lightning/pl_examples/basic_examples/autoencoder.py

# Copyright The PyTorch Lightning team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from argparse import ArgumentParser

import torch
import torch.nn.functional as F
from torch import nn
from torch.utils.data import DataLoader, random_split

import pytorch_lightning as pl
from pl_examples import _DATASETS_PATH, _TORCHVISION_MNIST_AVAILABLE, cli_lightning_logo
from pytorch_lightning.utilities.imports import _TORCHVISION_AVAILABLE

if _TORCHVISION_AVAILABLE:
    from torchvision import transforms
if _TORCHVISION_MNIST_AVAILABLE:
    from torchvision.datasets import MNIST
else:
    from tests.helpers.datasets import MNIST


class LitAutoEncoder(pl.LightningModule):
    """
    >>> LitAutoEncoder()  # doctest: +ELLIPSIS +NORMALIZE_WHITESPACE
    LitAutoEncoder(
      (encoder): ...
      (decoder): ...
    )
    """

    def __init__(self, hidden_dim: int = 64):
        super().__init__()
        self.encoder = nn.Sequential(
            nn.Linear(28 * 28, hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, 3),
        )
        self.decoder = nn.Sequential(
            nn.Linear(3, hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, 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):
        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)
        return loss

    def validation_step(self, batch, batch_idx):
        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('valid_loss', loss, on_step=True)

    def test_step(self, batch, batch_idx):
        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('test_loss', loss, on_step=True)

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


def cli_main():
    pl.seed_everything(1234)

    # ------------
    # args
    # ------------
    parser = ArgumentParser()
    parser.add_argument('--batch_size', default=32, type=int)
    parser.add_argument('--hidden_dim', type=int, default=64)
    parser = pl.Trainer.add_argparse_args(parser)
    args = parser.parse_args()

    # ------------
    # data
    # ------------
    dataset = MNIST(_DATASETS_PATH, train=True, download=True, transform=transforms.ToTensor())
    mnist_test = MNIST(_DATASETS_PATH, train=False, download=True, transform=transforms.ToTensor())
    mnist_train, mnist_val = random_split(dataset, [55000, 5000])

    train_loader = DataLoader(mnist_train, batch_size=args.batch_size)
    val_loader = DataLoader(mnist_val, batch_size=args.batch_size)
    test_loader = DataLoader(mnist_test, batch_size=args.batch_size)

    # ------------
    # model
    # ------------
    model = LitAutoEncoder(args.hidden_dim)

    # ------------
    # training
    # ------------
    trainer = pl.Trainer.from_argparse_args(args)
    trainer.fit(model, train_loader, val_loader)

    # ------------
    # testing
    # ------------
    result = trainer.test(test_dataloaders=test_loader)
    print(result)


if __name__ == '__main__':
    cli_lightning_logo()
    cli_main()