第P4周：猴痘病识别

• 🍨 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
• 🚀 文章来源：K同学的学习圈子

目录

一、代码及运行结果

1.前期准备

 2.构建简单的CNN网络

 3.训练模型

 4.结果可视化

5.保存并加载模型 

  二、个人总结 

 对保存模型的总结：

---

一、代码及运行结果

1.前期准备

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

import os,PIL,pathlib

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

print(device)

import os,PIL,random,pathlib

data_dir = './猴痘病识别/'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[1] for path in data_paths]
print(classeNames)

total_datadir = './猴痘病识别/'

# 关于transforms.Compose的更多介绍可以参考：https://blog.youkuaiyun.com/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    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(total_datadir,transform=train_transforms)
print(total_data)

print(total_data.class_to_idx)

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

cuda
['Monkeypox', 'Others']
Dataset ImageFolder
    Number of datapoints: 2142
    Root location: ./猴痘病识别/
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )
{'Monkeypox': 0, 'Others': 1}
Shape of X [N, C, H, W]:  torch.Size([32, 3, 224, 224])
Shape of y:  torch.Size([32]) torch.int64

 2.构建简单的CNN网络

import torch.nn.functional as F

class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__()
        """
        nn.Conv2d()函数：
        第一个参数（in_channels）是输入的channel数量
        第二个参数（out_channels）是输出的channel数量
        第三个参数（kernel_size）是卷积核大小
        第四个参数（stride）是步长，默认为1
        第五个参数（padding）是填充大小，默认为0
        """
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2,2)
        self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn5 = nn.BatchNorm2d(24)
        self.fc1 = nn.Linear(24*50*50, len(classeNames))

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))      
        x = F.relu(self.bn2(self.conv2(x)))     
        x = self.pool(x)                        
        x = F.relu(self.bn4(self.conv4(x)))     
        x = F.relu(self.bn5(self.conv5(x)))  
        x = self.pool(x)                        
        x = x.view(-1, 24*50*50)
        x = self.fc1(x)

        return x

device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = Network_bn().to(device)
print(model)

Using cuda device
Network_bn(
  (conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (fc1): Linear(in_features=60000, out_features=2, bias=True)
)

 3.训练模型

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片
    num_batches = len(dataloader)   # 批次数目，1875（60000/32）

    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

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，313（10000/32=312.5，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

epochs     = 20
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    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')

Epoch: 1, Train_acc:58.6%, Train_loss:0.691, Test_acc:64.1%，Test_loss:0.665
Epoch: 2, Train_acc:66.7%, Train_loss:0.609, Test_acc:68.8%，Test_loss:0.646
Epoch: 3, Train_acc:70.6%, Train_loss:0.567, Test_acc:66.2%，Test_loss:0.656
Epoch: 4, Train_acc:73.3%, Train_loss:0.541, Test_acc:70.9%，Test_loss:0.630
Epoch: 5, Train_acc:77.3%, Train_loss:0.494, Test_acc:75.1%，Test_loss:0.568
Epoch: 6, Train_acc:79.5%, Train_loss:0.471, Test_acc:76.0%，Test_loss:0.556
Epoch: 7, Train_acc:79.6%, Train_loss:0.453, Test_acc:72.0%，Test_loss:0.568
Epoch: 8, Train_acc:81.8%, Train_loss:0.432, Test_acc:74.8%，Test_loss:0.525
Epoch: 9, Train_acc:83.4%, Train_loss:0.414, Test_acc:76.0%，Test_loss:0.503
Epoch:10, Train_acc:84.4%, Train_loss:0.396, Test_acc:77.4%，Test_loss:0.505
Epoch:11, Train_acc:85.1%, Train_loss:0.388, Test_acc:75.8%，Test_loss:0.513
Epoch:12, Train_acc:86.3%, Train_loss:0.364, Test_acc:79.0%，Test_loss:0.475
Epoch:13, Train_acc:87.6%, Train_loss:0.354, Test_acc:80.2%，Test_loss:0.476
Epoch:14, Train_acc:87.3%, Train_loss:0.347, Test_acc:80.4%，Test_loss:0.468
Epoch:15, Train_acc:87.8%, Train_loss:0.342, Test_acc:78.6%，Test_loss:0.473
Epoch:16, Train_acc:88.6%, Train_loss:0.327, Test_acc:81.6%，Test_loss:0.457
Epoch:17, Train_acc:89.2%, Train_loss:0.321, Test_acc:81.4%，Test_loss:0.464
Epoch:18, Train_acc:88.8%, Train_loss:0.312, Test_acc:80.0%，Test_loss:0.453
Epoch:19, Train_acc:90.2%, Train_loss:0.304, Test_acc:81.4%，Test_loss:0.458
Epoch:20, Train_acc:90.1%, Train_loss:0.299, Test_acc:80.7%，Test_loss:0.434
Done

 4.结果可视化

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}')
    
# 预测训练集中的某张照片
predict_one_image(image_path='./猴痘病识别/Monkeypox/M01_01_00.jpg', 
                  model=model, 
                  transform=train_transforms, 
                  classes=classes)

预测结果是：Monkeypox

5.保存并加载模型 

# 模型保存
PATH = './model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)

# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))

<All keys matched successfully>

  二、个人总结 

 对保存模型的总结：

当保存和加载模型时，TensorFlow和PyTorch使用了不同的函数和机制。下面是对ModelCheckpoint、model.save()以及torch.save(model.state_dict(), PATH)函数的详细解释和区别：

1. TensorFlow中的model.save()函数：

   • 功能：model.save()函数用于保存整个模型，包括模型的架构和权重参数。
   • 格式：默认情况下，TensorFlow将模型保存为SavedModel格式，它是一个包含模型架构、权重参数和计算图的文件夹。
   • 使用方式：可以通过model.save(filepath)来保存模型，其中filepath是保存模型的文件路径。

2. PyTorch中的torch.save(model.state_dict(), PATH)函数：

   • 功能：torch.save()函数用于保存模型的状态字典（state_dict），即模型的权重参数。
   • 格式：PyTorch使用Python的pickle模块将状态字典保存为文件。
   • 使用方式：可以通过torch.save(model.state_dict(), PATH)来保存模型的状态字典，其中model.state_dict()获取模型的状态字典，PATH是保存模型的文件路径。

3. TensorFlow中的ModelCheckpoint回调函数：

   • 功能：ModelCheckpoint是一个TensorFlow的回调函数，用于在训练过程中定期保存模型的权重参数。
   • 格式：与model.save()函数类似，默认情况下，它会将模型保存为SavedModel格式。
   • 使用方式：可以通过在训练过程中指定ModelCheckpoint回调函数来自动保存模型。
   • 通过设置save_weights_only=True，可以仅保存模型的权重参数而不保存整个模型。