Lightning Script

auto_encoder.py

# main.py
# ! pip install torchvision
import torch, torch.nn as nn, torch.utils.data as data, torchvision as tv, torch.nn.functional as F
import lightning as L

# --------------------------------
# Step 1: Define a LightningModule
# --------------------------------
# A LightningModule (nn.Module subclass) defines a full *system*
# (ie: an LLM, diffusion model, autoencoder, or simple image classifier).


class LitAutoEncoder(L.LightningModule):
    def __init__(self):
        super().__init__()
        self.encoder = nn.Sequential(nn.Linear(28 * 28, 128), nn.ReLU(), nn.Linear(128, 3))
        self.decoder = nn.Sequential(nn.Linear(3, 128), nn.ReLU(), nn.Linear(128, 28 * 28))

    def forward(self, x):
        # in lightning, forward defines the prediction/inference actions
        embedding = self.encoder(x)
        return embedding

    def training_step(self, batch, batch_idx):
        # training_step defines the train loop. It is independent of forward
        x, y = batch
        x = x.view(x.size(0), -1)
        z = self.encoder(x)
        x_hat = self.decoder(z)
        loss = F.mse_loss(x_hat, x)
        self.log("train_loss", loss)
        return loss

    def configure_optimizers(self):
        optimizer = torch.optim.Adam(self.parameters(), lr=1e-3)
        return optimizer

    # -------------------
    # Step 2: Define data
    # -------------------
    def prepare_data(self):
        tv.datasets.MNIST(".", download=True)

    def setup(self, stage):
        dataset = tv.datasets.MNIST(".", transform=tv.transforms.ToTensor())
        self.train_dataset, self.val_dataset = data.random_split(dataset, [55000, 5000])

    def train_dataloader(self):
        return data.DataLoader(self.train_dataset)

    def val_dataloader(self):
        return data.DataLoader(self.val_dataset)


# -------------------
# Step 3: Train
# -------------------
autoencoder = LitAutoEncoder()
trainer = L.Trainer()
trainer.fit(autoencoder)