def train(self, sess, dw, dt, qw, qt, a, m_dw, m_qw, tt, tm, c, m_c, cl,
fnames, dropout, learning_rate):
"""
train model
Args:
- data: (object) containing training data
"""
feed_dict = {
self.doc: dw,
self.qry: qw,
self.doc_char: dt,
self.qry_char: qt,
self.target: a,
self.doc_mask: m_dw,
self.qry_mask: m_qw,
self.token: tt,
self.char_mask: tm,
self.cand: c,
self.cand_mask: m_c,
self.cloze: cl,
self.keep_prob: 1 - dropout,
self.lr: learning_rate
}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
loss, acc, _, = \
sess.run([self.loss, self.accuracy, self.updates], feed_dict)
return loss, acc
def validate(self, sess, data):
"""
test the model
"""
loss = acc = n_exmple = 0
tr = trange(len(data),
desc="loss: {:.3f}, acc: {:.3f}".format(0.0, 0.0),
leave=False)
for dw, dt, qw, qt, a, m_dw, m_qw, tt, \
tm, c, m_c, cl, fnames in data:
start = time.time()
feed_dict = {
self.doc: dw,
self.qry: qw,
self.doc_char: dt,
self.qry_char: qt,
self.target: a,
self.doc_mask: m_dw,
self.qry_mask: m_qw,
self.token: tt,
self.char_mask: tm,
self.cand: c,
self.cand_mask: m_c,
self.cloze: cl,
self.keep_prob: 1.,
self.lr: 0.
}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
_loss, _acc = sess.run([self.loss, self.accuracy], feed_dict)
n_exmple += dw.shape[0]
loss += _loss
acc += _acc
tr.set_description("loss: {:.3f}, acc: {:.3f}".format(
_loss, _acc / dw.shape[0]))
tr.update()
tr.close()
loss /= n_exmple
acc /= n_exmple
spend = (time.time() - start) / 60
statement = "loss: {:.3f}, acc: {:.3f}, time: {:.1f}(m)"\
.format(loss, acc, spend)
logging.info(statement)
return loss, acc
def train(self, sess, dw, dsw, dt, qw, qt, nw, a, m_dw, m_dsw, m_qw, tt,
tm, c, m_c, cl, fnames, dropout, learning_rate):
"""
train model
Args:
- data: (object) containing training data
"""
feed_dict = {self.doc_sent: dsw, self.qry: qw,
self.doc: dw, self.doc_mask: m_dw,
self.answer: a,
self.doc_sent_mask: m_dsw, self.qry_mask: m_qw,
self.candidate: c, self.candidate_mask: m_c, self.position: cl,
self.lr: learning_rate}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
loss, acc, _, test = \
sess.run([self.loss, self.accuracy, self.updates, self.test], feed_dict)
return loss, acc, test
def validate(self, sess, data):
"""
test the model
"""
loss = acc_p = acc_n = n_exmple = 0
tr = trange(
len(data),
desc="loss: {:.3f}, acc: {:.3f}".format(0.0, 0.0),
leave=False)
start = time.time()
for dw, dsw, dt, qw, qt, nw, a, m_dw, m_dsw, m_qw, tt, \
tm, c, m_c, cl, fnames in data:
feed_dict = {self.doc_sent: dsw, self.qry: qw,
self.doc: dw, self.doc_mask: m_dw,
self.answer: a,
self.doc_sent_mask: m_dsw, self.qry_mask: m_qw,
self.candidate: c, self.candidate_mask: m_c, self.position: cl,
self.lr: 0.0}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
_acc = sess.run(self.accuracy, feed_dict)
# _acc = sess.run(self.seq_length, feed_dict)
n_exmple += dw.shape[0]
acc_p += _acc
tr.set_description("loss: {:.3f}, acc: {:.3f}".
format(loss, _acc / dw.shape[0]))
tr.update()
tr.close()
'''
tr = trange(
len(data),
desc="loss: {:.3f}, acc: {:.3f}".format(0.0, 0.0),
leave=False)
start = time.time()
for dw, dsw, dt, qw, qt, nw, a, m_dw, m_dsw, m_qw, tt, \
tm, c, m_c, cl, fnames in data:
feed_dict = {self.doc_sent: dsw, self.qry: qw
self.doc: dw, self.doc_mask: m_dw,
self.answer: a,
self.doc_sent_mask: m_dsw, self.qry_mask: m_qw, self.neg_mask: m_qw,
self.candidate: c, self.candidate_mask: m_c, self.position: cl,
self.keep_prob: 1.0,
self.lr: 0.0}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
_acc = sess.run(self.accuracy, feed_dict)
acc_n += _acc
tr.set_description("loss: {:.3f}, acc: {:.3f}".
format(loss, _acc / dw.shape[0]))
tr.update()
tr.close()
'''
loss /= n_exmple
acc_p /= n_exmple
#acc_n /= n_exmple
spend = (time.time() - start) / 60
statement = "\nloss: {:.3f}, acc_p: {:.3f}\n" \
.format(loss, acc_p)
logging.info(statement)
return loss, acc_p
def validate(self, sess, data, write_results=False):
"""
test the model
"""
loss = acc = n_exmple = 0
tr = trange(len(data),
desc="loss: {:.3f}, acc: {:.3f}".format(0.0, 0.0),
leave=False)
for dw, dt, qw, qt, a, m_dw, m_qw, tt, \
tm, c, m_c, cl, fnames in data:
start = time.time()
feed_dict = {
self.doc: dw,
self.qry: qw,
self.doc_char: dt,
self.qry_char: qt,
self.target: a,
self.doc_mask: m_dw,
self.qry_mask: m_qw,
self.token: tt,
self.char_mask: tm,
self.cand: c,
self.cand_mask: m_c,
self.cloze: cl,
self.keep_prob: 1.,
self.lr: 0.
}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
_loss, _acc, pred_ans, attentions = sess.run(
[self.loss, self.accuracy, self.pred_ans, self.attentions],
feed_dict)
n_exmple += dw.shape[0]
loss += _loss
acc += _acc
tr.set_description("loss: {:.3f}, acc: {:.3f}".format(
_loss, _acc / dw.shape[0]))
tr.update()
if write_results:
for i, fname in enumerate(fnames):
doc_len = np.sum(m_dw[i])
qry_len = np.sum(m_qw[i])
result = {
'pred_ans': pred_ans[i],
'attentions': attentions[i, :, 0:doc_len, 0:qry_len],
'ans': a[i]
}
if pred_ans[i] == a[i]:
correct = 'correct'
else:
correct = 'incorrect'
question = os.path.basename(fname).split('.')[0]
pickle.dump(
result,
open(
'results/validation/{}/{}.pkl'.format(
correct, question), 'wb'))
tr.close()
loss /= n_exmple
acc /= n_exmple
merged = tf.summary.merge_all()
spend = (time.time() - start) / 60
statement = "loss: {:.3f}, acc: {:.3f}, time: {:.1f}(m)"\
.format(loss, acc, spend)
logging.info(statement)
return loss, acc
def train(self,
sess,
dw,
dt,
qw,
qt,
a,
m_dw,
m_qw,
tt,
tm,
c,
m_c,
cl,
fnames,
dropout,
learning_rate,
summary_step=False):
"""
train model
Args:
- data: (object) containing training data
"""
feed_dict = {
self.doc: dw,
self.qry: qw,
self.doc_char: dt,
self.qry_char: qt,
self.target: a,
self.doc_mask: m_dw,
self.qry_mask: m_qw,
self.token: tt,
self.char_mask: tm,
self.cand: c,
self.cand_mask: m_c,
self.cloze: cl,
self.keep_prob: 1 - dropout,
self.lr: learning_rate
}
if self.use_feat:
feat = prepare_input(dw, qw)
feed_dict += {self.feat: feat}
tf.summary.scalar('learning_rate', self.lr)
merged = tf.summary.merge_all()
options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
if summary_step:
loss, acc, _, summary = \
sess.run([self.loss, self.accuracy, self.updates, merged], feed_dict, options=options, run_metadata=run_metadata)
# Create the Timeline object, and write it to a json file
fetched_timeline = timeline.Timeline(run_metadata.step_stats)
chrome_trace = fetched_timeline.generate_chrome_trace_format()
with open('timeline_01.json', 'w') as f:
f.write(chrome_trace)
return loss, acc, summary
else:
loss, acc, _, = \
sess.run([self.loss, self.accuracy, self.updates], feed_dict, options=options, run_metadata=run_metadata)
# Create the Timeline object, and write it to a json file
fetched_timeline = timeline.Timeline(run_metadata.step_stats)
chrome_trace = fetched_timeline.generate_chrome_trace_format()
with open('timeline_01.json', 'w') as f:
f.write(chrome_trace)
return loss, acc