arcface backbone

from torch.nn import Linear,Conv2d,BatchNorm1d,BatchNorm2d,PReLU,ReLU,Sigmoid,Dropout,MaxPool2d,AdaptiveAvgPool2d,Sequential,Module,Parameter
import torch
from collections import namedtuple
import math

class Flatten(Module):
    def forward(self, input):
        return input.view(input.size(0), -1)

def l2_norm(input,axis=1):
    norm = torch.norm(input,2,axis,True)
    output = torch.div(input, norm)
    return output

class SEModule(Module):
    def __init__(self,channels,reduction):
        super(SEModule,self).__init__()
        self.avg_pool =AdaptiveAvgPool2d(1)
        self.fc1 = Conv2d(
            channels,channels//reduction,kernel_size=1,padding=0,bias=False
        )
        self.relu = ReLU(inplace=True)
        self.fc2 = Conv2d(channels//reduction,channels,kernel_size=1,padding=0,bias=False)
        self.sigmoid =Sigmoid()

    def forward(self,x):
        module_input = x
        x =self.avg_pool(x)
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = self.sigmoid(x)
        return module_input * x

class bottleneck_IR