File size: 1,097 Bytes
62a0e4e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) Meta Platforms, Inc. and affiliates.
#
# This source code is licensed under the Apache License, Version 2.0
# found in the LICENSE file in the root directory of this source tree.

# Modified from: https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py#L103-L110

from typing import Optional, Union

import torch
from torch import Tensor
from torch import nn


class LayerScale(nn.Module):
    def __init__(
        self,
        dim: int,
        init_values: Union[float, Tensor] = 1e-5,
        inplace: bool = False,
        device: Optional[torch.device] = None,
        dtype: Optional[torch.dtype] = None,
    ) -> None:
        super().__init__()
        self.inplace = inplace
        self.init_values = init_values
        self.gamma = nn.Parameter(torch.empty(dim, device=device, dtype=dtype))
        self.reset_parameters()

    def reset_parameters(self):
        nn.init.constant_(self.gamma, self.init_values)

    def forward(self, x: Tensor) -> Tensor:
        return x.mul_(self.gamma) if self.inplace else x * self.gamma