人脸识别 FaceNet人脸识别（一种人脸识别与聚类的统一嵌入表示）

FaceNet的简介

Facenet的实现思路

import torch.nn as nn


def conv_bn(inp, oup, stride = 1):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU6()
    )
    
def conv_dw(inp, oup, stride = 1):
    return nn.Sequential(
        nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
        nn.BatchNorm2d(inp),
        nn.ReLU6(),

        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU6(),
    )

class MobileNetV1(nn.Module):
    def __init__(self):
        super(MobileNetV1, self).__init__()
        self.stage1 = nn.Sequential(
            # 160,160,3 -> 80,80,32
            conv_bn(3, 32, 2), 
            # 80,80,32 -> 80,80,64
            conv_dw(32, 64, 1), 

            # 80,80,64 -> 40,40,128
            conv_dw(64, 128, 2),
            conv_dw(128, 128, 1),

            # 40,40,128 -> 20,20,256
            conv_dw(128, 256, 2),
            conv_dw(256, 256, 1),
        )
        self.stage2 = nn.Sequential(
            # 20,20,256 -> 10,10,512
            conv_dw(256, 512, 2),
            conv_dw(512, 512, 1),
            conv_dw(512, 512, 1),
            conv_dw(512, 512, 1),
            conv_dw(512, 512, 1),
            conv_dw(512, 512, 1),
        )
        self.stage3 = nn.Sequential(
            # 10,10,512 -> 5,5,1024
            conv_dw(512, 1024, 2),
            conv_dw(1024, 1024, 1),
        )

        self.avg = nn.AdaptiveAvgPool2d((1,1))
        self.fc = nn.Linear(1024, 1000)

    def forward(self, x):
        x = self.stage1(x)
        x = self.stage2(x)
        x = self.stage3(x)
        x = self.avg(x)
        # x = self.model(x)
        x = x.view(-1, 1024)
        x = self.fc(x)
        return x

class Facenet(nn.Module):
    def __init__(self, backbone="mobilenet", dropout_keep_prob=0.5, embedding_size=128, num_classes=None, mode="train"):  
        super(Facenet, self).__init__()
        if backbone == "mobilenet":
            self.backbone = mobilenet()
            flat_shape = 1024
        elif backbone == "inception_resnetv1":
            self.backbone = inception_resnet()
            flat_shape = 1792
        else:
            raise ValueError('Unsupported backbone - `{}`, Use mobilenet, inception_resnetv1.'.format(backbone))
        self.avg = nn.AdaptiveAvgPool2d((1,1))
        self.Dropout = nn.Dropout(1 - dropout_keep_prob)
        self.Bottleneck = nn.Linear(flat_shape, embedding_size,bias=False)
        self.last_bn = nn.BatchNorm1d(embedding_size, eps=0.001, momentum=0.1, affine=True)
        if mode == "train":
            self.classifier = nn.Linear(embedding_size, num_classes)

    def forward(self, x):
        x = self.backbone(x)
        x = self.avg(x)
        x = x.view(x.size(0), -1)
        x = self.Dropout(x)
        x = self.Bottleneck(x)
        x = self.last_bn(x)
        x = F.normalize(x, p=2, dim=1)
        return x

    def forward_feature(self, x):
        x = self.backbone(x)
        x = self.avg(x)
        x = x.view(x.size(0), -1)
        x = self.Dropout(x)
        x = self.Bottleneck(x)
        before_normalize = self.last_bn(x)
        x = F.normalize(before_normalize, p=2, dim=1)
        return before_normalize, x

    def forward_classifier(self, x):
        x = self.classifier(x)
        return x

在pytorch代码中，只需要一行就可以实现l2标准化的层。

class Facenet(nn.Module):
    def __init__(self, backbone="mobilenet", dropout_keep_prob=0.5, embedding_size=128, num_classes=None, mode="train"): 
        super(Facenet, self).__init__()
        if backbone == "mobilenet":
            self.backbone = mobilenet()
            flat_shape = 1024
        elif backbone == "inception_resnetv1":
            self.backbone = inception_resnet()
            flat_shape = 1792
        else:
            raise ValueError('Unsupported backbone - `{}`, Use mobilenet, inception_resnetv1.'.format(backbone))
        self.avg = nn.AdaptiveAvgPool2d((1,1))
        self.Dropout = nn.Dropout(1 - dropout_keep_prob)
        self.Bottleneck = nn.Linear(flat_shape, embedding_size,bias=False)
        self.last_bn = nn.BatchNorm1d(embedding_size, eps=0.001, momentum=0.1, affine=True)
        if mode == "train":
            self.classifier = nn.Linear(embedding_size, num_classes)

    def forward(self, x):
        x = self.backbone(x)
        x = self.avg(x)
        x = x.view(x.size(0), -1)
        x = self.Dropout(x)
        x = self.Bottleneck(x)
        x = self.last_bn(x)
        x = F.normalize(x, p=2, dim=1)
        return x

    def forward_feature(self, x):
        x = self.backbone(x)
        x = self.avg(x)
        x = x.view(x.size(0), -1)
        x = self.Dropout(x)
        x = self.Bottleneck(x)
        before_normalize = self.last_bn(x)
        x = F.normalize(before_normalize, p=2, dim=1)
        return before_normalize, x

    def forward_classifier(self, x):
        x = self.classifier(x)
        return x

class Facenet(nn.Module):
    def __init__(self, backbone="mobilenet", dropout_keep_prob=0.5, embedding_size=128, num_classes=None, mode="train"):
        super(Facenet, self).__init__()
        if backbone == "mobilenet":
            self.backbone = mobilenet()
            flat_shape = 1024
        elif backbone == "inception_resnetv1":
            self.backbone = inception_resnet()
            flat_shape = 1792
        else:
            raise ValueError('Unsupported backbone - `{}`, Use mobilenet, inception_resnetv1.'.format(backbone))
        self.avg = nn.AdaptiveAvgPool2d((1,1))
        self.Dropout = nn.Dropout(1 - dropout_keep_prob)
        self.Bottleneck = nn.Linear(flat_shape, embedding_size,bias=False)
        self.last_bn = nn.BatchNorm1d(embedding_size, eps=0.001, momentum=0.1, affine=True)
        if mode == "train":
            self.classifier = nn.Linear(embedding_size, num_classes)

    def forward(self, x):
        x = self.backbone(x)
        x = self.avg(x)
        x = x.view(x.size(0), -1)
        x = self.Dropout(x)
        x = self.Bottleneck(x)
        x = self.last_bn(x)
        x = F.normalize(x, p=2, dim=1)
        return x

    def forward_feature(self, x):
        x = self.backbone(x)
        x = self.avg(x)
        x = x.view(x.size(0), -1)
        x = self.Dropout(x)
        x = self.Bottleneck(x)
        before_normalize = self.last_bn(x)
        x = F.normalize(before_normalize, p=2, dim=1)
        return before_normalize, x

    def forward_classifier(self, x):
        x = self.classifier(x)
        return x

训练部分