Data loading with torchvision in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of torchvision DataLoader batch size

What is the shape of the images batch tensor returned by this DataLoader?

Computer Vision

import torchvision.transforms as transforms
from torchvision.datasets import FakeData
from torch.utils.data import DataLoader

transform = transforms.ToTensor()
dataset = FakeData(size=100, image_size=(3, 32, 32), transform=transform)
dataloader = DataLoader(dataset, batch_size=8)

images, labels = next(iter(dataloader))
print(images.shape)

A torch.Size([32, 32, 3, 8])

B torch.Size([3, 8, 32, 32])

C torch.Size([8, 32, 32, 3])

D torch.Size([8, 3, 32, 32])

💡 Hint

Remember batch size is the first dimension in the batch tensor.

The DataLoader returns batches with shape (batch_size, channels, height, width). Here batch_size=8, channels=3, height=32, width=32.

🧠 Conceptual

intermediate

Purpose of torchvision transforms

What is the main purpose of using transforms in torchvision datasets?

A To increase the dataset size by duplicating images

B To convert images to tensors and apply preprocessing like normalization

C To load images faster from disk

D To change the file format of images on disk

💡 Hint

Think about what happens before feeding images to a model.

Transforms convert images to tensors and apply preprocessing steps like resizing, cropping, or normalization to prepare data for training.

❓ Hyperparameter

advanced

Effect of shuffle=True in DataLoader

What effect does setting shuffle=True have when creating a DataLoader?

A Randomizes the order of data samples at each epoch

B Loads data samples in sorted order by label

C Duplicates data samples to increase dataset size

D Loads only a subset of the dataset

💡 Hint

Think about how shuffling affects training data order.

shuffle=True randomizes the order of samples each epoch to reduce model overfitting to data order.

🔧 Debug

advanced

Error when using torchvision transforms

What error will this code raise and why? import torchvision.transforms as transforms from torchvision.datasets import FakeData from torch.utils.data import DataLoader transform = transforms.Normalize(mean=[0.5], std=[0.5]) dataset = FakeData(size=10, image_size=(3, 32, 32), transform=transform) dataloader = DataLoader(dataset, batch_size=2) batch = next(iter(dataloader))

A TypeError because Normalize expects a tensor but receives a PIL image

B RuntimeError because batch size is too small

C ValueError because mean and std lengths do not match channels

D No error, code runs successfully

💡 Hint

Normalize requires tensor input, check transform order.

Normalize expects a tensor input but FakeData returns PIL images by default, causing a TypeError.

❓ Model Choice

expert

Choosing the best DataLoader setting for large image dataset

You have a large image dataset and want to train a model efficiently using torchvision DataLoader. Which setting combination is best?

A batch_size=1, shuffle=False, num_workers=0

B batch_size=16, shuffle=True, num_workers=0

C batch_size=64, shuffle=True, num_workers=4

D batch_size=128, shuffle=False, num_workers=0

💡 Hint

Consider batch size, shuffling, and parallel data loading.

A larger batch size with shuffling and multiple workers speeds up training and improves generalization.