for i in range(num_iter):
p, p_mask, q, q_mask, c, c_mask, y = batchify(
train_data[i * batch_size:(i + 1) * batch_size])
# print("passage", p, "\n", len(p), type(p))
# print("passage mask", p_mask, "\n", len(p_mask), type(p_mask))
# print("choice", c, "\n", len(c), type(c))
# print("choice mask", c_mask, "\n", len(c_mask), type(c_mask))
# print("question ", q, "\n", len(q), type(q))
# print("question mask", q_mask, "\n", len(q_mask), type(q_mask))
break
for i in range(epochs):
print('Epoch %d...' % i)
if i == 0:
dev_acc = model.evaluate(dev_data)
print('Dev accuracy: %f' % dev_acc)
start_time = time.time()
np.random.shuffle(train_data)
cur_train_data = train_data
#####################x
iter_cnt, num_iter = 0, (len(train_data) + batch_size -
1) // batch_size
for j in range(num_iter):
batch_input = batchify(train_data[j * batch_size:(j + 1) *
batch_size])
feed_input = [x for x in batch_input[:-1]]
y = batch_input[-1]
print(feed_input)
import sys
