365天深度学习训练营 第P6周：好莱坞明星识别

• 🍨 本文为🔗365天深度学习训练营 内部限免文章（版权归 K同学啊 所有）
• 🍦 参考文章地址： 🔗第P6周：好莱坞明星识别 | 365天深度学习训练营
• 🍖 作者：K同学啊 | 接辅导、程序定制

我的环境：

• 语言环境：Python 3.6.8
• 编译器：jupyter notebook
• 深度学习环境：
  • torch==0.13.1、cuda==11.3
  • torchvision==1.12.1、cuda==11.3

一、前期工作

1. 设置 GPU

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
from torchvision import transforms, datasets

if __name__=='__main__':
    ''' 设置GPU '''
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    print("Using {} device\n".format(device))

Using cuda device

2. 导入数据

import os, PIL, pathlib
data_dir = 'D:/jupyter notebook/DL-100-days/datasets/48-data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[5] for path in data_paths]
print(classeNames)

['Angelina Jolie',
 'Brad Pitt',
 'Denzel Washington',
 'Hugh Jackman',
 'Jennifer Lawrence',
 'Johnny Depp',
 'Kate Winslet',
 'Leonardo DiCaprio',
 'Megan Fox',
 'Natalie Portman',
 'Nicole Kidman',
 'Robert Downey Jr',
 'Sandra Bullock',
 'Scarlett Johansson',
 'Tom Cruise',
 'Tom Hanks',
 'Will Smith']

train_transforms = transforms.Compose([
    transforms.Resize([224,224]),# resize输入图片
    transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensor
    transforms.Normalize(
        mean = [0.485, 0.456, 0.406],
        std = [0.229,0.224,0.225]) # 从数据集中随机抽样计算得到
])
 
total_data = datasets.ImageFolder(data_dir,transform=train_transforms)
total_data

Dataset ImageFolder
    Number of datapoints: 1800
    Root location: hlw
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=PIL.Image.BILINEAR)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

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])

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)

二、调用vgg-16模型

from torchvision.models import vgg16
    
model = vgg16(pretrained = True).to(device)
for param in model.parameters():
    param.requires_grad = False
 
model.classifier._modules['6'] = nn.Linear(4096,len(classNames))
 
model.to(device)

# 查看要训练的层
params_to_update = model.parameters()
# params_to_update = []
for name,param in model.named_parameters():
    if param.requires_grad == True:
#         params_to_update.append(param)
        print("\t",name)

三、训练模型

1. 设置超参数

# 优化器设置
optimizer = torch.optim.Adam(params_to_update, lr=1e-4)#要训练什么参数/
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.92)#学习率每5个epoch衰减成原来的1/10
loss_fn = nn.CrossEntropyLoss()

2. 编写训练函数

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共900张图片
    num_batches = len(dataloader)   # 批次数目，29（900/32）
 
    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率
    
    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)
        
        # 计算预测误差
        pred = model(X)          # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
        
        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()        # 反向传播
        optimizer.step()       # 每一步自动更新
        
        # 记录acc与loss
        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

3. 编写测试函数

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小，一共10000张图片
    num_batches = len(dataloader)          # 批次数目，8（255/32=8，向上取整）
    test_loss, test_acc = 0, 0
    
    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            # 计算loss
            target_pred = model(imgs)
            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

4. 正式训练

epochs     = 20
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []
best_acc = 0
filename='checkpoint.pth'
 
for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
    
    scheduler.step()#学习率衰减
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    # 保存最优模型
    if epoch_test_acc > best_acc:
        best_acc = epoch_train_acc
        state = {
            'state_dict': model.state_dict(),#字典里key就是各层的名字，值就是训练好的权重
            'best_acc': best_acc,
            'optimizer' : optimizer.state_dict(),
        }
        torch.save(state, filename)
        
        
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')
print('best_acc：',best_acc)

Epoch: 1, Train_acc:12.2%, Train_loss:2.701, Test_acc:13.9%，Test_loss:2.544
Epoch: 2, Train_acc:20.8%, Train_loss:2.386, Test_acc:20.6%，Test_loss:2.377
Epoch: 3, Train_acc:26.1%, Train_loss:2.228, Test_acc:22.5%，Test_loss:2.274
…
Epoch:19, Train_acc:51.6%, Train_loss:1.528, Test_acc:35.8%，Test_loss:1.864
Epoch:20, Train_acc:53.9%, Train_loss:1.499, Test_acc:35.3%，Test_loss:1.852
Done
best_acc： 0.37430555555555556

四、结果可视化

1.Loss 与 Accuracy 图

import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 100        #分辨率
 
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.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('Training and Validation Loss')
plt.show()