Batch size and shuffling in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Effect of batch size on training speed

Which statement best describes how increasing the batch size affects the training speed of a neural network?

A Increasing batch size usually speeds up training per epoch because more samples are processed in parallel.

B Increasing batch size always slows down training because the model updates less frequently.

C Increasing batch size has no effect on training speed since the total data is the same.

D Increasing batch size causes the model to train slower because it requires more epochs.

💡 Hint

Think about how processing multiple samples at once affects computation.

Using a larger batch size allows the model to process more samples simultaneously, which often speeds up training per epoch due to parallel computation on hardware like GPUs.

❓ Predict Output

intermediate

Output shape with different batch sizes

What is the shape of the output tensor after passing a batch of images through a model?

Assume the model outputs a tensor of shape (batch_size, 10) for 10 classes.

PyTorch

import torch
batch_size = 16
model_output = torch.randn(batch_size, 10)
print(model_output.shape)

A torch.Size([16, 10])

B torch.Size([10, 16])

C torch.Size([1, 10])

D torch.Size([16])

💡 Hint

The first dimension is the batch size, the second is the number of classes.

The output shape is (batch_size, number_of_classes). Here batch_size is 16 and classes are 10, so shape is (16, 10).

❓ Model Choice

advanced

Choosing batch size for memory constraints

You have a GPU with limited memory. Which batch size choice is best to avoid out-of-memory errors while training a large model?

A Use a very large batch size to reduce training time.

B Use a batch size of 1 to minimize memory usage.

C Use a moderate batch size that fits comfortably in memory.

D Use batch size equal to the dataset size.

💡 Hint

Think about balancing memory use and training efficiency.

Choosing a batch size that fits in memory avoids errors and keeps training efficient. Too small slows training, too large causes errors.

❓ Metrics

advanced

Effect of shuffling on training metrics

How does enabling shuffling in the data loader affect training metrics like loss and accuracy?

A Shuffling causes training loss to increase because data order is random.

B Shuffling improves training by reducing overfitting and improving generalization.

C Shuffling has no effect on training metrics.

D Shuffling always decreases accuracy because batches are inconsistent.

💡 Hint

Consider how randomizing data order affects learning.

Shuffling data helps the model see varied examples each batch, reducing bias and improving generalization, which often improves training metrics.

🔧 Debug

expert

Identifying error from incorrect shuffling usage

What error will this PyTorch DataLoader code raise?

from torch.utils.data import DataLoader, TensorDataset
import torch

data = torch.randn(100, 3)
targets = torch.randint(0, 2, (100,))
dataset = TensorDataset(data, targets)
loader = DataLoader(dataset, batch_size=10, shuffle=False)

for batch_data, batch_targets in loader:
    print(batch_data.shape, batch_targets.shape)

loader = DataLoader(dataset, batch_size=10, shuffle='yes')  # Incorrect shuffle argument

A ValueError: batch_size must be an integer

B No error, code runs fine

C RuntimeError: DataLoader shuffle argument missing

D TypeError: shuffle must be a boolean, not str

💡 Hint

Check the type expected for the shuffle argument.

The shuffle argument must be True or False. Passing a string like 'yes' causes a TypeError.