DataLoaders in PyTorch

import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=True)

from torch.utils.data import Dataset

class MyDataset(Dataset):
    def __init__(self, csv_file):
        self.data = pd.read_csv(csv_file)
    def __len__(self):
        return len(self.data)
    def __getitem__(self, idx):
        row = self.data.iloc[idx]
        x = torch.tensor(row[:-1], dtype=torch.float32)
        y = torch.tensor(row[-1], dtype=torch.long)
        return x, y

• batch_size: number of samples per batch.
• shuffle: shuffle data every epoch (for training).
• num_workers: number of subprocesses for loading (increase for speed).
• drop_last: drop last incomplete batch (for some models).