365天深度学习训练营-第P4周：猴痘病识别

● 难度：新手入门⭐
● 语言：Python3、Pytorch3
🍺要求：
1、训练过程中保存效果最好的模型参数。
2、加载最佳模型参数识别本地的一张图片。
3、调整网络结构使测试集accuracy到达80%（重点）。

🍻拔高（可选）：
1、调整模型参数并观察测试集的准确率变化。
2、尝试设置动态学习率。
3、测试集accuracy到达90%。

🍨 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

---

第4周-猴痘病识别

一、前期准备

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

import os, PIL, pathlib

1.设置GPU

device = torch.device("cuda") 
device

2.导入数据

data_dir = pathlib.Path("./data/4_week/")
data_paths = list(data_dir.glob('*'))
class_names = [str(path).split('/')[2] for path in data_paths]

train_transform = 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_dir, transform=train_transform)
total_data

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=False, num_workers=1)

二、构建简单的CNN网络

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        
        # 特征提取网络
        self.feature_net = nn.Sequential(nn.Conv2d(3, 12, 5), nn.BatchNorm2d(12), nn.ReLU(),
                                         nn.Conv2d(12, 12, 5), nn.BatchNorm2d(12), nn.ReLU(), 
                                         nn.AvgPool2d(2), 
                                         nn.Conv2d(12, 24, 5), nn.BatchNorm2d(24), nn.ReLU(), 
                                         nn.Conv2d(24, 24, 5), nn.BatchNorm2d(24), 
                                         nn.MaxPool2d(2))
        
        # 分类网络
        self.class_net = nn.Sequential(nn.Linear(24*50*50, len(class_names)))
        
    def forward(self, x):
        
        x = self.feature_net(x)
        
        x = x.view(-1, 24*50*50)
        
        return self.class_net(x)

model = CNN().to(device)
model

三、训练模型

1.设置超参数

loss_fn = nn.CrossEntropyLoss()
lr = 1e-4
opt = torch.optim.SGD(model.parameters(), lr=lr)

2.编写训练函数

def train(dataloader, model, loss_fn, optimizer):
    
    size = len(dataloader.dataset)
    num_batchs = len(dataloader)
    
    train_acc, train_loss = 0, 0
    
    for X, y in dataloader:
        
        X, y = X.to(device), y.to(device)
        
        # 计算loss
        y_pred = model(X)
        loss = loss_fn(y_pred, y)
        
        # backward
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        # log
        train_acc += (y_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

3.编写测试函数

def test(dataloader, model, loss_fn):
    
    size = len(dataloader.dataset)
    num_batchs = len(dataloader)
    
    test_acc, test_loss = 0, 0
    
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            # loss
            target_pred = model(imgs)
            loss = loss_fn(target_pred, target)
            
            test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
            test_loss += loss.item()
            
        test_acc /= size
        test_loss /= num_batchs
        
    return test_acc, test_loss

4.正式训练

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

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!")

四、结果可视化

1.Loss和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']         = 200

epoch_range = range(epochs)

plt.figure(figsize=(12, 3))

plt.subplot(1, 2, 1)
plt.plot(epoch_range, train_acc, label="Training Accuracy")
plt.plot(epoch_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Traing and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epoch_range, train_loss, label="Training Loss")
plt.plot(epoch_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Traing and Validation 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}')

# 预测训练集某张照片
predict_one_image(image_path='./data/4_week/Monkeypox/M01_04_13.jpg', 
                  model=model, 
                  transform=train_transform, 
                  classes=classes)

其实，还是会有预测错误的情况！！！

五、保存并加载模型

# 模型保存
PATH = './model.pth'
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>

目标1.设置动态学习率

方式1:自定义学习率下降：

def adjust_learning_rate(optimizer, epoch, start_lr):
	lr = start_lr * (0.95 ** (epoch // 2))
	for param_group in optimizer.param_groups:
	param_group['lr'] = lr

第一次设置衰减到原来的95%
结果如下：

第二次将衰减到原来的98%，还是有一定的提升，但是不排除是训练的初始条件导致的。

同时，预测的准确度也有所提升！！！

目标2.测试集accuracy到达90%。✅