lightning_standard_way.py

class StandardMNIST(LightningModule):
    def __init__(self):
        super().__init__()
        # mnist images are (1, 28, 28) (channels, width, height)
        self.layer1 = torch.nn.Linear(28 * 28, 128)
        self.layer2 = torch.nn.Linear(128, 256)
        self.layer3 = torch.nn.Linear(256, 10)

    def forward(self, x):
        batch_size, channels, width, height = x.size()

        # (b, 1, 28, 28) -> (b, 1*28*28)
        x = x.view(batch_size, -1)

        x = self.layer1(x)
        x = torch.relu(x)

        x = self.layer2(x)
        x = torch.relu(x)

        x = self.layer3(x)
        x = torch.log_softmax(x, dim=1)

        return x

    def training_step(self, batch, batch_idx):
        data, target = batch
        logits = self.forward(data)
        loss = F.nll_loss(logits, target)
        return {'loss': loss}

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