重庆的建设工程造价信息网_北京国际化品牌设计_旅游seo整站优化_怎么根据视频链接找到网址

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊

1.检查GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasetsimport os,PIL,pathlibdevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")device

2.查看数据

import os,PIL,random,pathlibdata_dir = 'data/45-data/'
data_dir = pathlib.Path(data_dir)data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[2] for path in data_paths]
classeNames

3.划分数据集

total_datadir = 'data/45-data'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_datatrain_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_datasettrain_size,test_sizebatch_size = 32train_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, y.dtype)break

4.创建模型

import torch
import torch.nn as nn
import torch.nn.functional as F# SE注意力机制
class SqueezeExcitation(nn.Module):def __init__(self, in_channels, reduction=16):super(SqueezeExcitation, self).__init__()self.global_avg_pool = nn.AdaptiveAvgPool2d(1)self.fc1 = nn.Linear(in_channels, in_channels // reduction, bias=False)self.relu = nn.ReLU(inplace=True)self.fc2 = nn.Linear(in_channels // reduction, in_channels, bias=False)self.sigmoid = nn.Sigmoid()def forward(self, x):b, c, _, _ = x.size()y = self.global_avg_pool(x).view(b, c)y = self.fc1(y)y = self.relu(y)y = self.fc2(y)y = self.sigmoid(y).view(b, c, 1, 1)return x * y# DenseNet的Conv Block
class ConvBlock(nn.Module):def __init__(self, in_channels, growth_rate):super(ConvBlock, self).__init__()self.bn1 = nn.BatchNorm2d(in_channels)self.relu = nn.ReLU(inplace=True)self.conv1 = nn.Conv2d(in_channels, 4 * growth_rate, kernel_size=1, bias=False)self.bn2 = nn.BatchNorm2d(4 * growth_rate)self.conv2 = nn.Conv2d(4 * growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)def forward(self, x):out = self.conv1(self.relu(self.bn1(x)))out = self.conv2(self.relu(self.bn2(out)))return torch.cat([x, out], 1)# Dense Block
class DenseBlock(nn.Module):def __init__(self, num_layers, in_channels, growth_rate):super(DenseBlock, self).__init__()layers = []for i in range(num_layers):layers.append(ConvBlock(in_channels + i * growth_rate, growth_rate))self.block = nn.Sequential(*layers)def forward(self, x):return self.block(x)# Transition Block
class TransitionBlock(nn.Module):def __init__(self, in_channels, out_channels):super(TransitionBlock, self).__init__()self.bn = nn.BatchNorm2d(in_channels)self.relu = nn.ReLU(inplace=True)self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=False)self.pool = nn.AvgPool2d(kernel_size=2, stride=2)def forward(self, x):x = self.conv(self.relu(self.bn(x)))x = self.pool(x)return x# DenseNet
class DenseNet(nn.Module):def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, num_classes=3):super(DenseNet, self).__init__()# 初始卷积层self.features = nn.Sequential(nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False),nn.BatchNorm2d(num_init_features),nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2, padding=1))num_features = num_init_featureslayers = []for i, num_layers in enumerate(block_config):layers.append(DenseBlock(num_layers, num_features, growth_rate))num_features += num_layers * growth_rateif i != len(block_config) - 1:layers.append(TransitionBlock(num_features, num_features // 2))num_features = num_features // 2self.dense_blocks = nn.Sequential(*layers)self.se = SqueezeExcitation(num_features)self.final_bn = nn.BatchNorm2d(num_features)self.final_relu = nn.ReLU(inplace=True)self.global_avg_pool = nn.AdaptiveAvgPool2d(1)self.classifier = nn.Linear(num_features, num_classes)def forward(self, x):x = self.features(x)x = self.dense_blocks(x)x = self.se(x)x = self.final_relu(self.final_bn(x))x = self.global_avg_pool(x)x = torch.flatten(x, 1)x = self.classifier(x)return x# 定义不同版本的 DenseNetdef densenet121(num_classes=3):return DenseNet(growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, num_classes=num_classes)def densenet169(num_classes=3):return DenseNet(growth_rate=32, block_config=(6, 12, 32, 32), num_init_features=64, num_classes=num_classes)def densenet201(num_classes=3):return DenseNet(growth_rate=32, block_config=(6, 12, 48, 32), num_init_features=64, num_classes=num_classes)model=densenet121().to(device)
model

5.编译及训练模型

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losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn train_acc, train_lossdef 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_lossepochs     = 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.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from datetime import datetime
current_time = datetime.now() # 获取当前时间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.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效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()

7.预测图片

from PIL import Image classes = list(total_data.class_to_idx)def predict_one_image(image_path, model, transform, classes):test_img = Image.open(image_path).convert('RGB')# plt.imshow(test_img)  # 展示预测的图片test_img = transform(test_img)img = test_img.to(device).unsqueeze(0)model.eval()output = model(img)_,pred = torch.max(output,1)pred_class = classes[pred]print(f'预测结果是：{pred_class}')# 预测训练集中的某张照片
predict_one_image(image_path='data/45-data/Others/NM01_01_05.jpg', model=model, transform=train_transforms, classes=classes)

总结：

这段代码实现了一个基于DenseNet的图像分类任务，包含了数据加载、模型定义、训练、测试、结果可视化以及单张图片预测的全流程。以下是代码的主要步骤和功能总结：

1. 检查GPU
- 使用`torch.cuda.is_available()`检查是否有可用的GPU，并将模型和数据加载到GPU上。

2. 查看数据
- 定义了数据集的路径，并使用`pathlib.Path`来管理路径。
- 通过`glob`方法获取数据集中的所有类别，并生成类别名称列表。

3. 划分数据集
- 使用`transforms.Compose`定义数据预处理操作，包括调整大小、转换为Tensor、标准化等。
- 使用`datasets.ImageFolder`加载数据集，并将其划分为训练集和测试集（80%训练，20%测试）。
- 使用`DataLoader`将数据集加载为批量数据，方便后续训练和测试。

4. 创建模型
- 定义了`SqueezeExcitation`（SE注意力机制）模块，用于增强模型的表达能力。
- 定义了`ConvBlock`（卷积块）和`DenseBlock`（密集块），这些是DenseNet的核心组件。
- 定义了`TransitionBlock`（过渡块），用于减少特征图的尺寸。
- 定义了`DenseNet`模型，包含了初始卷积层、多个密集块、过渡块、SE注意力机制以及最后的分类层。
- 提供了`densenet121`、`densenet169`、`densenet201`等不同版本的DenseNet模型。

5. 编译及训练模型
- 使用`CrossEntropyLoss`作为损失函数，`SGD`作为优化器。
- 定义了`train`和`test`函数，分别用于训练和测试模型。
- 进行了20个epoch的训练，并在每个epoch结束后记录训练和测试的准确率及损失。

6. 结果可视化
- 使用`matplotlib`绘制了训练和测试的准确率曲线以及损失曲线。
- 在图中添加了时间戳，确保代码的可追溯性。

7. 预测图片
- 定义了一个函数`predict_one_image`，用于对单张图片进行预测。
- 通过加载图片、预处理、模型推理等步骤，输出图片的预测类别。