File size: 2,000 Bytes
593f3bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2025 ByteDance and/or its affiliates.
#
# 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.

import torch
from torch import nn


class LayerNorm(torch.nn.LayerNorm):
    """Layer normalization module.
    :param int nout: output dim size
    :param int dim: dimension to be normalized
    """

    def __init__(self, nout, dim=-1, eps=1e-5):
        """Construct an LayerNorm object."""
        super(LayerNorm, self).__init__(nout, eps=eps)
        self.dim = dim

    def forward(self, x):
        """Apply layer normalization.
        :param torch.Tensor x: input tensor
        :return: layer normalized tensor
        :rtype torch.Tensor
        """
        if self.dim == -1:
            return super(LayerNorm, self).forward(x)
        return super(LayerNorm, self).forward(x.transpose(1, -1)).transpose(1, -1)


class Reshape(nn.Module):
    def __init__(self, *args):
        super(Reshape, self).__init__()
        self.shape = args

    def forward(self, x):
        return x.view(self.shape)


class Permute(nn.Module):
    def __init__(self, *args):
        super(Permute, self).__init__()
        self.args = args

    def forward(self, x):
        return x.permute(self.args)


def Embedding(num_embeddings, embedding_dim, padding_idx=None):
    m = nn.Embedding(num_embeddings, embedding_dim, padding_idx=padding_idx)
    nn.init.normal_(m.weight, mean=0, std=embedding_dim ** -0.5)
    if padding_idx is not None:
        nn.init.constant_(m.weight[padding_idx], 0)
    return m