第P3周：Pytorch实现天气识别

计算机真好丸

已于 2024-08-02 21:42:24 修改

阅读量282

点赞数 2

文章标签： pytorch 人工智能

于 2024-08-02 20:53:03 首次发布

本文链接：https://blog.csdn.net/weixin_52447211/article/details/140879074

版权

>- **🍨 本文为[🔗365天深度学习训练营](https://mp.weixin.qq.com/s/Z9yL_wt7L8aPOr9Lqb1K3w) 中的学习记录博客**
>- **🍖 原作者：[K同学啊](https://mtyjkh.blog.csdn.net/)**

一、前期准备

1.设置GPU/CPU

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

import os,PIL,pathlib,random 

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

device

device(type='cpu')

2.导入数据

data_dir = './weather_photos/'
data_dir = pathlib.Path(data_dir)

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

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

import matplotlib.pyplot as plt
from PIL import Image

## 指定图像文件夹路径
image_folder = './weather_photos/cloudy/'

## 获取文件夹中的所有图像文件
image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]

## 创建Matplotlib图像
fig, axes = plt.subplots(3, 8, figsize=(16, 6))

## 使用列表推导式加载和显示图像
for ax, img_file in zip(axes.flat, image_files):
    img_path = os.path.join(image_folder, img_file)
    img = Image.open(img_path)
    ax.imshow(img)
    ax.axis('off')
    
## 显示图像
plt.tight_layout()
plt.show()

请添加图片描述

total_datadir = './weather_photos/'

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-->转换为标准正态分布（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)
total_data

Dataset ImageFolder
    Number of datapoints: 1125
    Root location: ./weather_photos/
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

3.划分数据集
● train_size表示训练集大小，通过将总体数据长度的80%转换为整数得到；
● test_size表示测试集大小，是总体数据长度减去训练集大小。
使用torch.utils.data.random_split()方法进行数据集划分。该方法将总体数据total_data按照指定的大小比例（[train_size, test_size]）随机划分为训练集和测试集，并将划分结果分别赋值给train_dataset和test_dataset两个变量。

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 0x1693c3850>,
 <torch.utils.data.dataset.Subset at 0x1693c2dd0>)

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.pool1 = 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.pool2 = nn.MaxPool2d(2,2)
        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.pool1(x)
        x = F.relu(self.bn4(self.conv4(x)))
        x = F.relu(self.bn5(self.conv5(x)))
        x = self.pool2(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 cpu 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)
  (pool1): 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)
  (pool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (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:   ## 获取图片及其比标签
        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
        
        ## 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:58.1%, Train_loss:1.027, Test_acc:47.6%, Test_loss:1.119
Epoch: 2, Train_acc:77.8%, Train_loss:0.667, Test_acc:82.2%, Test_loss:0.634
Epoch: 3, Train_acc:83.7%, Train_loss:0.567, Test_acc:83.6%, Test_loss:0.529
Epoch: 4, Train_acc:86.3%, Train_loss:0.460, Test_acc:79.1%, Test_loss:0.477
Epoch: 5, Train_acc:87.8%, Train_loss:0.411, Test_acc:89.3%, Test_loss:0.391
Epoch: 6, Train_acc:90.2%, Train_loss:0.349, Test_acc:91.1%, Test_loss:0.328
Epoch: 7, Train_acc:89.2%, Train_loss:0.350, Test_acc:89.8%, Test_loss:0.323
Epoch: 8, Train_acc:91.7%, Train_loss:0.338, Test_acc:88.4%, Test_loss:0.349
Epoch: 9, Train_acc:90.0%, Train_loss:0.321, Test_acc:89.8%, Test_loss:0.304
Epoch:10, Train_acc:92.9%, Train_loss:0.260, Test_acc:90.7%, Test_loss:0.316
Epoch:11, Train_acc:92.8%, Train_loss:0.242, Test_acc:91.6%, Test_loss:0.295
Epoch:12, Train_acc:93.7%, Train_loss:0.232, Test_acc:90.7%, Test_loss:0.292
Epoch:13, Train_acc:94.9%, Train_loss:0.218, Test_acc:89.8%, Test_loss:0.287
Epoch:14, Train_acc:94.7%, Train_loss:0.257, Test_acc:88.9%, Test_loss:0.311
Epoch:15, Train_acc:95.2%, Train_loss:0.191, Test_acc:90.2%, Test_loss:0.286
Epoch:16, Train_acc:95.1%, Train_loss:0.220, Test_acc:89.8%, Test_loss:0.451
Epoch:17, Train_acc:95.0%, Train_loss:0.196, Test_acc:90.2%, Test_loss:0.286
Epoch:18, Train_acc:95.7%, Train_loss:0.190, Test_acc:89.3%, Test_loss:0.339
Epoch:19, Train_acc:95.8%, Train_loss:0.171, Test_acc:90.7%, Test_loss:0.257
Epoch:20, Train_acc:95.8%, Train_loss:0.163, Test_acc:89.8%, Test_loss:0.469
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()

请添加图片描述

总结：
由第一次结果可以看出test_acc的结果只能达到90%，而训练集的表现比较可观，为了提升测试集准确性，可以尝试使用Adam优化器并且引入L2正则化来解决。修改代码如下：

loss_fn = nn.CrossEntropyLoss()  ##创建损失函数
learn_rate = 1e-4    ## 学习率（Adam默认lr应该为0.001，但是经过试验发现效果不太理想，于是尝试将lr改为0.0001发现效果比较可观）
opt = torch.optim.Adam(model.parameters(),lr=learn_rate, weight_decay=1e-4)

通过训练，test_acc获得提升，基本可以到达93%。
训练结果如下：
请添加图片描述
可视化后结果如下：

另外，还可以使用数据增强来提高模型泛化能力，即对训练数据进行随机变换来增加其多样性。

计算机真好丸

关注

2
点赞
踩
3

收藏

觉得还不错? 一键收藏
0
评论
第P3周：Pytorch实现天气识别

该方法将总体数据total_data按照指定的大小比例（[train_size, test_size]）随机划分为训练集和测试集，并将划分结果分别赋值给train_dataset和test_dataset两个变量。由第一次结果可以看出test_acc的结果只能达到90%，而训练集的表现比较可观，为了提升测试集准确性，可以尝试使用Adam优化器并且引入L2正则化来解决。另外，还可以使用数据增强来提高模型泛化能力，即对训练数据进行随机变换来增加其多样性。通过训练，test_acc获得提升，基本可以到达93%。
复制链接

扫一扫