Pytorch实现TripletAttention

Posted 2021-12-23 AI浩

# !/usr/bin/env python
# -- coding: utf-8 --

import torch
import torch.nn as nn
import torchvision


class ChannelPool(nn.Module):
    def forward(self, x):
        return torch.cat( (torch.max(x,1)[0].unsqueeze(1), torch.mean(x,1).unsqueeze(1)), dim=1 )


class SpatialGate(nn.Module):
    def __init__(self):
        super(SpatialGate, self).__init__()

        self.channel_pool = ChannelPool()
        self.conv = nn.Sequential(
            nn.Conv2d(in_channels=2, out_channels=1, kernel_size=7, stride=1, padding=3),
            nn.BatchNorm2d(1)
        )
        self.sigmod = nn.Sigmoid()

    def forward(self, x):
        out = self.conv(self.channel_pool(x))
        return out * self.sigmod(out)


class TripletAttention(nn.Module):
    def __init__(self, spatial=True):
        super(TripletAttention, self).__init__()
        self.spatial = spatial
        self.height_gate = SpatialGate()
        self.width_gate = SpatialGate()
        if self.spatial:
            self.spatial_gate = SpatialGate()

    def forward(self, x):
        x_perm1 = x.permute(0, 2, 1, 3).contiguous()
        x_out1 = self.height_gate(x_perm1)
        x_out1 = x_out1.permute(0, 2, 1, 3).contiguous()

        x_perm2 = x.permute(0, 3, 2, 1).contiguous()
        x_out2 = self.width_gate(x_perm2)
        x_out2 = x_out2.permute(0, 3, 2, 1).contiguous()

        if self.spatial:
            x_out3 = self.spatial_gate(x)
            return (1/3) * (x_out1 + x_out2 + x_out3)
        else:
            return (1/2) * (x_out1 + x_out2)



if __name__=='__main__':
    model = TripletAttention()
    print(model)

    input = torch.randn(1, 16, 256, 256)
    out = model(input)
    print(out.shape)