datamodule.py

import os

import numpy as np
import pytorch_lightning as pl
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader, random_split
from torchvision.datasets import MNIST

PATH_DATASETS = os.environ.get("PATH_DATASETS", ".")
BATCH_SIZE = 256 if torch.cuda.is_available() else 64
NUM_WORKERS = int(os.cpu_count() / 2)

class MNISTDataModule(pl.LightningDataModule):
    def __init__(
        self,
        data_dir: str = PATH_DATASETS,
        batch_size: int = BATCH_SIZE,
        num_workers: int = NUM_WORKERS,
    ):
        super().__init__()
        self.data_dir = data_dir
        self.batch_size = batch_size
        self.num_workers = num_workers

        self.transform = transforms.Compose(
            [
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,)),
            ]
        )

        self.dims = (1, 28, 28)
        self.num_classes = 10

    def prepare_data(self):
        # download
        MNIST(self.data_dir, train=True, download=True)
        MNIST(self.data_dir, train=False, download=True)

    def setup(self, stage=None):
        # Assign train/val datasets for use in dataloaders
        if stage == "fit" or stage is None:
            mnist_full = MNIST(self.data_dir, train=True, transform=self.transform)
            self.mnist_train, self.mnist_val = random_split(mnist_full, [55000, 5000])

        # Assign test dataset for use in dataloader(s)
        if stage == "test" or stage is None:
            self.mnist_test = MNIST(self.data_dir, train=False, transform=self.transform)

    def train_dataloader(self):
        return DataLoader(
            self.mnist_train,
            batch_size=self.batch_size,
            num_workers=self.num_workers,
        )

    def val_dataloader(self):
        return DataLoader(self.mnist_val, batch_size=self.batch_size, num_workers=self.num_workers)

    def test_dataloader(self):
        return DataLoader(self.mnist_test, batch_size=self.batch_size, num_workers=self.num_workers)