"output_size": FLAGS.output_size,
"optimizer": FLAGS.optimizer,
"learning_rate": FLAGS.learning_rate,
"epochs": FLAGS.epochs,
"batch_size": FLAGS.batch_size,
"max_gradient_norm": FLAGS.max_gradient_norm,
"dropout_keep_prob": 1.0 - FLAGS.dropout,
"train_dir": FLAGS.train_dir,
"state_size": FLAGS.state_size
}
qa = QASystem(encoder, decoder, **qa_args)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, dataset, save_train_dir)
def evaluate(model_name, n=None):
data = []
with open(config.TREC_PATH, 'r') as f:
reader = csv.reader(f, delimiter='\t')
for row in list(reader)[199:]:
data.append((row[2].strip(), row[3].strip()))
if not n:
n = len(data)
qa = QASystem(model_name)
top_count = 0
top_5_count = 0
top_10_count = 0
with tf.Session() as sess:
qa.initialize_model(sess)
with open(os.path.join(config.MODELS_DIR, model_name, 'trec.csv'),
'w') as f:
writer = csv.writer(f)
i = 0
for question, answer_pattern in tqdm(data[:n]):
answers = [
answer for answer, confidence, doc in answer_question(
qa, sess, question, 10)
]
writer.writerow(answers)
correct = [
bool(re.search(answer_pattern, answer))
for answer in answers
]
if True in correct[:1]:
top_count += 1
if True in correct[:5]:
top_5_count += 1
if True in correct[:10]:
top_10_count += 1
i += 1
print('{}: {}, {}, {}'.format(i,
float(top_count) / i,
float(top_5_count) / i,
float(top_10_count) / i))
print('Top match: {}'.format(float(top_count) / n))
print('Top 5 match: {}'.format(float(top_5_count) / n))
print('Top 10 match: {}'.format(float(top_10_count) / n))
def main(_):
vocab, rev_vocab = initialize_vocab(FLAGS.vocab_path)
embed_path = FLAGS.embed_path or pjoin("data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
global_train_dir = '/tmp/cs224n-squad-train'
# Adds symlink to {train_dir} from /tmp/cs224n-squad-train to canonicalize the
# file paths saved in the checkpoint. This allows the model to be reloaded even
# if the location of the checkpoint files has moved, allowing usage with CodaLab.
# This must be done on both train.py and qa_answer.py in order to work.
if not os.path.exists(FLAGS.train_dir):
os.makedirs(FLAGS.train_dir)
if os.path.exists(global_train_dir):
os.unlink(global_train_dir)
os.symlink(os.path.abspath(FLAGS.train_dir), global_train_dir)
train_dir = global_train_dir
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
# ========= Load Dataset =========
# You can change this code to load dataset in your own way
dev_dirname = os.path.dirname(os.path.abspath(FLAGS.dev_path))
dev_filename = os.path.basename(FLAGS.dev_path)
context_data, question_data, question_uuid_data = prepare_dev(dev_dirname, dev_filename, vocab)
dataset = load_data(context_data, question_data, question_uuid_data)
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
# ========= Model-specific =========
# You must change the following code to adjust to your model
embed_path = FLAGS.embed_path or "data/squad/glove.trimmed.{}.npz".format(FLAGS.embedding_size)
embeddingz = np.load(embed_path)
embeddings = embeddingz['glove']
embeddingz.close()
assert embeddings.shape[1] == FLAGS.embedding_size
qa = QASystem(train_dir, embeddings)
with tf.Session() as sess:
initialize_model(sess, qa, train_dir)
answers = generate_answers(sess, qa, dataset, rev_vocab)
# write to json file to root dir
with io.open('dev-prediction.json', 'w', encoding='utf-8') as f:
f.write(unicode(json.dumps(answers, ensure_ascii=False)))
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(_):
logging.info("Loading training data")
dataset_train = load_train_data(FLAGS.data_dir, isValidation = False)
logging.info("Loading validation data")
dataset_val = load_train_data(FLAGS.data_dir, isValidation = True)
logging.info("Building Model Graph")
tf.set_random_seed(42)
np.random.seed(43)
select_test(0)
encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
decoder = SimpleLinearDecoder() #AnswerPointerDecoder()
qa = QASystem(encoder, decoder, len(dataset_train[0]))
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
logging.info(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
cris_flag = os.environ.get('CS224N_CRIS')
if cris_flag is not None:
logging.info('hi cris')
sess = tf.Session(config = tf.ConfigProto(intra_op_parallelism_threads = 1))
else:
sess = tf.Session()
with sess.as_default():
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, dataset_train, dataset_val, save_train_dir)
sess.close()
def main(args):
if args:
restore = args
embed_path = FLAGS.embed_path or "data/squad/glove.trimmed.{}.npz".format(
FLAGS.embedding_size)
embeddingz = np.load(embed_path)
embeddings = embeddingz['glove']
embeddingz.close()
assert embeddings.shape[1] == FLAGS.embedding_size
vocab_len = embeddings.shape[0]
train = load_squad(FLAGS.data_dir,
"train",
max_vocab=vocab_len if FLAGS.check_embeddings else 0,
max_samples=FLAGS.max_train_samples)
val = load_squad(FLAGS.data_dir,
"val",
max_vocab=vocab_len if FLAGS.check_embeddings else 0,
max_samples=FLAGS.max_val_samples)
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
if FLAGS.verify_only:
print_samples(train, FLAGS.verify_only, rev_vocab)
return
global_train_dir = '/tmp/cs224n-squad-train'
# Adds symlink to {train_dir} from /tmp/cs224n-squad-train to canonicalize the
# file paths saved in the checkpoint. This allows the model to be reloaded even
# if the location of the checkpoint files has moved, allowing usage with CodaLab.
# This must be done on both train.py and qa_answer.py in order to work.
if os.path.exists(global_train_dir):
os.unlink(global_train_dir)
if not os.path.exists(FLAGS.train_dir):
os.makedirs(FLAGS.train_dir)
os.symlink(os.path.abspath(FLAGS.train_dir), global_train_dir)
train_dir = global_train_dir
qa = QASystem(train_dir, embeddings)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
initialize_model(sess, qa, train_dir)
qa.train(sess, train)
qa.evaluate_answer(sess, qa.preprocess_sequence_data(val), log=True)
def main(_):
vocab, rev_vocab = initialize_vocab(FLAGS.vocab_path)
FLAGS.embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
# ========= Load Dataset =========
# You can change this code to load dataset in your own way
dev_dirname = os.path.dirname(os.path.abspath(FLAGS.dev_path))
dev_filename = os.path.basename(FLAGS.dev_path)
context_data, question_data, question_uuid_data = prepare_dev(
dev_dirname, dev_filename, vocab)
dataset = {
"val_context": context_data,
"val_questions": question_data,
"val_question_uuids": question_uuid_data
}
# ========= Model-specific =========
# You must change the following code to adjust to your model
encoder = Encoder(size=FLAGS.state_size,
vocab_dim=FLAGS.embedding_size,
FLAGS=FLAGS)
decoder = Decoder(FLAGS=FLAGS)
qa = QASystem(encoder, decoder, FLAGS)
with tf.Session() as sess:
#train_dir = get_normalized_train_dir(FLAGS.train_dir)
train_dir = FLAGS.train_dir
print("train_dir: ", train_dir)
initialize_model(sess, qa, train_dir)
print("Generating Answers")
answers = generate_answers(sess, qa, dataset, rev_vocab)
# write to json file to root dir
print("Writing to json file")
with io.open('dev-prediction.json', 'w', encoding='utf-8') as f:
f.write(unicode(json.dumps(answers, ensure_ascii=False)))
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
datasetTrain = initialize_datasets(FLAGS.data_dir, 'train')
datasetVal = initialize_datasets(FLAGS.data_dir, 'val')
#datasetTrain = datasetTrain[0:100]
embed_path = FLAGS.embed_path or pjoin("data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
decoder = Decoder(output_size=FLAGS.output_size)
qa = QASystem(encoder, decoder, embed_path, rev_vocab, FLAGS)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, datasetTrain, save_train_dir)
qa.evaluate_answer(sess, datasetVal, sample=1000, log=True)
def main(_):
dataset = [
load_dataset([
"embedding/train.ids.question", "embedding/train.ids.context",
"data/train.span"
]),
load_dataset([
"embedding/val.ids.question", "embedding/val.ids.context",
"data/val.span"
])
]
embed_path = pjoin("embedding",
"glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
tf.reset_default_graph()
encoder = Encoder(FLAGS.num_hidden_unit, tf.contrib.rnn.GRUCell)
decoder = Decoder(FLAGS.num_hidden_unit, tf.contrib.rnn.BasicLSTMCell)
embedding = np.load(embed_path)["glove"]
qa = QASystem(encoder, decoder, embedding, FLAGS.keep_prob)
if not os.path.exists(FLAGS.train_dir):
os.makedirs(FLAGS.train_dir)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
initialize_model(sess, qa, FLAGS.train_dir)
qa.train(sess, dataset, FLAGS.epochs, FLAGS.batch_size,
FLAGS.train_dir)
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
dataset = get_dataset(FLAGS.data_dir, FLAGS.max_question_size,
FLAGS.max_paragraph_size)
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
FLAGS.embed_path = embed_path
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
encoder = Encoder(size=FLAGS.state_size,
vocab_dim=FLAGS.embedding_size,
FLAGS=FLAGS)
decoder = Decoder(FLAGS=FLAGS)
qa = QASystem(encoder, decoder, FLAGS)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
#load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir or FLAGS.train_dir) #Change these back for final submission
load_train_dir = FLAGS.load_train_dir or FLAGS.train_dir
print("load_train_dir: ", load_train_dir)
initialize_model(sess, qa, load_train_dir)
#save_train_dir = get_normalized_train_dir(FLAGS.train_dir) #Change back for final submission
save_train_dir = FLAGS.train_dir
print("save_train_dir: ", save_train_dir)
qa.train(sess, dataset, save_train_dir, rev_vocab)
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
dataset = []
dataset.append(pjoin(FLAGS.data_dir, "train.ids.question"))
dataset.append(pjoin(FLAGS.data_dir, "train.ids.context"))
dataset.append(pjoin(FLAGS.data_dir, "train.span"))
dataset.append(pjoin(FLAGS.data_dir, "val.ids.question"))
dataset.append(pjoin(FLAGS.data_dir, "val.ids.context"))
dataset.append(pjoin(FLAGS.data_dir, "val.span"))
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
encoder = Encoder(size=FLAGS.state_size, vocab_dim=FLAGS.embedding_size)
decoder = Decoder(output_size=FLAGS.paragraph_output_size)
qa = QASystem(encoder, decoder)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, dataset, save_train_dir)
def main(_):
config = Config()
dataset = None # TODO ;load dateset ??? - look at dataset and seenhow it loooks - change model.py accordingly
embed_path = config.embed_path or pjoin("data", "squad", "glove.trimmed.{}.npz".format(config.embed_size))
embeddingz = np.load(embed_path)
embeddings = embeddingz['glove']
embeddingz.close()
vocab_len = embeddings.shape[0]
train = load_squad(config.data_dir, "train", vocab_len, config.data_dir, max_samples=config.max_train_samples)
val = load_squad(config.data_dir, "val", vocab_len, config.data_dir, max_samples=config.max_val_samples)
print('train size: ', len(train), ' val size: ', len(val))
vocab_path = config.vocab_path or pjoin(config.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
# print_samples(train,1, rev_vocab) #train is triplets of (context,question,answer)
encoder = Encoder(state_size=config.hidden_size, embedding_size=config.embed_size)
decoder = Decoder(state_size=config.hidden_size, embedding_size=config.embed_size)
qa = QASystem(encoder, decoder)
with tf.Session() as sess:
load_train_dir = (config.load_train_dir or config.train_dir) # put "" here if you want to build a new model
initialize_model(sess, qa, load_train_dir)
save_train_dir = config.train_dir
ds_train = qa.pad_sequences(train)
ret_q, ret_p, ret_labels = ds_train
qa.train(sess, ds_train, save_train_dir)
ds_val = qa.pad_sequences(val)
print('train error')
qa.evaluate_answer(sess, ds_train, log=True)
print('val error')
qa.evaluate_answer(sess, ds_val, log=True)
def main(FLAGS):
print(80 * "=")
print("INITIALIZING")
print(80 * "=")
# Do what you need to load datasets from FLAGS.data_dir
#parser, embeddings, train_examples, dev_set, test_set = load_and_preprocess_data(debug)
if not os.path.exists('./data/weights/'):
os.makedirs('./data/weights/')
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
print("Loading Embedding Matrix")
embeddings = np.load(embed_path)['glove']
encoder = Encoder(size=FLAGS.output_size, vocab_dim=FLAGS.embedding_size)
decoder = Decoder(output_size=FLAGS.output_size)
qa = QASystem(encoder, decoder, FLAGS, embeddings)
#qa = QASystem(encoder, FLAGS, embeddings)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
with tf.Session() as sess:
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
print("Building Network ... ")
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
print("Load Training Data")
dataset = initialize_datasets(FLAGS.data_dir,
dataset='train',
debugMode=True)
# encoder.encode_question(
# dataset['Questions'], question['Questions_masks'])
print(80 * "=")
print("Training")
print(80 * "=")
qa.train(sess, dataset, save_train_dir)
print("Finished Training")
print("Load Validation Data")
dataset = initialize_datasets(FLAGS.data_dir,
dataset='val',
debugMode=True)
print(80 * "=")
print("Evaluation")
print(80 * "=")
qa.evaluate_answer(sess, dataset, vocab, FLAGS.evaluate, log=True)
def main(_):
# Do what you need to load datasets from FLAGS.data_dir
embed_path = FLAGS.embed_path or pjoin(
"data", "squad", "glove.trimmed.{}.npz".format(FLAGS.embedding_size))
vocab_path = FLAGS.vocab_path or pjoin(FLAGS.data_dir, "vocab.dat")
vocab, rev_vocab = initialize_vocab(vocab_path)
train_path = 'data/squad'
val_path = 'data/squad'
config = Config(embed_path, train_path, val_path)
encoder = EncoderCoattention(config)
decoder = DecoderDynamic(config)
qa = QASystem(encoder, decoder, config)
if not os.path.exists(FLAGS.log_dir):
os.makedirs(FLAGS.log_dir)
file_handler = logging.FileHandler(pjoin(FLAGS.log_dir, "log.txt"))
logging.getLogger().addHandler(file_handler)
print(vars(FLAGS))
with open(os.path.join(FLAGS.log_dir, "flags.json"), 'w') as fout:
json.dump(FLAGS.__flags, fout)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
load_train_dir = get_normalized_train_dir(FLAGS.load_train_dir
or FLAGS.train_dir)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(FLAGS.train_dir)
qa.train(sess, save_train_dir)
def run_func(model_name):
train = SquadData.load(config.SQUAD_TRAIN_PREFIX, size=config.TRAIN_SIZE)
dev = SquadData.load(config.SQUAD_DEV_PREFIX, size=config.EVAL_SIZE)
qa = QASystem(model_name)
with tf.Session() as sess:
# ====== Load a pretrained model if it exists or create a new one if no pretrained available ======
qa.initialize_model(sess)
qa.train(sess, [train, dev])
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(_):
c_time = time.strftime('%Y%m%d_%H%M', time.localtime())
args = parse_arg()
update_config(args, c_time)
# pprint.pprint(cfg)
logging.info(cfg)
if args.test:
pdb.set_trace()
data_dir = cfg.DATA_DIR
set_names = cfg.set_names
suffixes = cfg.suffixes
dataset = mask_dataset(data_dir, set_names, suffixes)
answers = read_answers(data_dir)
raw_answers = read_raw_answers(data_dir)
vocab_path = pjoin(data_dir, cfg.vocab_file)
vocab, rev_vocab = initialize_vocab(vocab_path)
embed_path = pjoin(data_dir, "glove.trimmed." + str(cfg.embed_size) + ".npz")
# logging.info('embed size: {} for path {}'.format(cfg.embed_size, embed_path))
# embedding = np.load(embed_path)['glove']
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)
file_handler = logging.FileHandler(pjoin(cfg.log_dir, 'log' + c_time + '.txt'))
logging.getLogger().addHandler(file_handler)
print_parameters()
# 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, embed_path)
with tf.Session(config=config) as sess:
init = tf.global_variables_initializer()
sess.run(init)
load_train_dir = get_normalized_train_dir(cfg.train_dir)
logging.info('=========== trainable varaibles ============')
for i in tf.trainable_variables():
logging.info(i.name)
logging.info('=========== regularized varaibles ============')
for i in tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES):
logging.info(i.name)
initialize_model(sess, qa, load_train_dir)
save_train_dir = get_normalized_train_dir(cfg.train_dir)
if args.test:
qa.train(cfg.start_lr, sess, dataset, answers, save_train_dir,
raw_answers=raw_answers,
debug_num=100,
rev_vocab=rev_vocab)
else:
qa.train(cfg.start_lr, sess, dataset, answers, save_train_dir,
raw_answers=raw_answers,
rev_vocab=rev_vocab)
qa.evaluate_answer(sess, dataset, raw_answers, rev_vocab,
log=True,
training=True,
sample=4000)
