【365计划-3】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
🍦 参考文章地址： 365天深度学习训练营-第P3周：天气识别
🍖 作者：K同学啊

###本项目来自K同学在线指导###
数据集下载：https://pan.baidu.com/s/1Viq7s2FEtmcQQ3sRTMhszg
提取码：hqij

import torch
import torch.nn as  nn
import torchvision.transforms as transforms
from torchvision import datasets
import pathlib
##检测是否有cuda显卡
device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

data_dir='./weather_photos/'
data_dir=pathlib.Path(data_dir)
data_paths=list(data_dir.glob('*'))
classNames=[str(path).split('\\')[1] for path in data_paths]
print(classNames)


train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # resize输入图片
    transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换成tensor
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 从数据集中随机抽样计算得到
])

total_data = datasets.ImageFolder(data_dir, 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])

batch_size = 32
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)

for X,y in test_dl:
    print('Shape of X [N, C, H, W]:', X.shape)
    print('Shape of y:', y.shape)
    break

import torch.nn.functional as F

num_classes = 4  # 图片的类别数


class Network_bn(nn.Module):
    def __init__(self):
        super().__init__()
        # 特征提取网络
        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(2, 2)
        self.conv3 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn3 = nn.BatchNorm2d(24)
        self.conv4 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        # 分类网络
        self.fc1 = nn.Linear(24 * 50 * 50, num_classes)

    # 前向传播
    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.bn3(self.conv3(x)))
        x = F.relu(self.bn4(self.conv4(x)))
        x = self.pool(x)
        x = x.view(-1, 24 * 50 * 50)
        x = self.fc1(x)

        return x


model = Network_bn().to(device)

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)


# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共900张图片
    num_batches = len(dataloader)  # 批次数目，29（900/32）

    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


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，8（255/32=8，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


epochs = 100
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')

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()

训练过程：

Epoch: 1, Train_acc:65.3%, Train_loss:1.396, Test_acc:52.4%，Test_loss:0.886
Epoch: 2, Train_acc:85.1%, Train_loss:0.381, Test_acc:86.7%，Test_loss:0.345
Epoch: 3, Train_acc:91.7%, Train_loss:0.252, Test_acc:89.8%，Test_loss:0.257
Epoch: 4, Train_acc:92.1%, Train_loss:0.250, Test_acc:40.4%，Test_loss:6.429
Epoch: 5, Train_acc:91.1%, Train_loss:0.342, Test_acc:67.1%，Test_loss:0.966
Epoch: 6, Train_acc:93.9%, Train_loss:0.150, Test_acc:89.8%，Test_loss:0.223
Epoch: 7, Train_acc:95.8%, Train_loss:0.136, Test_acc:83.6%，Test_loss:0.820
Epoch: 8, Train_acc:95.8%, Train_loss:0.149, Test_acc:86.7%，Test_loss:0.291
Epoch: 9, Train_acc:94.2%, Train_loss:0.143, Test_acc:89.8%，Test_loss:0.264
Epoch:10, Train_acc:98.1%, Train_loss:0.083, Test_acc:72.9%，Test_loss:1.241
Epoch:11, Train_acc:96.9%, Train_loss:0.145, Test_acc:53.3%，Test_loss:7.011
Epoch:12, Train_acc:88.3%, Train_loss:0.469, Test_acc:56.0%，Test_loss:2.457
Epoch:13, Train_acc:94.0%, Train_loss:0.204, Test_acc:92.0%，Test_loss:0.211
Epoch:14, Train_acc:98.0%, Train_loss:0.096, Test_acc:75.1%，Test_loss:0.686
Epoch:15, Train_acc:95.3%, Train_loss:0.121, Test_acc:91.6%，Test_loss:0.244
Epoch:16, Train_acc:97.3%, Train_loss:0.083, Test_acc:84.9%，Test_loss:0.305
Epoch:17, Train_acc:98.8%, Train_loss:0.047, Test_acc:92.0%，Test_loss:0.184
Epoch:18, Train_acc:99.1%, Train_loss:0.034, Test_acc:93.3%，Test_loss:0.210
Epoch:19, Train_acc:99.8%, Train_loss:0.027, Test_acc:94.2%，Test_loss:0.174
Epoch:20, Train_acc:99.7%, Train_loss:0.033, Test_acc:92.4%，Test_loss:0.182
Done

心得：
（1）出现一定程度的过拟合
（2）训练过程有小幅波动，不稳定
（3）训练方式比较简单
处理办法：
（1）加L2正则化或者dropout
（2）加大数据集，尝试增大第二层卷积层的通道数，导致准确率直线下降，增大第三层有小幅增大