File size: 3,722 Bytes
a89d9fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
# copyright (c) 2021 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle
from paddle import nn
class CosineEmbeddingLoss(nn.Layer):
def __init__(self, margin=0.):
super(CosineEmbeddingLoss, self).__init__()
self.margin = margin
self.epsilon = 1e-12
def forward(self, x1, x2, target):
similarity = paddle.sum(
x1 * x2, axis=-1) / (paddle.norm(
x1, axis=-1) * paddle.norm(
x2, axis=-1) + self.epsilon)
one_list = paddle.full_like(target, fill_value=1)
out = paddle.mean(
paddle.where(
paddle.equal(target, one_list), 1. - similarity,
paddle.maximum(
paddle.zeros_like(similarity), similarity - self.margin)))
return out
class AsterLoss(nn.Layer):
def __init__(self,
weight=None,
size_average=True,
ignore_index=-100,
sequence_normalize=False,
sample_normalize=True,
**kwargs):
super(AsterLoss, self).__init__()
self.weight = weight
self.size_average = size_average
self.ignore_index = ignore_index
self.sequence_normalize = sequence_normalize
self.sample_normalize = sample_normalize
self.loss_sem = CosineEmbeddingLoss()
self.is_cosin_loss = True
self.loss_func_rec = nn.CrossEntropyLoss(weight=None, reduction='none')
def forward(self, predicts, batch):
targets = batch[1].astype("int64")
label_lengths = batch[2].astype('int64')
sem_target = batch[3].astype('float32')
embedding_vectors = predicts['embedding_vectors']
rec_pred = predicts['rec_pred']
if not self.is_cosin_loss:
sem_loss = paddle.sum(self.loss_sem(embedding_vectors, sem_target))
else:
label_target = paddle.ones([embedding_vectors.shape[0]])
sem_loss = paddle.sum(
self.loss_sem(embedding_vectors, sem_target, label_target))
# rec loss
batch_size, def_max_length = targets.shape[0], targets.shape[1]
mask = paddle.zeros([batch_size, def_max_length])
for i in range(batch_size):
mask[i, :label_lengths[i]] = 1
mask = paddle.cast(mask, "float32")
max_length = max(label_lengths)
assert max_length == rec_pred.shape[1]
targets = targets[:, :max_length]
mask = mask[:, :max_length]
rec_pred = paddle.reshape(rec_pred, [-1, rec_pred.shape[2]])
input = nn.functional.log_softmax(rec_pred, axis=1)
targets = paddle.reshape(targets, [-1, 1])
mask = paddle.reshape(mask, [-1, 1])
output = -paddle.index_sample(input, index=targets) * mask
output = paddle.sum(output)
if self.sequence_normalize:
output = output / paddle.sum(mask)
if self.sample_normalize:
output = output / batch_size
loss = output + sem_loss * 0.1
return {'loss': loss}
|