def parse_function(serialized):
features = {
'token_ids': tf.io.FixedLenFeature([sequence_length],
tf.int64),
}
features = tf.io.parse_single_example(serialized, features)
token_ids = features['token_ids']
segment = K.random_uniform(shape=[1],
minval=1,
maxval=sequence_length - 1,
dtype='int64')[0]
segment_ids = K.one_hot(segment + 1, sequence_length)
segment_ids = K.cast(K.cumsum(segment_ids), 'int64')
token_ids_1 = token_ids[:segment]
token_ids_2 = K.zeros([1], dtype='int64') + token_sep_id
token_ids_3 = token_ids[segment:-1]
token_ids = K.concatenate([token_ids_1, token_ids_2, token_ids_3])
x = {
'Input-Token': token_ids,
'Input-Segment': segment_ids,
}
y = {
'unilm_loss': K.zeros([1]),
'unilm_acc': K.zeros([1]),
}
return x, y
def compute_copy_loss(self, inputs, mask=None):
_, y_mask, y_true, _, y_pred = inputs
y_mask = K.cumsum(y_mask[:, ::-1], axis=1)[:, ::-1]
y_mask = K.cast(K.greater(y_mask, 0.5), K.floatx())
y_mask = y_mask[:, 1:] # mask标记，减少一位
y_pred = y_pred[:, :-1] # 预测序列，错开一位
loss = K.sparse_categorical_crossentropy(y_true, y_pred)
loss = K.sum(loss * y_mask) / K.sum(y_mask)
return loss
def compute_loss(self, inputs, mask=None):
q_start_in, q_end_in, q_label_in, ps_category, ps_heads, ps_tails = inputs
if mask is None:
mask = 1.0
else:
mask = K.cast(mask, K.floatx())
loss0 = K.sparse_categorical_crossentropy(q_label_in,
ps_category,
from_logits=True)
loss0 = K.mean(loss0)
loss0 = K.sum(loss0 * mask) / K.sum(mask)
loss1 = K.categorical_crossentropy(q_start_in,
ps_heads,
from_logits=True)
loss1 = K.mean(loss1)
ps_tails = ps_tails - (1 - K.cumsum(q_start_in, axis=1)) * 1e10
loss2 = K.mean(
K.categorical_crossentropy(q_end_in, ps_tails, from_logits=True))
loss2 = K.mean(loss2)
# 总的loss
return loss0 + loss1 + loss2
