深度学习案例—天气识别

目录

一、前言

 二、我的环境

二、操作流程

1.导入所需要的库

2.导入数据 

 3. 划分数据集

 4.构建简单的CNN网络

5.模型构建

5.1. 设置超参数

 5.2.编写训练函数

5.3.编写测试函数

5.4.正式训练

 6.预测&结果可视化

---

一、前言

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客

• 🍦 参考文章：Pytorch实战 | 第P3周：彩色图片识别：天气识别

• 🍖 原作者：K同学啊|接辅导、项目定制

 二、我的环境

• 电脑系统：Windows 10

• 语言环境：Python 3.7

• 编译器：pycharm

• 深度学习环境：Pytorch

二、操作流程

1.导入所需要的库

# 1.导入所需要的库
import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(torch.__version__)
print(torch.cuda.is_available())
print(torch.cuda.get_device_name(0))
# 1.7.0+cu110
#  True
# 'NVIDIA GeForce GT 730'
device = torch.device("cpu")

2.导入数据 

import os, PIL, random, pathlib
# 定义数据增强和预处理
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.RandomHorizontalFlip(),
    transforms.RandomRotation(20),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                         std=[0.229, 0.224, 0.225])
])
data_dir = './data/data_weather/weather_photos/'  # 本地文件数据集存放路径读取
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[3] for path in data_paths]
#print(data_paths)
print(classeNames)
#exit()

total_datadir = './data/data_weather/weather_photos/'

# 关于transforms.Compose的更多介绍可以参考：
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)
print(total_data)

 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])
print(train_dataset,'\n',test_dataset)
print(train_size,test_size)

# exit()

batch_size = 32
#  num_workers不为零,多线程来读数据，多线程必须加  if __name__ == '__main__':
train_dl = torch.utils.data.DataLoader(train_dataset,
                                       batch_size=batch_size,
                                       shuffle=True,
                                       )
test_dl = torch.utils.data.DataLoader(test_dataset,
                                      batch_size=batch_size,
                                      shuffle=True,
                                      )
# print(train_dl)
# print(test_dl)
# exit()


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

在DataLoader时候，num_workers要设置为零，否则运行程序会报错。

 4.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(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.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.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

model = Network_bn().to(device)
# print(model)

5.模型构建

5.1. 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)
opt = torch.optim.Adam(model.parameters(), lr=learn_rate)

在这里我们选择两种不同的优化算法，后面模型评估时会放出来两种优化算法的结果。adam比SGD效果要好。

 5.2.编写训练函数

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，28.125,不够一张的按一张算29（900/32）
    # print(size)
    # print(num_batches)

    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()
        #test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
        train_loss += loss.item()

    train_acc /= size
    train_loss /= num_batches

    return train_acc, train_loss

5.3.编写测试函数

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)  # 训练集的大小，一共900张图片
    num_batches = len(dataloader)  # 批次数目，28.125,不够一张的按一张算29（900/32）
    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

5.4.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')

 6.预测&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()

优化算法SGD下的模型效果

 优化算法Adam下的模型效果