CNN天气识别

李恒道

数据集
https://www.heywhale.com/mw/dataset/60d9bd7c056f570017c305ee/file
主要区别就是dataloader部分
其他代码基本一致

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import torch.nn.functional as F
import os,PIL,pathlib
import os,PIL,random,pathlib

data_dir = './weather_photos/'
data_dir = pathlib.Path(data_dir)
total_datadir = './weather_photos/'
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
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)
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(f"训练集样本数: {len(train_dataset)}")
print(f"测试集样本数: {len(test_dataset)}")

batch_size = 32

def make_dataloaders(train_dataset, test_dataset, batch_size=32, num_workers=0):
    train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=num_workers)
    test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=num_workers)
    return train_dl, test_dl

class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__()
        """
        保持原始结构，只做最小必要的改进
        """
        # 关键改进：添加padding保持特征图尺寸
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=2)  # 224→224
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=2)  # 224→224
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2,2)  # 224→112

        self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=2)  # 112→112
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=2)  # 112→112
        self.bn5 = nn.BatchNorm2d(24)
        # pool: 112→56

        # 保持原始的全连接层设计
        self.fc1 = nn.Linear(24*56*56, len(classeNames))

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))      # 224→224
        x = F.relu(self.bn2(self.conv2(x)))      # 224→224  
        x = self.pool(x)                         # 224→112

        x = F.relu(self.bn4(self.conv4(x)))      # 112→112
        x = F.relu(self.bn5(self.conv5(x)))      # 112→112
        x = self.pool(x)                         # 112→56

        x = x.view(-1, 24*56*56)                # 展平
        x = self.fc1(x)

        return x

model = Network_bn().to(device)

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
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
    # On Windows the DataLoader with multiple workers requires the
    # `if __name__ == '__main__'` guard. Use next(iter(...)) to fetch
    # a single batch without indexing the DataLoader.
train_dl, test_dl = make_dataloaders(train_dataset, test_dataset, batch_size=batch_size, num_workers=0)
batch = next(iter(test_dl))
X, y = batch
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)

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)

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')