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.

Practice

1. What is the main purpose of using torchvision.datasets in a computer vision project?

easy

A. To easily download and load popular image datasets

B. To create neural network layers

C. To visualize images in a dataset

D. To perform mathematical operations on tensors

Solution

1. Step 1: Understand the role of torchvision.datasets

   It provides ready-to-use popular image datasets like CIFAR10, MNIST, etc., for easy loading.

2. Step 2: Differentiate from other torchvision modules

   Other modules handle transforms or models, but datasets focus on loading data.

3. Final Answer:

   To easily download and load popular image datasets -> Option A

4. Quick Check:

   torchvision.datasets = load datasets [OK]

Hint: Datasets module is for loading data, not building models [OK]

Common Mistakes:

• Confusing datasets with model creation
• Thinking datasets handle image visualization
• Assuming datasets perform tensor math

2. Which of the following is the correct way to import the DataLoader class from torchvision?

easy

A. from torch.utils.data import DataLoader

B. from torchvision import DataLoader

C. import DataLoader from torchvision

D. from torchvision.datasets import DataLoader

Solution

1. Step 1: Recall the correct import path for DataLoader

   DataLoader is part of torch.utils.data, not torchvision directly.

2. Step 2: Check each option's syntax and source

   Only from torch.utils.data import DataLoader correctly imports DataLoader from torch.utils.data.

3. Final Answer:

   from torch.utils.data import DataLoader -> Option A

4. Quick Check:

   DataLoader import = torch.utils.data [OK]

Hint: DataLoader is in torch.utils.data, not torchvision [OK]

Common Mistakes:

• Importing DataLoader directly from torchvision
• Using incorrect import syntax
• Confusing datasets and DataLoader imports

3. What will be the output shape of images loaded from CIFAR10 dataset using torchvision if no transform is applied?

medium

A. [224, 224, 3]

B. [1, 28, 28]

C. [3, 32, 32]

D. [32, 32, 3]

Solution

1. Step 1: Recall CIFAR10 image dimensions

   CIFAR10 images are 32x32 pixels with 3 color channels (RGB).

2. Step 2: Understand PyTorch image tensor shape format

   PyTorch uses channel-first format: [channels, height, width], so shape is [3, 32, 32].

3. Final Answer:

   [3, 32, 32] -> Option C

4. Quick Check:

   CIFAR10 image shape = [3, 32, 32] [OK]

Hint: PyTorch images are channel-first: channels, height, width [OK]

Common Mistakes:

• Confusing channel order with height-width-channel
• Assuming grayscale images with 1 channel
• Mixing CIFAR10 size with MNIST or ImageNet

4. Identify the error in this code snippet for loading MNIST dataset with transforms:

from torchvision import datasets, transforms
transform = transforms.Compose([transforms.Resize(32), transforms.ToTensor()])
mnist_data = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(mnist_data, batch_size=64, shuffle=True)

medium

A. batch_size must be 1 or 32 only

B. Missing import of DataLoader from torch.utils.data

C. MNIST dataset does not support transforms

D. Transforms.Resize cannot resize images

Solution

1. Step 1: Check imports for DataLoader usage

   DataLoader is used but not imported, causing a NameError.

2. Step 2: Verify other parts of the code

   Transforms.Resize and MNIST support transforms; batch_size can be any positive integer.

3. Final Answer:

   Missing import of DataLoader from torch.utils.data -> Option B

4. Quick Check:

   DataLoader must be imported before use [OK]

Hint: Always import DataLoader before using it [OK]

Common Mistakes:

• Forgetting to import DataLoader
• Thinking MNIST doesn't support transforms
• Assuming Resize is invalid for MNIST

5. You want to load CIFAR10 images resized to 64x64 pixels, normalized with mean=[0.5,0.5,0.5] and std=[0.5,0.5,0.5], and shuffled in batches of 128. Which code snippet correctly achieves this?

hard

A. transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor()])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=128, shuffle=True)

B. transform = transforms.Compose([transforms.ToTensor(), transforms.Resize(64), transforms.Normalize([0.5]*3, [0.5]*3)])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=128, shuffle=False)

C. transform = transforms.Compose([transforms.Resize(64), transforms.Normalize([0.5]*3, [0.5]*3)])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=64, shuffle=True)

D. transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor(), transforms.Normalize([0.5]*3, [0.5]*3)])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=128, shuffle=True)

Solution

1. Step 1: Check transform order and parameters

   Resize must be first with size (64,64), then ToTensor, then Normalize with correct mean and std.

2. Step 2: Verify DataLoader parameters

   Batch size is 128 and shuffle=True as required.

3. Step 3: Compare options

   transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor(), transforms.Normalize([0.5]*3, [0.5]*3)]) data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) loader = DataLoader(data, batch_size=128, shuffle=True) matches all requirements exactly; others have wrong order, missing steps, or wrong batch/shuffle.

4. Final Answer:

   transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor(), transforms.Normalize([0.5]*3, [0.5]*3)]) data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) loader = DataLoader(data, batch_size=128, shuffle=True) -> Option D

5. Quick Check:

   Resize->ToTensor->Normalize + batch=128 + shuffle=True [OK]

Hint: Resize first, then ToTensor, then Normalize; batch and shuffle as needed [OK]

Common Mistakes:

• Applying Normalize before ToTensor
• Using wrong Resize size or format
• Setting shuffle=False when shuffle=True needed
• Incorrect batch size