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.

Practice

1. What does the batch_size parameter control in a PyTorch DataLoader?

easy

A. The number of samples processed before the model updates its weights

B. The total number of samples in the dataset

C. The order in which samples are loaded

D. The number of features in each sample

Solution

1. Step 1: Understand batch size meaning

   Batch size defines how many samples the model processes before updating its weights during training.

2. Step 2: Differentiate from other parameters

   It is not the total dataset size, order of samples, or feature count, but the chunk size for training updates.

3. Final Answer:

   The number of samples processed before the model updates its weights -> Option A

4. Quick Check:

   Batch size = samples per update [OK]

Hint: Batch size = samples per training step [OK]

Common Mistakes:

• Confusing batch size with dataset size
• Thinking batch size controls feature count
• Mixing batch size with shuffling

2. Which of the following is the correct way to create a DataLoader with batch size 32 and shuffling enabled?

easy

A. DataLoader(dataset, batch=32, shuffle=True)

B. DataLoader(dataset, shuffle=32, batch_size=True)

C. DataLoader(dataset, batch_size=32, shuffle=True)

D. DataLoader(dataset, batch_size=True, shuffle=32)

Solution

1. Step 1: Recall DataLoader parameters

   PyTorch DataLoader uses batch_size for batch size and shuffle as a boolean for shuffling.

2. Step 2: Check parameter names and types

   DataLoader(dataset, batch_size=32, shuffle=True) correctly uses batch_size=32 and shuffle=True. Others misuse parameter names or types.

3. Final Answer:

   DataLoader(dataset, batch_size=32, shuffle=True) -> Option C

4. Quick Check:

   Correct parameter names and types [OK]

Hint: Use exact parameter names: batch_size and shuffle [OK]

Common Mistakes:

• Swapping parameter names
• Using wrong data types for parameters
• Omitting required parameters

3. Given the code below, what will be the output length of each batch printed?

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

data = torch.arange(10)
dataset = TensorDataset(data)
dataloader = DataLoader(dataset, batch_size=4, shuffle=False)

for batch in dataloader:
    print(len(batch[0]))

medium

A. 10

B. 4, 4, 2

C. 5, 5

D. 4, 3, 3

Solution

1. Step 1: Understand dataset and batch size

   Dataset has 10 samples. Batch size is 4, so batches will be split into groups of 4 samples each.

2. Step 2: Calculate batch lengths

   First two batches have 4 samples each (4 + 4 = 8), last batch has remaining 2 samples (10 - 8 = 2).

3. Final Answer:

   4, 4, 2 -> Option B

4. Quick Check:

   10 samples split by 4 = 4,4,2 [OK]

Hint: Last batch may be smaller if dataset size not divisible by batch size [OK]

Common Mistakes:

• Assuming all batches have equal size
• Ignoring leftover samples in last batch
• Confusing batch length with dataset length

4. What is wrong with this DataLoader code snippet?

from torch.utils.data import DataLoader

dataloader = DataLoader(dataset, batch_size=0, shuffle=True)

medium

A. Batch size cannot be zero; it must be a positive integer

B. Shuffle cannot be true when batch size is set

C. Dataset must be a list, not a variable named dataset

D. DataLoader requires batch_size to be a float

Solution

1. Step 1: Check batch_size validity

   Batch size must be a positive integer greater than zero to form batches.

2. Step 2: Validate other parameters

   Shuffle can be True regardless of batch size. Dataset variable name is valid. Batch size must be int, not float.

3. Final Answer:

   Batch size cannot be zero; it must be a positive integer -> Option A

4. Quick Check:

   Batch size > 0 required [OK]

Hint: Batch size must be positive integer, never zero [OK]

Common Mistakes:

• Setting batch size to zero
• Confusing shuffle restrictions
• Wrong data type for batch size

5. You have a dataset of 103 samples. You want to train a model with batch size 20 and shuffle enabled. How many batches will the DataLoader produce each epoch, and why is shuffling important here?

hard

A. 103 batches; shuffling splits data into single samples

B. 5 batches; shuffling is not needed when batch size is large

C. 20 batches; shuffling controls batch size

D. 6 batches; shuffling helps the model see data in different orders to avoid bias

Solution

1. Step 1: Calculate number of batches

   103 samples with batch size 20 means 5 full batches (20*5=100) plus 1 batch with 3 samples, total 6 batches.

2. Step 2: Understand shuffling importance

   Shuffling mixes data order each epoch to prevent the model from learning patterns based on data order, reducing bias.

3. Final Answer:

   6 batches; shuffling helps the model see data in different orders to avoid bias -> Option D

4. Quick Check:

   103/20 = 6 batches; shuffle avoids bias [OK]

Hint: Batches = ceil(dataset size / batch size); shuffle avoids order bias [OK]

Common Mistakes:

• Ignoring last smaller batch
• Thinking shuffle disables batch size
• Misunderstanding shuffle purpose