Data Loading & Preprocessing

Learn to load, transform, and batch datasets using PyTorch DataLoader and torchvision transforms.

Using DataLoader

python

from torch.utils.data import DataLoader, TensorDatasetimport torch X = torch.randn(1000, 10)y = torch.randint(0, 3, (1000,)) dataset = TensorDataset(X, y)loader = DataLoader(dataset, batch_size=32, shuffle=True) for batch_X, batch_y in loader:    print(batch_X.shape, batch_y.shape)    break

Transforms

python

from torchvision import transforms transform = transforms.Compose([    transforms.ToTensor(),    transforms.Normalize(mean=[0.5], std=[0.5]),    transforms.RandomHorizontalFlip(),])