File size: 1,909 Bytes
1e84a23 c5966ab 54795a4 1e84a23 f346da9 1e84a23 f346da9 1e84a23 f346da9 1e84a23 f346da9 1e84a23 f346da9 1e84a23 f346da9 1e84a23 f346da9 1e84a23 f346da9 131782a f346da9 4b074d9 f346da9 4b074d9 131782a 4b074d9 |
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 |
import torch
import torch.nn as nn
import torch.nn.functional as F
# Swish https://arxiv.org/pdf/1905.02244.pdf ---------------------------------------------------------------------------
class Swish(nn.Module): #
@staticmethod
def forward(x):
return x * torch.sigmoid(x)
class MemoryEfficientSwish(nn.Module):
class F(torch.autograd.Function):
@staticmethod
def forward(ctx, x):
ctx.save_for_backward(x)
return x * torch.sigmoid(x)
@staticmethod
def backward(ctx, grad_output):
x = ctx.saved_tensors[0]
sx = torch.sigmoid(x)
return grad_output * (sx * (1 + x * (1 - sx)))
def forward(self, x):
return self.F.apply(x)
# 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)
self.bn = nn.BatchNorm2d(c1)
def forward(self, x):
return torch.max(x, self.bn(self.conv(x)))
|