深入浅出孪生神经网络，手把手教你搭建起来 原创

#数据预处理和加载
class SiameseDataset():
    def __init__(self,training_csv=None,training_dir=None,transform=None):
        # used to prepare the labels and images path
        self.train_df=pd.read_csv(training_csv)
        self.train_df.columns =["image1","image2","label"]
        self.train_dir = training_dir    
        self.transform = transform

    def __getitem__(self,index):
        # 获取图像路径
        image1_path=os.path.join(self.train_dir,self.train_df.iat[index,0])
        image2_path=os.path.join(self.train_dir,self.train_df.iat[index,1])
        # Loading the image
        img0 = Image.open(image1_path)
        img1 = Image.open(image2_path)
        img0 = img0.convert("L")
        img1 = img1.convert("L")
        # 应用图像变换
        if self.transform is not None:
            img0 = self.transform(img0)
            img1 = self.transform(img1)
        return img0, img1 , th.from_numpy(np.array([int(self.train_df.iat[index,2])],dtype=np.float32))
    def __len__(self):
        return len(self.train_df)

# 从原始图像文件夹加载数据集
siamese_dataset = SiameseDataset(training_csv,training_dir,
                                        transform=transforms.Compose([transforms.Resize((105,105)),
                                                                      transforms.ToTensor()
                                                                      ])
                                       )

#创建孪生网络
class SiameseNetwork(nn.Module):
    def __init__(self):
        super(SiameseNetwork, self).__init__()
        # 设置CNN层序列
        self.cnn1 = nn.Sequential(
            nn.Conv2d(1, 96, kernel_size=11,stride=1),
            nn.ReLU(inplace=True),
            nn.LocalResponseNorm(5,alpha=0.0001,beta=0.75,k=2),
            nn.MaxPool2d(3, stride=2),
            
            nn.Conv2d(96, 256, kernel_size=5,stride=1,padding=2),
            nn.ReLU(inplace=True),
            nn.LocalResponseNorm(5,alpha=0.0001,beta=0.75,k=2),
            nn.MaxPool2d(3, stride=2),
            nn.Dropout2d(p=0.3),

            nn.Conv2d(256,384 , kernel_size=3,stride=1,padding=1),
            nn.ReLU(inplace=True),
            
            nn.Conv2d(384,256 , kernel_size=3,stride=1,padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(3, stride=2),
            nn.Dropout2d(p=0.3),
        )
        # 定义全连接层
        self.fc1 = nn.Sequential(
            nn.Linear(30976, 1024),
            nn.ReLU(inplace=True),
            nn.Dropout2d(p=0.5),
            
            nn.Linear(1024, 128),
            nn.ReLU(inplace=True),
            
            nn.Linear(128,2))
        
    def forward_once(self, x):
        # 前向传播
        output = self.cnn1(x)
        output = output.view(output.size()[0], -1)
        output = self.fc1(output)
        return output

    def forward(self, input1, input2):
        # 输入1的前向传播
        output1 = self.forward_once(input1)
        # 输入2的前向传播
        output2 = self.forward_once(input2)
        return output1, output2

class ContrastiveLoss(torch.nn.Module):
    """
    Contrastive loss function.
    Based on:
    """

    def __init__(self, margin=1.0):
        super(ContrastiveLoss, self).__init__()
        self.margin = margin

    def forward(self, x0, x1, y):
        # 欧几里得距离
        diff = x0 - x1
        dist_sq = torch.sum(torch.pow(diff, 2), 1)
        dist = torch.sqrt(dist_sq)

        mdist = self.margin - dist
        dist = torch.clamp(mdist, min=0.0)
        loss = y * dist_sq + (1 - y) * torch.pow(dist, 2)
        loss = torch.sum(loss) / 2.0 / x0.size()[0]
        return loss

# 声明孪生网络
net = SiameseNetwork().cuda()
# 声明损失函数
criterion = ContrastiveLoss()
# 声明优化器
optimizer = th.optim.Adam(net.parameters(), lr=1e-3, weight_decay=0.0005)
#训练模型
def train():
    loss=[] 
    counter=[]
    iteration_number = 0
    for epoch in range(1,config.epochs):
        for i, data in enumerate(train_dataloader,0):
            img0, img1 , label = data
            img0, img1 , label = img0.cuda(), img1.cuda() , label.cuda()
            optimizer.zero_grad()
            output1,output2 = net(img0,img1)
            loss_contrastive = criterion(output1,output2,label)
            loss_contrastive.backward()
            optimizer.step()    
        print("Epoch {}\n Current loss {}\n".format(epoch,loss_contrastive.item()))
        iteration_number += 10
        counter.append(iteration_number)
        loss.append(loss_contrastive.item())
    show_plot(counter, loss)   
    return net
#将设备设置为cuda
device = torch.device('cuda' if th.cuda.is_available() else 'cpu')
model = train()
torch.save(model.state_dict(), "model.pt")
print("Model Saved Successfully")

# 加载测试数据集
test_dataset = SiameseDataset(training_csv=testing_csv,training_dir=testing_dir,
                                        transform=transforms.Compose([transforms.Resize((105,105)),
                                                                      transforms.ToTensor()
                                                                      ])
                                       )

test_dataloader = DataLoader(test_dataset,num_workers=6,batch_size=1,shuffle=True)
#测试网络
count=0
for i, data in enumerate(test_dataloader,0): 
  x0, x1 , label = data
  concat = torch.cat((x0,x1),0)
  output1,output2 = model(x0.to(device),x1.to(device))

  eucledian_distance = F.pairwise_distance(output1, output2)
    
  if label==torch.FloatTensor([[0]]):
    label="Original Pair Of Signature"
  else:
    label="Forged Pair Of Signature"
    
  imshow(torchvision.utils.make_grid(concat))
  print("Predicted Eucledian Distance:-",eucledian_distance.item())
  print("Actual Label:-",label)
  count=count+1
  if count ==10:
     break