第P6周：VGG-16-Pytorch实现人脸识别_pytorch人脸识别模型-优快云博客

本文链接：https://blog.youkuaiyun.com/weixin_59907394/article/details/145936873

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊

一.前期准备

1.设置GPU

import torch
import torch.nn as nn
from torchvision import datasets,transforms
import PIL,os,pathlib,warnings

device=torch.device('cuda' if torch.cuda.is_available() else 'cpu')
device

2.导入数据

data_dir='./data/48-data/'
data_dir=pathlib.Path(data_dir)

data_path=list(data_dir.glob('*'))
classeNames=[str(path).split('\\')[2] for path in data_path]
classeNames

train_transforms=transforms.Compose([
    transforms.Resize([224,224]),
    transforms.ToTensor(),
    transforms.Normalize(
        mean=[0.485,0.456,0.406],
        std=[0.229,0.224,0.225]
    )
])
total_data=datasets.ImageFolder('./data/48-data/',transform=train_transforms)
total_data

total_data.class_to_idx

3.划分数据集

train_size=int(0.8*len(total_data))
test_size=len(total_data)-train_size
train_dataset,test_dataset=torch.utils.data.random_split(total_data,[train_size,test_size])
train_dataset,test_dataset

batch_size=32

train_dl=torch.utils.data.DataLoader(train_dataset,
                                     batch_size=batch_size,
                                     shuffle=True,
                                     num_workers=1)
test_dl=torch.utils.data.DataLoader(test_dataset,
                                    batch_size=batch_size,
                                    shuffle=True,
                                    num_workers=1)

for X,y in train_dl:
    print('shape of X[N,C,H,W]:',X.shape)
    print('shape of y:',y.shape,y.dtype)
    break

二.调用官方的VGG-16模型

from torchvision.models import vgg16

model=vgg16(pretrained=True).to(device)

for param in model.parameters():
    param.requires_grad = False  #冻结模型的参数，只训练最后一层的参数

#修改classifier模块的第6层
model.classifier[6]=nn.Linear(4096,len(classeNames))
model.to(device)
model

三.训练模型

1.编写训练函数

def train(dataloader,model,loss_fn,optimizer):
    size=len(dataloader.dataset)
    num_batches=len(dataloader)
    train_acc,train_loss=0,0

    for X,y in dataloader:
        X,y=X.to(device),y.to(device)

        pred=model(X)
        loss=loss_fn(pred,y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        train_acc+=(pred.argmax(1)==y).type(torch.float).sum().item()
        train_loss+=loss.item()

    train_acc/=size
    train_loss/=num_batches

    return train_acc,train_loss

2.编写测试函数

def test(dataloader,model,loss_fn):
    size=len(dataloader.dataset)
    num_batches=len(dataloader)
    test_loss,test_acc=0,0

    with torch.no_grad():
        for img,target in dataloader:
            img,target=img.to(device),target.to(device)

            target_pred=model(img)
            loss=loss_fn(target_pred,target)

            test_loss+=loss.item()
            test_acc+=(target_pred.argmax(1)==target).type(torch.float).sum().item()

    test_acc/=size
    test_loss/=num_batches

    return test_acc,test_loss

3.设置动态学习率

learn_rate=1e-4
lambda1=lambda epoch: 0.92 ** (epoch // 4)
optimizer=torch.optim.Adam(model.parameters(),lr=learn_rate)
scheduler=torch.optim.lr_scheduler.LambdaLR(optimizer,lr_lambda=lambda1)

4.正式训练

import copy

loss_fn=nn.CrossEntropyLoss()
epochs=40

train_acc=[]
train_loss=[]
test_acc=[]
test_loss=[]

best_acc=0

for epoch in range(epochs):
    model.train()
    epoch_train_acc,epoch_train_loss=train(train_dl,model,loss_fn,optimizer)
    scheduler.step()

    model.eval()
    epoch_test_acc,epoch_test_loss=test(test_dl,model,loss_fn)

    if epoch_test_acc >best_acc:
        best_acc=epoch_test_acc
        best_model=copy.deepcopy(model)

    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)

    lr=optimizer.state_dict()['param_groups'][0]['lr']

    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss,
                          epoch_test_acc*100, epoch_test_loss, lr))

PATH='./best/best_model.pth'
torch.save(model.state_dict(),PATH)

print('Done')

四.结果可视化

1.Loss与Accuracy图

import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')

plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.rcParams['figure.dpi']=100

from datetime import datetime
current_time=datetime.now()

epochs_range=range(epochs)

plt.figure(figsize=(12,3))
plt.subplot(1,2,1)
plt.plot(epochs_range,train_acc,label='Training Accuracy')
plt.plot(epochs_range,test_acc,label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.xlabel(current_time)

plt.subplot(1,2,2)
plt.plot(epochs_range,train_loss,label='Training Loss')
plt.plot(epochs_range,test_loss,label='Test Loss')
plt.legend(loc='upper right')
plt.title('Train and Test Loss')
plt.show()

2.指定图片进行预测

from PIL import Image

classes=list(total_data.class_to_idx)

def predict_one_image(image_path,model,transform,classes):
    test_img=Image.open(image_path).convert('RGB')
    plt.imshow(test_img)

    test_img=transform(test_img)
    img=test_img.to(device).unsqueeze(0)

    model.eval()
    output=model(img)

    _,pred=torch.max(output,1)
    pred_class=classes[pred]
    print(f'预测结果是:{pred_class}')

predict_one_image(image_path='./data/48-data/Angelina Jolie/003_57612506.jpg',
                  model=model,
                  transform=train_transforms,
                  classes=classes)

3.模型评估

best_model.eval()
epoch_test_acc,epoch_test_loss=test(test_dl,best_model,loss_fn)

epoch_test_acc,epoch_test_loss

使用了迁移学习的方法，通过加载 VGG16 预训练模型，并在其基础上修改最后一层，使其适应新的分类任务，数据被分为训练集和测试集，并经过归一化等预处理后喂入模型进行训练，优化器采用 Adam，并结合学习率调度器逐步调整学习率，整个训练过程中，模型不断优化，最终选择表现最好的模型进行保存，并通过可视化方式展示训练过程中的准确率和损失变化，同时提供了一个单张图片预测的功能，能够方便地对新图片进行分类预测。