File size: 3,777 Bytes
24bea5e
 
 
 
fe341fa
1e84a23
c5966ab
54795a4
1e84a23
 
fea9c9b
6bd5e8b
1e84a23
 
f346da9
1e84a23
 
4d7f222
71209a6
 
00e308f
 
71209a6
 
f346da9
 
1e84a23
f346da9
 
1e84a23
 
 
f346da9
 
 
 
 
 
 
 
 
 
 
 
1e84a23
f346da9
 
131782a
 
f346da9
4b074d9
 
f346da9
94a7f55
4b074d9
131782a
4b074d9
 
264d860
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9c7bb5a
 
 
 
264d860
 
 
9c7bb5a
 
 
264d860
 
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
101
102
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Activation functions
"""

import torch
import torch.nn as nn
import torch.nn.functional as F


# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
    @staticmethod
    def forward(x):
        return x * torch.sigmoid(x)


class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
    @staticmethod
    def forward(x):
        # return x * F.hardsigmoid(x)  # for TorchScript and CoreML
        return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0  # for TorchScript, CoreML and ONNX


# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
class Mish(nn.Module):
    @staticmethod
    def forward(x):
        return x * F.softplus(x).tanh()


class MemoryEfficientMish(nn.Module):
    class F(torch.autograd.Function):
        @staticmethod
        def forward(ctx, x):
            ctx.save_for_backward(x)
            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))

        @staticmethod
        def backward(ctx, grad_output):
            x = ctx.saved_tensors[0]
            sx = torch.sigmoid(x)
            fx = F.softplus(x).tanh()
            return grad_output * (fx + x * sx * (1 - fx * fx))

    def forward(self, x):
        return self.F.apply(x)


# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
class FReLU(nn.Module):
    def __init__(self, c1, k=3):  # ch_in, kernel
        super().__init__()
        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
        self.bn = nn.BatchNorm2d(c1)

    def forward(self, x):
        return torch.max(x, self.bn(self.conv(x)))


# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
class AconC(nn.Module):
    r""" ACON activation (activate or not).
    AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
    """

    def __init__(self, c1):
        super().__init__()
        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))

    def forward(self, x):
        dpx = (self.p1 - self.p2) * x
        return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x


class MetaAconC(nn.Module):
    r""" ACON activation (activate or not).
    MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
    """

    def __init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r
        super().__init__()
        c2 = max(r, c1 // r)
        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
        self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
        # self.bn1 = nn.BatchNorm2d(c2)
        # self.bn2 = nn.BatchNorm2d(c1)

    def forward(self, x):
        y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
        # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
        # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y)))))  # bug/unstable
        beta = torch.sigmoid(self.fc2(self.fc1(y)))  # bug patch BN layers removed
        dpx = (self.p1 - self.p2) * x
        return dpx * torch.sigmoid(beta * dpx) + self.p2 * x