【pytorch】孪生网络Siamese network入门教程

这篇博客介绍了如何使用PyTorch实现一个Siamese网络进行人脸识别。通过AT&T人脸数据集训练,网络采用了卷积神经网络,并定义了对比损失函数进行相似性学习。数据预处理、训练配置、损失可视化以及模型训练过程都得到了详细说明。
摘要由CSDN通过智能技术生成

论文原文:《Learning a Similarity Metric Discriminatively, with Application to Face
Verification》
http://yann.lecun.com/exdb/publis/pdf/chopra-05.pdf

1. 数据集

数据采用的是AT&T人脸数据。共40个人,每个人有10张脸。数据集下载:AT&T

2. Imports

All the imports are defined here

import torchvision
import torchvision.datasets as dset
import torchvision.transforms as transforms
from torch.utils.data import DataLoader,Dataset
import matplotlib.pyplot as plt
import torchvision.utils
import numpy as np
import random
from PIL import Image
import torch
from torch.autograd import Variable
import PIL.ImageOps    
import torch.nn as nn
from torch import optim
import torch.nn.functional as F
3. Helper functions

Set of helper functions

def imshow(img,text=None,should_save=False):
    npimg = img.numpy()
    plt.axis("off")
    if text:
        plt.text(75, 8, text, style='italic',fontweight='bold',
            bbox={'facecolor':'white', 'alpha':0.8, 'pad':10})
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()    

def show_plot(iteration,loss):
    plt.plot(iteration,loss)
    plt.show()
4. Configuration Class

A simple class to manage configuration

class Config():
    training_dir = "./data/faces/training/"
    testing_dir = "./data/faces/testing/"
    train_batch_size = 64
    train_number_epochs = 100
5. Custom Dataset Class

This dataset generates a pair of images. 0 for geniune pair and 1 for imposter pair

class SiameseNetworkDataset(Dataset):
    
    def __init__(self,imageFolderDataset,transform=None,should_invert=True):
        self.imageFolderDataset = imageFolderDataset    
        self.transform = transform
        self.should_invert = should_invert
        
    def __getitem__(self,index):
        img0_tuple = random.choice(self.imageFolderDataset.imgs)
        #we need to make sure approx 50% of images are in the same class
        should_get_same_class = random.randint(0,1) 
        if should_get_same_class:
            while True:
                #keep looping till the same class image is found
                img1_tuple = random.choice(self.imageFolderDataset.imgs) 
                if img0_tuple[1]==img1_tuple[1]:
                    break
        else:
            while True:
                #keep looping till a different class image is found
                
                img1_tuple = random.choice(self.imageFolderDataset.imgs) 
                if img0_tuple[1] !=img1_tuple[1]:
                    break

        img0 = Image.open(img0_tuple[0])
        img1 = Image.open(img1_tuple[0])
        img0 = img0.convert("L")
        img1 = img1.convert("L")
        
        if self.should_invert:
            img0 = PIL.ImageOps.invert(img0)
            img1 = PIL.ImageOps.invert(img1)

        if self.transform is not None:
            img0 = self.transform(img0)
            img1 = self.transform(img1)
        
        return img0, img1 , torch.from_numpy(np.array([int(img1_tuple[1]!=img0_tuple[1])],dtype=np.float32))
    
    def __len__(self):
        return len(self.imageFolderDataset.imgs)
6. Using Image Folder Dataset
folder_dataset = dset.ImageFolder(root=Config.training_dir)
siamese_dataset = SiameseNetworkDataset(imageFolderDataset=folder_dataset,
                                        transform=transforms.Compose([transforms.Resize((100,100)),
                                                                      transforms.ToTensor()
                                                                      ])
                                       ,should_invert=False)
7. Visualising some of the data

The top row and the bottom row of any column is one pair. The 0s and 1s correspond to the column of the image. 1 indiciates dissimilar, and 0 indicates similar.

vis_dataloader = DataLoader(siamese_dataset,
                        shuffle=True,
                        num_workers=8,
                        batch_size=8)
dataiter = iter(vis_dataloader)


example_batch = next(dataiter)
concatenated = torch.cat((example_batch[0],example_batch[1]),0)
imshow(torchvision.utils.make_grid(concatenated))
print(example_batch[2].numpy())

在这里插入图片描述
[[1.]
[1.]
[0.]
[0.]
[1.]
[1.]
[1.]
[1.]]

8. Neural Net Definition

We will use a standard convolutional neural network

class SiameseNetwork(nn.Module):
    def __init__(self):
        super(SiameseNetwork, self).__init__()
        self.cnn1 = nn.Sequential(
            nn.ReflectionPad2d(1),
            nn.Conv2d(1, 4, kernel_size=3),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(4),
            
            nn.ReflectionPad2d(1),
            nn.Conv2d(4, 8, kernel_size=3),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(8),


            nn.ReflectionPad2d(1),
            nn.Conv2d(8, 8, kernel_size=3),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(8),


        )

        self.fc1 = nn.Sequential(
            nn.Linear(8*100*100, 500),
            nn.ReLU(inplace=True),

            nn.Linear(500, 500),
            nn.ReLU(inplace=True),

            nn.Linear(500, 5))

    def forward_once(self, x):
        output = self.cnn1(x)
        output = output.view(output.size()[0], -1)
        output = self.fc1(output)
        return output

    def forward(self, input1, input2):
        output1 = self.forward_once(input1)
        output2 = self.forward_once(input2)
        return output1, output2
9. Contrastive Loss
class ContrastiveLoss(torch.nn.Module):
    """
    Contrastive loss function.
    Based on: http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
    """

    def __init__(self, margin=2.0):
        super(ContrastiveLoss, self).__init__()
        self.margin = margin

    def forward(self, output1, output2, label):
        euclidean_distance = F.pairwise_distance(output1, output2, keepdim = True)
        loss_contrastive = torch.mean((1-label) * torch.pow(euclidean_distance, 2) +
                                      (label) * torch.pow(torch.clamp(self.margin - euclidean_distance, min=0.0), 2))


        return loss_contrastive
10. Training Time!
train_dataloader = DataLoader(siamese_dataset,
                        shuffle=True,
                        num_workers=8,
                        batch_size=Config.train_batch_size)

net = SiameseNetwork().cuda()
criterion = ContrastiveLoss()
optimizer = optim.Adam(net.parameters(),lr = 0.0005 )

counter = []
loss_history = [] 
iteration_number= 0

for epoch in range(0,Config.train_number_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()
        if i %10 == 0 :
            print("Epoch number {}\n Current loss {}\n".format(epoch,loss_contrastive.item()))
            iteration_number +=10
            counter.append(iteration_number)
            loss_history.append(loss_contrastive.item())
show_plot(counter,loss_history)

在这里插入图片描述

参考

https://blog.csdn.net/yukai08008/article/details/108236724

https://www.cnblogs.com/king-lps/p/8342452.html

https://github.com/harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch/

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

机器不学习我学习

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值