13.5 迁移学习应用

import torch import torch.nn as nn import torchvision.models as models # 加载预训练ResNet-50 model = models.resnet50(pretrained=True) # 冻结所有卷积层参数 for param in model.parameters(): param.requires_grad = False # 替换最后的全连接层 num_features = model.fc.in_features model.fc = nn.Linear(num_features, 10) # 10分类任务 # 只有fc层的参数会被更新 optimizer = torch.optim.Adam(model.fc.parameters(), lr=0.001) # 查看可训练参数 trainable_params = sum(p.numel() for p in model.parameters() if p.requires_grad) print(f'可训练参数: {trainable_params}') # 仅约2万参数

# 加载预训练模型 model = models.resnet50(pretrained=True) # 替换分类层 num_features = model.fc.in_features model.fc = nn.Linear(num_features, 10) # 为不同层设置不同学习率 params = [ {'params': model.conv1.parameters(), 'lr': 1e-5}, # 浅层小学习率 {'params': model.layer1.parameters(), 'lr': 1e-4}, {'params': model.layer2.parameters(), 'lr': 1e-4}, {'params': model.layer3.parameters(), 'lr': 1e-3}, {'params': model.layer4.parameters(), 'lr': 1e-3}, {'params': model.fc.parameters(), 'lr': 1e-2}, # 分类层大学习率 ] optimizer = torch.optim.Adam(params) # 或者使用更简单的方式：分类层更大学习率 optimizer = torch.optim.Adam([ {'params': model.fc.parameters(), 'lr': 0.01}, {'params': [p for n, p in model.named_parameters() if 'fc' not in n], 'lr': 0.001} ])

import torch import torch.nn as nn import torchvision.models as models import torchvision.transforms as transforms from torchvision.datasets import ImageFolder from torch.utils.data import DataLoader # 数据预处理（使用ImageNet标准化） transform = { 'train': transforms.Compose([ transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), 'val': transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]) } # 加载自定义数据集 train_dataset = ImageFolder('data/train', transform=transform['train']) val_dataset = ImageFolder('data/val', transform=transform['val']) train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True) val_loader = DataLoader(val_dataset, batch_size=32) # 创建模型 model = models.resnet50(pretrained=True) num_classes = len(train_dataset.classes) model.fc = nn.Linear(model.fc.in_features, num_classes) # 训练配置 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = model.to(device) criterion = nn.CrossEntropyLoss() optimizer = torch.optim.Adam(model.parameters(), lr=0.001) scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)