### 使用PyTorch生成基于动物数据集的完整代码 以下是使用PyTorch框架完成的一个完整的解决方案，涵盖了数据预处理、模型构建、训练和评估的过程。该方案适用于任何分类任务，特别是针对动物图像数据集。 #### 数据准备 在PyTorch中，可以利用`torchvision.datasets`模块加载常见的图像数据集，并通过自定义转换操作对数据进行增强和标准化[^1]。 ```python import torch from torchvision import datasets, transforms from torch.utils.data import DataLoader # 定义数据变换 transform = transforms.Compose([ transforms.Resize((64, 64)), # 调整大小 transforms.RandomHorizontalFlip(), # 随机水平翻转 transforms.ToTensor(), # 转换为张量 transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # 归一化 ]) # 加载数据集 data_dir = 'path_to_animal_dataset' # 替换为实际路径 train_data = datasets.ImageFolder(root=f'{data_dir}/train', transform=transform) val_data = datasets.ImageFolder(root=f'{data_dir}/val', transform=transform) test_data = datasets.ImageFolder(root=f'{data_dir}/test', transform=transform) # 创建DataLoader batch_size = 32 train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True) val_loader = DataLoader(val_data, batch_size=batch_size, shuffle=False) test_loader = DataLoader(test_data, batch_size=batch_size, shuffle=False) ``` #### 模型构建 这里我们采用简单的卷积神经网络（CNN），并使用`nn.Sequential()`方法逐步堆叠各层结构。 ```python import torch.nn as nn import torch.optim as optim class AnimalClassifier(nn.Module): def __init__(self, num_classes=10): # 假设有10种不同的动物类别 super(AnimalClassifier, self).__init__() self.features = nn.Sequential( nn.Conv2d(3, 32, kernel_size=3, padding=1), # 输入通道数为3 (RGB)，输出通道数为32 nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(32, 64, kernel_size=3, padding=1), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(64, 128, kernel_size=3, padding=1), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2) ) self.classifier = nn.Sequential( nn.Linear(128 * 8 * 8, 512), # 根据输入尺寸调整线性层参数 nn.ReLU(), nn.Dropout(p=0.5), nn.Linear(512, num_classes) ) def forward(self, x): x = self.features(x) x = x.view(x.size(0), -1) # 展平特征图 x = self.classifier(x) return x model = AnimalClassifier(num_classes=len(train_data.classes)) print(model) ``` #### 损失函数与优化器 选择交叉熵损失作为目标函数，并应用随机梯度下降法（SGD）更新权重。 ```python criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model.to(device) ``` #### 训练过程 编写循环脚本执行批量训练逻辑，记录每轮次的表现指标以便后续分析。 ```python def train_model(model, criterion, optimizer, dataloaders, device, epochs=10): best_acc = 0.0 for epoch in range(epochs): model.train() running_loss = 0.0 for inputs, labels in dataloaders['train']: inputs, labels = inputs.to(device), labels.to(device) outputs = model(inputs) loss = criterion(outputs, labels) optimizer.zero_grad() loss.backward() optimizer.step() running_loss += loss.item() avg_loss = running_loss / len(dataloaders['train']) print(f'[Epoch {epoch+1}/{epochs}] Loss: {avg_loss:.4f}') return model dataloaders = {'train': train_loader} trained_model = train_model(model, criterion, optimizer, dataloaders, device=device, epochs=10) ``` #### 测试性能 最后，在独立测试集中验证最终版模型的效果如何[^1]。 ```python def evaluate_model(model, test_loader, device): correct = 0 total = 0 model.eval() with torch.no_grad(): for images, labels in test_loader: images, labels = images.to(device), labels.to(device) outputs = model(images) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item() accuracy = 100 * correct / total print(f'Test Accuracy of the Model on Test Images: {accuracy:.2f}%') evaluate_model(trained_model, test_loader=test_loader, device=device) ``` ---