Python+pytorch实现天气识别-群英

上一篇：Python整数的底层实现是什么，整数如何存储下一篇：Python中如何将元素添加到列表中，有多少种方法

在实际应用中，我们有时候会遇到“Python+pytorch实现天气识别”这样的问题，我们该怎样来处理呢？下文给大家介绍了解决方法，希望这篇“Python+pytorch实现天气识别”文章能帮助大家解决问题。

一、前期工作

环境：python3.6，1080ti，pytorch1.10（实验室服务器的环境）

1.设置GPU或者cpu

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")
 
device

2.导入数据

import os,PIL,random,pathlib
 
data_dir = 'weather_photos/'
data_dir = pathlib.Path(data_dir)
print(data_dir)
 
data_paths = list(data_dir.glob('*'))
print(data_paths)
classeNames = [str(path).split("/")[1] for path in data_paths]
classeNames

二、数据预处理

数据格式设置

total_datadir = 'weather_photos/'
 
# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
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)
total_data

数据集划分

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

设置dataset

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)

检查数据格式

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

三、搭建网络

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential,ReLU
 
num_classes = 4
 
class Model(nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        # 卷积层
        self.layers = Sequential(
            # 第一层
            nn.Conv2d(3, 24, kernel_size=5),
            nn.BatchNorm2d(24),
            nn.ReLU(),
            # 第二层
            nn.Conv2d(24,64 , kernel_size=5),
            nn.BatchNorm2d(64),
            nn.ReLU(),
            nn.MaxPool2d(2,2),
            nn.Conv2d(64, 128, kernel_size=5),
            nn.BatchNorm2d(128),
            nn.ReLU(),
            nn.Conv2d(128, 24, kernel_size=5),
            nn.BatchNorm2d(24),
            nn.ReLU(),
            nn.MaxPool2d(2,2),
            nn.Flatten(),
            nn.Linear(24*50*50, 516,bias=True),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(516, 215,bias=True),
            nn.ReLU(),
            nn.Dropout(0.5),
            nn.Linear(215, num_classes,bias=True),
        )
 
    def forward(self, x):
 
        x = self.layers(x)
        return x    
 
 
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
 
model = Model().to(device)
model

打印网络结构

四、训练模型

1.设置学习率

loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-3 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

2.模型训练

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

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

具体训练代码

epochs     = 30
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')

五、模型评估

1.Loss和Accuracy图

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()

2.对结果进行预测

import os
import json
 
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
 
img_path = "weather_photos/cloudy/cloudy1.jpg"
classes = ['cloudy', 'rain', 'shine', 'sunrise']
data_transform = 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。
])
def main():
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    
    img = Image.open(img_path)
    plt.imshow(img)
    # [N, C, H, W]
    img = data_transform(img)
    # expand batch dimension
    img = torch.unsqueeze(img, dim=0)
    model.eval()
    with torch.no_grad():
        # predict class
        output = torch.squeeze(model(img.to(device))).cpu()
        predict = torch.softmax(output, dim=0)
        predict_cla = torch.argmax(predict).numpy()
        print(classes[predict_cla])
    plt.show()
    
if __name__ == '__main__':
    main()

预测结果如下：

3.总结

1.本次能主要对以下函数进行了学习

transforms.Compose	针对数据转换，例如尺寸，类型
datasets.ImageFolder	结合上面这个对某文件夹下数据处理
torch.utils.data.DataLoader	设置dataset