Lightning基础训练尝试实例
一、训练任务概述
动机：由于后续的课题中会用到类似图像去噪的算法，考虑先用U-Net，这里做一个前置的尝试。
训练任务：分割出图像中的细胞。
数据集：可私
数据集结构：
二、具体实现
U-Net的网络实现是现成的，只需要在网上找一个比较漂亮的实现（一般都是模块化，写的很漂亮）copy就可以了，需要特别注意的是最后整合的模型：
2.1 基础模型模块实现
双卷积模块
class DoubleConv(nn.Module):"""(convolution => [BN] => ReLU) * 2"""def __init__(self, in_channels, out_channels, mid_channels=None):super().__init__()if not mid_channels:mid_channels = out_channelsself.double_conv = nn.Sequential(nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False),nn.BatchNorm2d(mid_channels),nn.ReLU(inplace=True),nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False),nn.BatchNorm2d(out_channels),nn.ReLU(inplace=True))def forward(self, x):return self.double_conv(x)上采样模块
class Up(nn.Module):"""Upscaling then double conv"""def __init__(self, in_channels, out_channels, bilinear=True):super().__init__()# if bilinear, use the normal convolutions to reduce the number of channelsif bilinear:self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)else:self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)self.conv = DoubleConv(in_channels, out_channels)def forward(self, x1, x2):x1 = self.up(x1)# input is CHWdiffY = x2.size()[2] - x1.size()[2]diffX = x2.size()[3] - x1.size()[3]x1 = torch.nn.functional.pad(x1, [diffX // 2, diffX - diffX // 2,diffY // 2, diffY - diffY // 2])x = torch.cat([x2, x1], dim=1)return self.conv(x)下采样模块
class Down(nn.Module):"""Downscaling with maxpool then double conv"""def __init__(self, in_channels, out_channels):super().__init__()self.maxpool_conv = nn.Sequential(nn.MaxPool2d(2),DoubleConv(in_channels, out_channels))def forward(self, x):return self.maxpool_conv(x)输出层
class OutConv(nn.Module):def __init__(self, in_channels, out_channels):super(OutConv, self).__init__()self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)def forward(self, x):return self.conv(x)2.2 整合模块->模型
class UNet(L.LightningModule):def __init__(self, n_channels, n_classes, bilinear=False):super(UNet, self).__init__()self.n_channels = n_channelsself.n_classes = n_classesself.bilinear = bilinearself.inc = (DoubleConv(n_channels, 64))self.down1 = (Down(64, 128))self.down2 = (Down(128, 256))self.down3 = (Down(256, 512))factor = 2 if bilinear else 1self.down4 = (Down(512, 1024 // factor))self.up1 = (Up(1024, 512 // factor, bilinear))self.up2 = (Up(512, 256 // factor, bilinear))self.up3 = (Up(256, 128 // factor, bilinear))self.up4 = (Up(128, 64, bilinear))self.outc = (OutConv(64, n_classes))def forward(self, x):x1 = self.inc(x)x2 = self.down1(x1)x3 = self.down2(x2)x4 = self.down3(x3)x5 = self.down4(x4)x = self.up1(x5, x4)x = self.up2(x, x3)x = self.up3(x, x2)x = self.up4(x, x1)logits = self.outc(x)return logits# 对应的层设置检查点，节省显存m，可用可不用def use_checkpointing(self):self.inc = torch.utils.checkpoint(self.inc)self.down1 = torch.utils.checkpoint(self.down1)self.down2 = torch.utils.checkpoint(self.down2)self.down3 = torch.utils.checkpoint(self.down3)self.down4 = torch.utils.checkpoint(self.down4)self.up1 = torch.utils.checkpoint(self.up1)self.up2 = torch.utils.checkpoint(self.up2)self.up3 = torch.utils.checkpoint(self.up3)self.up4 = torch.utils.checkpoint(self.up4)self.outc = torch.utils.checkpoint(self.outc)# 定义优化器def configure_optimizers(self):optimizer = torch.optim.Adam(self.parameters(),lr=0.001)return optimizer# 定义train的单步流程def training_step(self,train_batch,batch_index):image,label = train_batchimage_hat = self.forward(image)# U-Net的lossloss = nn.functional.mse_loss(image_hat,label)return loss# 定义val的单步流程def validation_step(self, val_batch,batch_index):image,label = val_batchimage_hat = self.forward(image)# U-Net的lossloss = nn.functional.mse_loss(image_hat,label)self.log('val_loss',loss)return loss注意：模块可以不需要继承自L.LightningModule，只要最后整合的时候继承自L.LightningModule就可以了。
2.3 数据划分
重定义Dataset类，供数据集划分函数调用，二者要相互配合
class UDataset(Dataset):def __init__(self,image_dir,mask_dir,transform=None):self.image_dir = image_dirself.mask_dir = mask_dirif transform is not None:self.transform = transformelse:self.transform = Nonedef __getitem__(self, index):image = Image.open(self.image_dir[index]).convert('RGB')label = Image.open(self.mask_dir[index]).convert('RGB')if self.transform is not None:image = self.transform(image)label = self.transform(label)return image,labeldef __len__(self):return len(self.image_dir)定义数据集划分函数（包括"找出文件列表"、"定义数据预处理方式"、“定义批量大小”）
train_image_dir = "./data/train/image/*.png"
train_label_dir = "./data/train/label/*.png"
val_image_dir = "./data/val/image/*.png"
val_label_dir = "./data/val/label/*.png" def data_process(train_image_dir,train_label_dir,val_image_dir,val_label_dir):# 查找路径下的所有文件，返回文件路径列表train_image_list = glob.glob(train_image_dir)train_label_list = glob.glob(train_label_dir)val_image_list = glob.glob(val_image_dir)val_label_list = glob.glob(val_label_dir)# 数据处理train_data_transform = transforms.Compose([transforms.Resize((256,256)),transforms.ToTensor()])val_data_transform = transforms.Compose([ transforms.Resize((256,256)),transforms.ToTensor()])train_dataloader = data.DataLoader(UDataset(train_image_list,train_label_list,train_data_transform),batch_size=5,shuffle=True)val_dataloader = data.DataLoader(UDataset(val_image_list,val_label_list,val_data_transform),batch_size=5,shuffle=False)return train_dataloader,val_dataloader2.4 模型验证
在训练之前，要看一下模型的结构有没有错误，用summary打印出网络的结构
# 模型验证device = torch.device("cuda" if torch.cuda.is_available() else "cpu")model = UNet(n_channels=3,n_classes=1).to(device)print(summary(model,(3,512,512)))也可以用其他的方法查看网络结构
2.5 模型训练
加入TensorBoardLogger是为了可视化训练Loss
训练的流程遵循前文的基本流程
# 创建 TensorBoardLoggerlogger = TensorBoardLogger("tb_logs", name="unet")# 创建 Trainertrainer = L.Trainer(max_epochs=20, logger=logger)# 划分数据集train_dataloader,val_dataloader = data_process(train_image_dir,train_label_dir,val_image_dir,val_label_dir)# 创建模型model = UNet(n_channels=3,n_classes=1)# 启动模型训练过程trainer.fit(model,train_dataloader,val_dataloader)# 保存模型权重torch.save(model.state_dict(),'./model.pth')