Shortcuts

Child Modules

Research projects tend to test different approaches to the same dataset. This is very easy to do in Lightning with inheritance.

For example, imagine we now want to train an Autoencoder to use as a feature extractor for MNIST images. We are extending our Autoencoder from the LitMNIST-module which already defines all the dataloading. The only things that change in the Autoencoder model are the init, forward, training, validation and test step.

class Encoder(torch.nn.Module):
    pass

class Decoder(torch.nn.Module):
    pass

class AutoEncoder(LitMNIST):

    def __init__(self):
        super().__init__()
        self.encoder = Encoder()
        self.decoder = Decoder()
        self.metric = MSE()

    def forward(self, x):
        return self.encoder(x)

    def training_step(self, batch, batch_idx):
        x, _ = batch

        representation = self.encoder(x)
        x_hat = self.decoder(representation)

        loss = self.metric(x, x_hat)
        return loss

    def validation_step(self, batch, batch_idx):
        self._shared_eval(batch, batch_idx, 'val')

    def test_step(self, batch, batch_idx):
        self._shared_eval(batch, batch_idx, 'test')

    def _shared_eval(self, batch, batch_idx, prefix):
        x, _ = batch
        representation = self.encoder(x)
        x_hat = self.decoder(representation)

        loss = self.metric(x, x_hat)
        self.log(f'{prefix}_loss', loss)

and we can train this using the same trainer

autoencoder = AutoEncoder()
trainer = Trainer()
trainer.fit(autoencoder)

And remember that the forward method should define the practical use of a LightningModule. In this case, we want to use the AutoEncoder to extract image representations

some_images = torch.Tensor(32, 1, 28, 28)
representations = autoencoder(some_images)
Read the Docs v: stable
Versions
latest
stable
1.0.3
1.0.2
1.0.1
1.0.0
0.10.0
0.9.0
0.8.5
0.8.4
0.8.3
0.8.2
0.8.1
0.8.0
0.7.6
0.7.5
0.7.4
0.7.3
0.7.2
0.7.1
0.7.0
0.6.0
0.5.3.2
0.5.3
0.4.9
Downloads
pdf
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.