Continue training with torch.save and torch.load - key error messages

Question

I am new to Torch and using a code template for a masked-cnn model. In order to be prepared if the training is interrupted, I have used torch.save and torch.load in my code, but I think I cannot use this alone for continuing training sessions? I start training by:

model = train_mask_net(64)

This calls the function train_mask.net where I have included torch.save in the epoch loop. I wanted to load one of the saved models and continue training with torch.load in front of the loop, but I got "key error" messages for the optimizer, loss and epoch call. Should I have made a specific checkpoint function as I have seen in some tutorials or is there a possibility that I can continue training with the files saved by the torch.saved command?

def train_mask_net(num_epochs=1):
    data = MaskDataset(list(data_mask.keys()))
    data_loader = torch.utils.data.DataLoader(data, batch_size=8, shuffle=True, num_workers=4)

    model = XceptionHourglass(max_clz+2)
    model.cuda()
    dp = torch.nn.DataParallel(model)
    loss = nn.CrossEntropyLoss()

    params = [p for p in dp.parameters() if p.requires_grad]
    optimizer = torch.optim.RMSprop(params, lr=2.5e-4,  momentum=0.9)
    lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
                                                   step_size=6,
                                                   gamma=0.9)
    
    checkpoint = torch.load('imaterialist2020-pretrain-models/maskmodel_160.model_ep17')
    #print(checkpoint)
    model.load_state_dict(checkpoint)
    #optimizer.load_state_dict(checkpoint)
    #epoch = checkpoint['epoch']
    #loss = checkpoint['loss']
    
    for epoch in range(num_epochs):
        print(epoch)
        total_loss = []
        prog = tqdm(data_loader, total=len(data_loader))
        for i, (imag, mask) in enumerate(prog):
            X = imag.cuda()
            y = mask.cuda()
            xx = dp(X)
            # to 1D-array
            y = y.reshape((y.size(0),-1))  # batch, flatten-img
            y = y.reshape((y.size(0) * y.size(1),))  # flatten-all
            xx = xx.reshape((xx.size(0), xx.size(1), -1))  # batch, channel, flatten-img
            xx = torch.transpose(xx, 2, 1)  # batch, flatten-img, channel
            xx = xx.reshape((xx.size(0) * xx.size(1),-1))  # flatten-all, channel

            losses = loss(xx, y)

            prog.set_description("loss:%05f"%losses)
            optimizer.zero_grad()
            losses.backward()
            optimizer.step()

            total_loss.append(losses.detach().cpu().numpy())
            torch.save(model.state_dict(), MODEL_FILE_DIR+"maskmodel_%d.model"%attr_image_size[0]+'_ep'+str(epoch)+'_tsave')

        prog, X, xx, y, losses = None, None, None, None, None,
        torch.cuda.empty_cache()
        gc.collect()
    return model

I don't think its necessary, but the xceptionhour class looks like this:

class XceptionHourglass(nn.Module):
    def __init__(self, num_classes):
        super(XceptionHourglass, self).__init__()
        self.num_classes = num_classes

        self.conv1 = nn.Conv2d(3, 128, 3, 2, 1, bias=True)
        self.bn1 = nn.BatchNorm2d(128)
        self.mish = Mish()

        self.conv2 = nn.Conv2d(128, 256, 3, 1, 1, bias=True)
        self.bn2 = nn.BatchNorm2d(256)

        self.block1 = HourglassNet(4, 256)
        self.bn3 = nn.BatchNorm2d(256)
        self.block2 = HourglassNet(4, 256)
...

Answer 1

torch.save(model.state_dict(), PATH) only saves the model weights.

To also save optimizer, loss, epoch, etc., change it to:

torch.save({'model': model.state_dict(),
            'optimizer': optimizer.state_dict(),
            'loss': loss,
            'epoch': epoch,
            # ...
            }, PATH)

To load them:

checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model'])
optimizer.load_state_dict(checkpoint['optimizer'])
epoch = checkpoint['epoch']
loss = checkpoint['loss']

More on it here .