第P6周：VGG-16算法-Pytorch实现人脸识别

•  🍨 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 | 接辅导、项目定制

  import torch
  import torch.nn as nn
  import torchvision.transforms as transforms
  import torchvision
  from torchvision import transforms, datasets
  import os,PIL,pathlib,warnings
  
  warnings.filterwarnings("ignore")             #忽略警告信息
  
  device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
  import os,PIL,random,pathlib
  
  data_dir = './6-data/'
  data_dir = pathlib.Path(data_dir)
  
  data_paths  = list(data_dir.glob('*'))
  classeNames = [str(path).split("\\")[1] for path in data_paths]
  train_transforms = transforms.Compose([
      transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
      # transforms.RandomHorizontalFlip(), # 随机水平翻转
      transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
      transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
          mean=[0.485, 0.456, 0.406], 
          std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
  ])
  
  total_data = datasets.ImageFolder("./6-data/",transform=train_transforms)
  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)
  
  for X, y in test_dl:
      print("Shape of X [N, C, H, W]: ", X.shape)
      print("Shape of y: ", y.shape, y.dtype)
      break
  
  from torchvision.models import vgg16
  
  device = "cuda" if torch.cuda.is_available() else "cpu"
  print("Using {} device".format(device))
      
  # 加载预训练模型，并且对模型进行微调
  model = vgg16(pretrained = True).to(device) # 加载预训练的vgg16模型
  
  for param in model.parameters():
      param.requires_grad = False # 冻结模型的参数，这样子在训练的时候只训练最后一层的参数
  
  # 修改classifier模块的第6层（即：(6): Linear(in_features=4096, out_features=2, bias=True)）
  # 注意查看我们下方打印出来的模型
  model.classifier._modules['6'] = nn.Linear(4096,len(classeNames)) # 修改vgg16模型中最后一层全连接层，输出目标类别个数
  model.to(device)  
  model
  
  def train(dataloader,model,loss_fn,optimizer):
      size=len(dataloader.dataset)
      num_batchs=len(dataloader)
      train_loss,train_acc=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_batchs
  
      return train_acc,train_loss
  
  def test (dataloader, model, loss_fn):
      size        = len(dataloader.dataset)  # 测试集的大小
      num_batches = len(dataloader)          # 批次数目, (size/batch_size，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
  
  learn_rate = 1e-4 # 初始学习率
  
  # 调用官方动态学习率接口时使用
  lambda1 = lambda epoch: 0.92 ** (epoch // 4)
  optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
  scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) #选定调整方法
  
  import copy
  
  loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
  epochs     = 40
  
  train_loss = []
  train_acc  = []
  test_loss  = []
  test_acc   = []
  
  best_acc = 0    # 设置一个最佳准确率，作为最佳模型的判别指标
  
  for epoch in range(epochs):
      # 更新学习率（使用自定义学习率时使用）
      # adjust_learning_rate(optimizer, epoch, learn_rate)
      
      model.train()
      epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
      scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）
      
      model.eval()
      epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
      
      # 保存最佳模型到 best_model
      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)
      
      # 获取当前的学习率
      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))
      
  # 保存最佳模型到文件中
  PATH = './best_model.pth'  # 保存的参数文件名
  torch.save(model.state_dict(), PATH)
  
  print('Done')
  
  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()
  
  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)  # 展示预测的图片
  
      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='./6-data/Angelina Jolie/001_fe3347c0.jpg', 
                    model=model, 
                    transform=train_transforms, 
                    classes=classes)

  

• 
• 
• 
• 总结：加油