第p3周：Pytorch实现天气识别

• 🍨 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

前言

要求：

1.本地读取并加载数据
2.测试集accuracy到达93%

拔高：
1.测试集accuracy到达95%
2.调用模型识别一张本地图片

实验环境：

• 语言环境：Python3.10
• 编译器：Pycharm
• 深度学习环境：Pytorch
  1.torch == 2.2.2
  2.torchvision == 0.16.0

一、前期准备

1.设置GPU

import os
import pathlib
import warnings

import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.nn.functional as F
from PIL import Image
from torchvision import transforms, datasets


#-------------设置GPU---------------
# 设置硬件设备，如果有GPU则使用，没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

代码输出：

cuda

2.导入数据

输入代码：

#---------------------------导入数据----------------------
data_dir = 'F:/tianqidata/data/weather_photos'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[4] for path in data_paths]
print(classeNames)

代码输出：

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

# 指定图像文件夹路径
image_folder = 'F:/tianqidata/data/weather_photos/rain/'

#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", ".npg", ".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()

代码输出：

代码输入：

total_datadir = 'F:/tianqidata/data/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转换成tensor，并归一化到[0,1]之间
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                         std=[0.229, 0.224, 0.225])   #其中 mean=[0.485, 0.456, 0.406]和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)

代码输出：

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

3.划分数据集

代码输入：

#----------------------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)
print(test_dataset)

代码输出：

<torch.utils.data.dataset.Subset object at 0x0000019413177CD0>
<torch.utils.data.dataset.Subset object at 0x0000019413177130>

代码输入：

print(train_size, test_size)

代码输出：

900 225

代码输入：

batch_size = 32
train_dl = torch.utils.DataLoader(train_dataset,
                                  batch_size=batch_size,
                                  shuffle=True,
                                  num_workers=1)
test_dl = torch.utils.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

代码输出：

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

代码输入：

#-------------------------------构建简单的cnn网络----------------------------
class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__() #特征提取网络
        self.conv1 = nn.Conv2d(3, 12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(12, 12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv4 = nn.Conv2d(12, 24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(24, 24, kernel_size=5, stride=1, padding=0)
        self.bn5 = nn.BatchNorm2d(24)
        self.pool2 = nn.MaxPool2d(2, 2)

        # 分类网络
        self.fc1 = nn.Linear(24*50*50, len(classeNames))
        # 向前传播
    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)
print(model)

代码输出：

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)
  (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

#-----------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

#-------------------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

#--------------------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

#---------------------------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')

代码输出：

Epoch: 1, Train_acc:55.8%, Train_loss:1.064, Test_acc:75.1%, Test_loss:0.994
Epoch: 2, Train_acc:75.2%, Train_loss:0.763, Test_acc:55.6%, Test_loss:0.894
Epoch: 3, Train_acc:81.7%, Train_loss:0.601, Test_acc:85.3%, Test_loss:0.458
Epoch: 4, Train_acc:86.1%, Train_loss:0.511, Test_acc:86.2%, Test_loss:0.733
Epoch: 5, Train_acc:87.3%, Train_loss:0.450, Test_acc:84.9%, Test_loss:0.651
Epoch: 6, Train_acc:88.4%, Train_loss:0.406, Test_acc:91.1%, Test_loss:0.299
Epoch: 7, Train_acc:89.6%, Train_loss:0.356, Test_acc:90.7%, Test_loss:0.352
Epoch: 8, Train_acc:90.6%, Train_loss:0.331, Test_acc:92.4%, Test_loss:0.328
Epoch: 9, Train_acc:92.6%, Train_loss:0.298, Test_acc:91.6%, Test_loss:0.250
Epoch:10, Train_acc:93.0%, Train_loss:0.282, Test_acc:92.4%, Test_loss:0.225
Epoch:11, Train_acc:92.3%, Train_loss:0.279, Test_acc:92.9%, Test_loss:0.468
Epoch:12, Train_acc:92.7%, Train_loss:0.252, Test_acc:92.4%, Test_loss:0.239
Epoch:13, Train_acc:93.7%, Train_loss:0.256, Test_acc:92.4%, Test_loss:0.220
Epoch:14, Train_acc:94.0%, Train_loss:0.252, Test_acc:92.4%, Test_loss:0.191
Epoch:15, Train_acc:92.9%, Train_loss:0.264, Test_acc:92.4%, Test_loss:0.206
Epoch:16, Train_acc:93.2%, Train_loss:0.250, Test_acc:92.0%, Test_loss:0.193
Epoch:17, Train_acc:94.9%, Train_loss:0.216, Test_acc:92.0%, Test_loss:0.187
Epoch:18, Train_acc:94.0%, Train_loss:0.246, Test_acc:94.7%, Test_loss:0.191
Epoch:19, Train_acc:95.1%, Train_loss:0.222, Test_acc:93.3%, Test_loss:0.217
Epoch:20, Train_acc:94.6%, Train_loss:0.201, Test_acc:92.9%, Test_loss:0.192

四、结果可视化

#--------------------------------结果可视化------------------------
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()

代码输出：

五、总结

本周练习过程中，运行代码有些不顺利，但一件件的解决了。
首先，学习了如何找到文件夹路径的数据集。
其次也学习了使用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。
最后，学习了torch.utils.data.DataLoader 是 PyTorch 中用于加载和管理数据的一个实用工具类。它允许你以小批次的方式迭代你的数据集，这对于训练神经网络和其他机器学习任务非常有用。