🍨 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P3周：天气识别 | 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

import os,PIL,random,pathlib

data_dir = 'D:/jupyter notebook/DL-100-days/datasets/weather_photos/'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classNames = [str(path).split("\\")[5] for path in data_paths]
classNames

['cloudy', 'rain', 'shine', 'sunrise']

total_datadir = 'D:/jupyter notebook/DL-100-days/datasets/weather_photos/'

train_transforms = 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(total_datadir,transform=train_transforms)
total_data

Dataset ImageFolder
    Number of datapoints: 1125
    Root location: D:/jupyter notebook/DL-100-days/datasets/weather_photos/
    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])
           )

torch.Size([32, 3, 32, 32])

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

(<torch.utils.data.dataset.Subset at 0x2700e413988>,
<torch.utils.data.dataset.Subset at 0x2700e413848>)

train_size,test_size

(900, 225)

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

Shape of X [N,C,H,W]:  torch.Size([32, 3, 224, 224])
Shape of y:  torch.Size([32]) 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(24, 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=12, stride=12, padding=0, dilation=1, ceil_mode=False)
  (conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
  (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=4, 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，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

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，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

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:61.4%, Train_loss:0.986, Test_acc:72.0%，Test_loss:0.865
Epoch: 2, Train_acc:76.7%, Train_loss:0.674, Test_acc:83.6%，Test_loss:0.558
Epoch: 3, Train_acc:80.8%, Train_loss:0.561, Test_acc:88.4%，Test_loss:0.447
Epoch: 4, Train_acc:83.6%, Train_loss:0.485, Test_acc:90.2%，Test_loss:0.431
Epoch: 5, Train_acc:86.3%, Train_loss:0.423, Test_acc:89.8%，Test_loss:0.354
Epoch: 6, Train_acc:86.3%, Train_loss:0.418, Test_acc:88.4%，Test_loss:0.306
Epoch: 7, Train_acc:87.6%, Train_loss:0.389, Test_acc:88.4%，Test_loss:0.401
Epoch: 8, Train_acc:90.0%, Train_loss:0.340, Test_acc:92.9%，Test_loss:0.488
Epoch: 9, Train_acc:90.7%, Train_loss:0.321, Test_acc:92.4%，Test_loss:0.260
Epoch:10, Train_acc:91.0%, Train_loss:0.316, Test_acc:92.9%，Test_loss:0.240
Epoch:11, Train_acc:92.6%, Train_loss:0.288, Test_acc:93.3%，Test_loss:0.254
Epoch:12, Train_acc:91.3%, Train_loss:0.291, Test_acc:92.4%，Test_loss:0.231
Epoch:13, Train_acc:93.9%, Train_loss:0.238, Test_acc:92.4%，Test_loss:0.226
Epoch:14, Train_acc:93.9%, Train_loss:0.255, Test_acc:93.3%，Test_loss:0.200
Epoch:15, Train_acc:93.7%, Train_loss:0.239, Test_acc:94.7%，Test_loss:0.236
Epoch:16, Train_acc:93.4%, Train_loss:0.224, Test_acc:93.3%，Test_loss:0.201
Epoch:17, Train_acc:94.1%, Train_loss:0.265, Test_acc:94.7%，Test_loss:0.187
Epoch:18, Train_acc:93.7%, Train_loss:0.222, Test_acc:94.2%，Test_loss:0.193
Epoch:19, Train_acc:95.4%, Train_loss:0.224, Test_acc:93.8%，Test_loss:0.199
Epoch:20, Train_acc:95.1%, Train_loss:0.201, Test_acc:93.3%，Test_loss:0.175
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()