数据预处理部分:
- 数据增强:torchvision中transforms模块自带功能,比较实用
- 数据预处理:torchvision中transforms也帮我们实现好了,直接调用即可
- DataLoader模块直接读取batch数据
网络模块设置:
- 加载预训练模型,torchvision中有很多经典网络架构,调用起来十分方便,并且可以用人家训练好的权重参数来继续训练,也就是所谓的迁移学习
- 需要注意的是别人训练好的任务跟咱们的可不是完全一样,需要把最后的head层改一改,一般也就是最后的全连接层,改成咱们自己的任务
- 训练时可以全部重头训练,也可以只训练最后咱们任务的层,因为前几层都是做特征提取的,本质任务目标是一致的
网络模型保存与测试
- 模型保存的时候可以带有选择性,例如在验证集中如果当前效果好则保存
- 读取模型进行实际测试
data_transforms = {'train': transforms.Compose([transforms.Resize([96, 96]),transforms.RandomRotation(45),transforms.CenterCrop(64),transforms.RandomHorizontalFlip(p=0.5),transforms.RandomVerticalFlip(p=0.5),transforms.ColorJitter(brightness=0.2, contrast=0.1, saturation=0.1, hue=0.1),transforms.RandomGrayscale(p=0.025),transforms.ToTensor(),transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),'valid': transforms.Compose([transforms.Resize([64, 64]),transforms.ToTensor(),transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
}
选择性的权重更新
def set_parameter_requires_grad(model, feature_extracting):if feature_extracting:for param in model.parameters():param.requires_grad = False
自定义修改模型输出层,以resnet18为例
def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):model_ft = models.resnet18(pretrained=use_pretrained)set_parameter_requires_grad(model_ft, feature_extract)num_ftrs = model_ft.fc.in_featuresmodel_ft.fc = nn.Linear(num_ftrs, 102)input_size = 64return model_ft, input_size
训练权重 选择
model_ft, input_size = initialize_model(model_name, 102, feature_extract, use_pretrained=True)
model_ft = model_ft.to(device)
filename='checkpoint.pth'
params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:params_to_update = []for name,param in model_ft.named_parameters():if param.requires_grad == True:params_to_update.append(param)print("\t",name)
else:for name,param in model_ft.named_parameters():if param.requires_grad == True:print("\t",name)
基本训练代码
def train_model(model, dataloaders, criterion, optimizer, num_epochs=25,filename='best.pt'):since = time.time()best_acc = 0model.to(device)val_acc_history = []train_acc_history = []train_losses = []valid_losses = []LRs = [optimizer.param_groups[0]['lr']]best_model_wts = copy.deepcopy(model.state_dict())for epoch in range(num_epochs):print('Epoch {}/{}'.format(epoch, num_epochs - 1))print('-' * 10)for phase in ['train', 'valid']:if phase == 'train':model.train() else:model.eval() running_loss = 0.0running_corrects = 0for inputs, labels in dataloaders[phase]:inputs = inputs.to(device)labels = labels.to(device)optimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, labels)_, preds = torch.max(outputs, 1)if phase == 'train':loss.backward()optimizer.step()running_loss += loss.item() * inputs.size(0)running_corrects += torch.sum(preds == labels.data)epoch_loss = running_loss / len(dataloaders[phase].dataset)epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)time_elapsed = time.time() - sinceprint('Time elapsed {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))if phase == 'valid' and epoch_acc > best_acc:best_acc = epoch_accbest_model_wts = copy.deepcopy(model.state_dict())state = {'state_dict': model.state_dict(),'best_acc': best_acc,'optimizer' : optimizer.state_dict(),}torch.save(state, filename)if phase == 'valid':val_acc_history.append(epoch_acc)valid_losses.append(epoch_loss)if phase == 'train':train_acc_history.append(epoch_acc)train_losses.append(epoch_loss)print('Optimizer learning rate : {:.7f}'.format(optimizer.param_groups[0]['lr']))LRs.append(optimizer.param_groups[0]['lr'])print()scheduler.step()time_elapsed = time.time() - sinceprint('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))print('Best val Acc: {:4f}'.format(best_acc))model.load_state_dict(best_model_wts)return model, val_acc_history, train_acc_history, valid_losses, train_losses, LRs
调用训练
model_ft, val_acc_history, train_acc_history, valid_losses, train_losses, LRs = train_model(model_ft, dataloaders, criterion, optimizer_ft, num_epochs=20)
def im_convert(tensor):""" 展示数据"""image = tensor.to("cpu").clone().detach()image = image.numpy().squeeze()image = image.transpose(1,2,0)image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))image = image.clip(0, 1)return image