🍨 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P4周：猴痘病识别 | 365天深度学习训练营
🍖 作者：K同学啊 | 接辅导、程序定制

文章目录

我的环境：
一、前期工作
- 1. 设置 GPU
- 2. 导入数据
- 3. 划分数据集
二、构建简单的CNN网络
三、训练模型
- 1. 设置超参数
- 2. 编写训练函数
- 3. 编写测试函数
- 4. 正式训练
四、结果可视化

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

import os,PIL,pathlib

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

device

device(type='cuda')

2. 导入数据

data_dir = 'D:\\jupyter notebook\\DL-100-days\\datasets\\45-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)

['Monkeypox', 'Others']

total_datadir = 'D:\\jupyter notebook\\DL-100-days\\datasets\\45-data'
 
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)

Dataset ImageFolder
    Number of datapoints: 2142
    Root location: D:\jupyter notebook\DL-100-days\datasets\45-data
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=None)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

print(total_data.class_to_idx)

{'Monkeypox': 0, 'Others': 1}

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])
print(train_dataset, test_dataset)
print(train_size, test_size)

<torch.utils.data.dataset.Subset object at 0x000001C3687BF508> <torch.utils.data.dataset.Subset object at 0x000001C3687BF548>
1713 429

train_size,test_size

(900, 225)

batch_size = 128
 
train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=0)
 
# 数据的shape为：[batch_size, channel, height, weight]
# 其中batch_size为自己设定，channel，height和weight分别是图片的通道数，高度和宽度。
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

Shape of X [N, C, H, W]: torch.Size([128, 3, 224, 224])
Shape of y: torch.Size([128]) torch.int64

二、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__()
        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(12)
        self.conv4 = nn.Conv2d(in_channels=12,out_channels=24,kernel_size=5,stride=1,padding=0)
        self.bn1 = 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(classNames))
        
    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)
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)
)

三、训练模型

1. 设置超参数

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)

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
    num_batches = len(dataloader)  # 批次数目
 
    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

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小
    num_batches = len(dataloader)  # 批次数目
 
    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

4. 正式训练

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:56.7%, Train_loss:0.694, Test_acc:65.3%，Test_loss:0.671
Epoch: 2, Train_acc:62.8%, Train_loss:0.636, Test_acc:61.5%，Test_loss:0.652
Epoch: 3, Train_acc:64.9%, Train_loss:0.622, Test_acc:58.7%，Test_loss:0.688
Epoch: 4, Train_acc:68.0%, Train_loss:0.597, Test_acc:68.1%，Test_loss:0.630
Epoch: 5, Train_acc:68.4%, Train_loss:0.590, Test_acc:68.1%，Test_loss:0.623
Epoch: 6, Train_acc:70.9%, Train_loss:0.572, Test_acc:69.2%，Test_loss:0.581
Epoch: 7, Train_acc:71.7%, Train_loss:0.554, Test_acc:69.2%，Test_loss:0.596
Epoch: 8, Train_acc:72.7%, Train_loss:0.542, Test_acc:68.3%，Test_loss:0.617
Epoch: 9, Train_acc:74.0%, Train_loss:0.530, Test_acc:70.9%，Test_loss:0.577
Epoch:10, Train_acc:74.3%, Train_loss:0.520, Test_acc:73.2%，Test_loss:0.595
Epoch:11, Train_acc:75.1%, Train_loss:0.510, Test_acc:68.1%，Test_loss:0.589
Epoch:12, Train_acc:75.3%, Train_loss:0.505, Test_acc:73.7%，Test_loss:0.559
Epoch:13, Train_acc:77.2%, Train_loss:0.488, Test_acc:71.6%，Test_loss:0.563
Epoch:14, Train_acc:78.4%, Train_loss:0.478, Test_acc:73.0%，Test_loss:0.545
Epoch:15, Train_acc:78.9%, Train_loss:0.468, Test_acc:74.8%，Test_loss:0.537
Epoch:16, Train_acc:80.1%, Train_loss:0.463, Test_acc:75.1%，Test_loss:0.538
Epoch:17, Train_acc:80.1%, Train_loss:0.457, Test_acc:75.1%，Test_loss:0.550
Epoch:18, Train_acc:79.8%, Train_loss:0.447, Test_acc:76.5%，Test_loss:0.503
Epoch:19, Train_acc:81.6%, Train_loss:0.440, Test_acc:76.9%，Test_loss:0.511
Epoch:20, Train_acc:82.0%, Train_loss:0.435, Test_acc:78.1%，Test_loss:0.508
Done

四、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()

在这里插入图片描述

# 模型保存
PATH = 'D:\\jupyter notebook\\DL-100-days\\datasets\\45-data\\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))

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) #（0表示，在第一个位置增加维度）
 
    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='D:\\jupyter notebook\\DL-100-days\\datasets\\45-data\\Others\\NM01_01_00.jpg',
                  model=model,
                  transform=train_transforms,
                  classes=classes)