•  🍨 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

一、前期准备

1.设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms,datasets
import matplotlib.pyplot as plt
import os,PIL,pathlib

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

device(type='cuda')

2.导入数据

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]
classNames

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

train_transforms = transforms.Compose([transforms.Resize([224,224]),# resize输入图片transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensortransforms.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)
total_data

Dataset ImageFolderNumber of datapoints: 1125Root location: weather_photosStandardTransform
Transform: Compose(Resize(size=[224, 224], interpolation=PIL.Image.BILINEAR)ToTensor()Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]))

3.数据集划分

train_size = int(0.8*len(total_data))
test_size = len(total_data) - train_size
train_size,test_size

(900, 225)

train_dataset, test_dataset = torch.utils.data.random_split(total_data,[train_size,test_size])
train_dataset,test_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)

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

Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32])

二、构建简单的CNN网络

import torch.nn.functional as Fnum_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 xmodel = Network_bn().to(device)
model

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)(pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(conv3): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))(bn3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv4): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))(bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(fc1): Linear(in_features=60000, out_features=4, bias=True)
)

三、训练模型

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

SGD (
Parameter Group 0dampening: 0lr: 0.0001momentum: 0nesterov: Falseweight_decay: 0
)

2.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losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn train_acc, train_loss

3.编写测试函数

与测试函数和训练函数大致相同，由于不需要进行梯度下降更新权重，所以不需要传入优化器。

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losstarget_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  /= sizetest_loss /= num_batchesreturn test_acc, test_loss

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')

Epoch: 1, Train_acc:61.3%, Train_loss:0.975, Test_acc:60.9%，Test_loss:0.961
...
Epoch:18, Train_acc:94.4%, Train_loss:0.255, Test_acc:87.6%，Test_loss:0.315
Epoch:19, Train_acc:93.8%, Train_loss:0.231, Test_acc:92.4%，Test_loss:0.226
Epoch:20, Train_acc:94.9%, Train_loss:0.187, Test_acc:92.0%，Test_loss:0.315
Done

四、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()