### 基于CUB_200_2011数据集的细粒度鸟类图像分类完整Python代码 以下是基于CUB_200_2011数据集的细粒度鸟类图像分类的完整Python代码实现。此代码使用卷积神经网络（CNN）作为基础模型，并结合迁移学习技术来提高分类性能。 #### 数据预处理 为了加载和准备CUB_200_2011数据集，我们需要定义一些辅助函数来进行图像增强、标签映射和其他必要的操作。 ```python import os from torchvision import datasets, models, transforms from torch.utils.data import DataLoader import torch.nn as nn import torch.optim as optim import torch from sklearn.model_selection import train_test_split from PIL import Image import numpy as np # 定义数据变换 data_transforms = { 'train': transforms.Compose([ transforms.Resize((224, 224)), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), 'val': transforms.Compose([ transforms.Resize((224, 224)), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]) } # 加载数据集 def load_cub_data(data_dir): image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']} dataloaders = {x: DataLoader(image_datasets[x], batch_size=32, shuffle=True, num_workers=4) for x in ['train', 'val']} dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']} class_names = image_datasets['train'].classes return dataloaders, dataset_sizes, class_names data_dir = './CUB_200_2011' # 替换为实际路径 dataloaders, dataset_sizes, class_names = load_cub_data(data_dir) ``` #### 模型构建与训练 我们使用ResNet-50作为基线模型，并对其进行微调以适应CUB_200_2011数据集中的特定任务需求。 ```python device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") # 使用预训练的ResNet-50模型 model_ft = models.resnet50(pretrained=True) # 修改最后一层全连接层以适配200个类别 num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, len(class_names)) model_ft = model_ft.to(device) criterion = nn.CrossEntropyLoss() # 只优化最后的全连接层参数 optimizer_ft = optim.SGD(model_ft.fc.parameters(), lr=0.001, momentum=0.9) # 学习率调度器 exp_lr_scheduler = optim.lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1) # 训练模型 def train_model(model, criterion, optimizer, scheduler, num_epochs=25): best_model_wts = model.state_dict() best_acc = 0.0 for epoch in range(num_epochs): print(f'Epoch {epoch}/{num_epochs - 1}') print('-' * 10) # 每个epoch都有训练和验证阶段 for phase in ['train', 'val']: if phase == 'train': model.train() else: model.eval() running_loss = 0.0 running_corrects = 0 # 遍历数据 for inputs, labels in dataloaders[phase]: inputs = inputs.to(device) labels = labels.to(device) # 清零梯度 optimizer.zero_grad() # 前向传播 with torch.set_grad_enabled(phase == 'train'): outputs = model(inputs) _, preds = torch.max(outputs, 1) loss = criterion(outputs, labels) # 如果是训练阶段，则反向传播并更新权重 if phase == 'train': loss.backward() optimizer.step() # 统计损失和准确率 running_loss += loss.item() * inputs.size(0) running_corrects += torch.sum(preds == labels.data) if phase == 'train': scheduler.step() epoch_loss = running_loss / dataset_sizes[phase] epoch_acc = running_corrects.double() / dataset_sizes[phase] print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}') # 更新最佳模型权重 if phase == 'val' and epoch_acc > best_acc: best_acc = epoch_acc best_model_wts = model.state_dict() print('Best val Acc: {:4f}'.format(best_acc)) model.load_state_dict(best_model_wts) return model model_trained = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25) torch.save(model_trained.state_dict(), 'resnet50_bird_classifier.pth') ``` 以上代码实现了基于CUB_200_2011数据集的细粒度鸟类图像分类任务[^1]。它利用了PyTorch框架的强大功能，包括数据加载、模型定义、训练过程管理等功能模块。 --- ###