pytorch-lightning: custom training with 0.8.0.dev0 gives import error

Due to another issue and the advise to upgrade to master, I upgraded to 0.8.0.dev0. Now, the same model and no code changes gives the error:

Traceback (most recent call last):
  File "/home/luca/project/apps/train_siamnet.py", line 3, in <module>
    from ..models.siamnet import SiameseNet
ImportError: attempted relative import with no known parent package

This did not happen before and does not make sense TBH as there is no such invalid import.

After that, the thing just hangs during GGPus initialising phase:

initializing ddp: LOCAL_RANK: 0/3 WORLD_SIZE:4

I am trying to train my model on multiple GPUs and the training code is:

model = SiameseNet(hparams)
if torch.cuda.is_available():
        trainer = Trainer(gpus=-1, distributed_backend='ddp')
else:
        trainer = Trainer()

trainer.fit(model)

The model def is:

class SiameseNet(pl.LightningModule):
    """
    Implement a siamese network as a feature extractor withh Lightning module
    """
    def __init__(self,
                 hparams):
        """
        Build the network
        """
        super(SiameseNet, self).__init__()
        self.net = self._build_net()
        self.hparams = hparams
        self.train_data_path = hparams.get('train_data_path', None)
        self.test_data_path = hparams.get('test_data_path', None)
        self.val_data_path = hparams.get('val_data_path', None)
        self.train_dataset = None
        self.val_dataset = None
        self.test_dataset = None

        self.lossfn = TripletLoss(margin=1.0)

    def forward_once(self, x):
        output = self.net(x)
        output = torch.squeeze(output)
        return output

    def forward(self, input1, input2, input3=None):
        output1 = self.forward_once(input1)
        output2 = self.forward_once(input2)

        if input3 is not None:
            output3 = self.forward_once(input3)
            return output1, output2, output3

        return output1, output2

    @staticmethod
    def _build_net():
        net = nn.Sequential(
            nn.Conv2d(3, 32,kernel_size=3,stride=2),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(32),

            nn.Conv2d(32, 64, kernel_size=3, stride=2),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(64),

            nn.Conv2d(64, 128, kernel_size=3, stride=2),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(128),

            nn.Conv2d(128, 256, kernel_size=1, stride=2),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(256),

            nn.Conv2d(256, 256, kernel_size=1, stride=2),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(256),

            nn.Conv2d(256, 512, kernel_size=3, stride=2),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(512),

            nn.Conv2d(512, 1024, kernel_size=1, stride=1),
            nn.ReLU(inplace=True),
            nn.BatchNorm2d(1024))

        return net

    def prepare_data(self):
        transform = torchvision.transforms.Compose([
            torchvision.transforms.Resize((128, 128)),
            torchvision.transforms.ColorJitter(hue=.05, saturation=.05),
            torchvision.transforms.RandomHorizontalFlip(),
            torchvision.transforms.RandomRotation(20, resample=PIL.Image.BILINEAR),
            torchvision.transforms.ToTensor()
        ])

        if self.train_data_path:
            train_folder_dataset = dset.ImageFolder(root=self.train_data_path)
            self.train_dataset = SiameseTriplet(image_folder_dataset=train_folder_dataset,
                                                transform=transform)
        if self.val_data_path:
            val_folder_dataset = dset.ImageFolder(root=self.val_data_path)
            self.val_dataset = SiameseTriplet(image_folder_dataset=val_folder_dataset)

        if self.test_data_path:
            test_folder_dataset = dset.ImageFolder(root=self.test_data_path)
            self.test_dataset = SiameseTriplet(image_folder_dataset=test_folder_dataset)

    def training_step(self, batch, batch_idx):
        anchor, positive, negative = batch
        anchor_out, positive_out, negative_out = self.forward(anchor, positive, negative)
        loss_val = self.lossfn(anchor_out, positive_out, negative_out)
        return {'loss': loss_val}

    def configure_optimizers(self):
        optimizer = optim.Adam(self.parameters(), lr=self.hparams.get('learning_rate', 0.001))
        scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=10)
        return [optimizer], [scheduler]

    @pl.data_loader
    def train_dataloader(self):
        if self.train_dataset:
            return DataLoader(self.train_dataset,
                              self.hparams.get('batch_size', 64),
                              num_workers=12)
        return None