DataLoader basics in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of a DataLoader in PyTorch?

A DataLoader helps load data in batches, shuffles it, and can load data in parallel using multiple workers. It makes training models easier and faster by managing data efficiently.

beginner

What does the 'batch_size' parameter control in a DataLoader?

The 'batch_size' sets how many samples are loaded together in one batch. For example, batch_size=4 means 4 samples are loaded at once for training or evaluation.

beginner

What does setting 'shuffle=True' do in a DataLoader?

It randomizes the order of the data at the start of each training epoch. This helps the model learn better by seeing data in different orders.

intermediate

How does 'num_workers' affect DataLoader performance?

It sets how many subprocesses load data in parallel. More workers can speed up data loading but use more CPU. Usually, 2-4 workers are good for faster training.

beginner

What is the output of iterating over a DataLoader?

Each iteration returns a batch of data, usually as a tuple of inputs and labels (e.g., images and their classes). This batch is used for training or testing the model.

What does the DataLoader's 'batch_size' parameter specify?

A Number of samples per batch

B Number of epochs

C Number of features in data

D Number of classes

The 'batch_size' controls how many samples are loaded together in one batch.

What happens if you set 'shuffle=False' in a DataLoader?

A Data is loaded in reverse order

B Data is randomized every batch

C Data is duplicated

D Data is loaded in the original order

With 'shuffle=False', data is loaded in the original order without randomizing.

Why use multiple workers in DataLoader?

A To load data faster using parallel CPU processes

B To increase model accuracy

C To reduce GPU memory usage

D To shuffle data

Multiple workers load data in parallel, speeding up data loading.

What does each iteration over a DataLoader return?

A The entire dataset

B A batch of data samples

C A single data sample

D Model predictions

Each iteration returns a batch of data samples for training or testing.

Which PyTorch class is commonly used to create a DataLoader?

A torch.optim.SGD

B torch.nn.Module

C torch.utils.data.DataLoader

D torch.Tensor

DataLoader is created using torch.utils.data.DataLoader.

Explain how a DataLoader helps in training a machine learning model in PyTorch.

Think about how data is prepared and fed to the model during training.

Describe the effect of changing 'batch_size' and 'num_workers' in a DataLoader.

Consider how these parameters affect speed and resource use.

Practice

1. What is the main purpose of using DataLoader in PyTorch?

easy

A. To split the dataset into batches and optionally shuffle it for training

B. To define the neural network architecture

C. To calculate the loss during training

D. To save the trained model to disk

Solution

1. Step 1: Understand DataLoader's role

   DataLoader helps by splitting data into smaller batches and can shuffle data to improve training.

2. Step 2: Compare options

   Options B, C, and D relate to other parts of training, not data loading.

3. Final Answer:

   To split the dataset into batches and optionally shuffle it for training -> Option A

4. Quick Check:

   DataLoader = batching and shuffling [OK]

Hint: DataLoader = batch + shuffle, not model or loss [OK]

Common Mistakes:

• Confusing DataLoader with model definition
• Thinking DataLoader calculates loss
• Assuming DataLoader saves models

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

easy

A. loader = DataLoader(my_dataset, batch_size=32, shuffle=True)

B. loader = DataLoader(my_dataset, batch=32, shuffle=True)

C. loader = DataLoader(my_dataset, batch_size=32, shuffle=False)

D. loader = DataLoader(my_dataset, size=32, shuffle=True)

Solution

1. Step 1: Recall DataLoader parameters

   The correct parameter for batch size is batch_size, and shuffle is a boolean.

2. Step 2: Check each option

   loader = DataLoader(my_dataset, batch_size=32, shuffle=True) uses correct parameter names and values. Options B and D use wrong parameter names. loader = DataLoader(my_dataset, batch_size=32, shuffle=False) disables shuffling.

3. Final Answer:

   loader = DataLoader(my_dataset, batch_size=32, shuffle=True) -> Option A

4. Quick Check:

   batch_size and shuffle=True correct [OK]

Hint: Use batch_size= and shuffle= for DataLoader [OK]

Common Mistakes:

• Using batch instead of batch_size
• Setting shuffle to False when shuffling is needed
• Using size instead of batch_size

3. Given the following code, what will be the output printed?

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

x = torch.arange(10)
y = torch.arange(10) * 2
dataset = TensorDataset(x, y)
loader = DataLoader(dataset, batch_size=4, shuffle=False)

for batch in loader:
    print(batch)

medium

A. Only one batch with all data

B. (tensor([0, 1, 2, 3]), tensor([0, 2, 4, 6])) then (tensor([4, 5, 6, 7]), tensor([8, 10, 12, 14])) then (tensor([8, 9]), tensor([16, 18])) but shuffled

C. Error because shuffle=False is invalid

D. (tensor([0, 1, 2, 3]), tensor([0, 2, 4, 6])) then (tensor([4, 5, 6, 7]), tensor([8, 10, 12, 14])) then (tensor([8, 9]), tensor([16, 18]))

Solution

1. Step 1: Understand DataLoader batching without shuffle

   DataLoader splits data into batches of size 4, no shuffling means order is preserved.

2. Step 2: Calculate batches

   Dataset has 10 items, batches are: first 4 (0-3), second 4 (4-7), last 2 (8-9). Corresponding y values are double x.

3. Final Answer:

   (tensor([0, 1, 2, 3]), tensor([0, 2, 4, 6])) then (tensor([4, 5, 6, 7]), tensor([8, 10, 12, 14])) then (tensor([8, 9]), tensor([16, 18])) -> Option D

4. Quick Check:

   Batch size 4, no shuffle = ordered batches [OK]

Hint: No shuffle means batches keep original order [OK]

Common Mistakes:

• Assuming shuffle=True by default
• Expecting all data in one batch
• Thinking shuffle=False causes error

4. What is wrong with this DataLoader usage?

from torch.utils.data import DataLoader
loader = DataLoader(batch_size=16, shuffle=True)
for batch in loader:
    print(batch)

medium

A. batch_size should be a string, not integer

B. shuffle cannot be True

C. Missing dataset argument when creating DataLoader

D. for loop syntax is incorrect

Solution

1. Step 1: Check DataLoader parameters

   DataLoader requires a dataset as the first argument; it's missing here.

2. Step 2: Validate other parts

   batch_size as integer and shuffle=True are valid. For loop syntax is correct.

3. Final Answer:

   Missing dataset argument when creating DataLoader -> Option C

4. Quick Check:

   Dataset argument required [OK]

Hint: Always pass dataset first to DataLoader [OK]

Common Mistakes:

• Forgetting to pass dataset to DataLoader
• Thinking batch_size must be string
• Believing shuffle=True is invalid

5. You have a dataset of 103 samples and want to train a model using batches of size 20 with shuffling enabled. How many batches will the DataLoader produce per epoch, and what happens to the last batch?

hard

A. 5 batches; the last batch is dropped because it's smaller

B. 6 batches; the last batch has 3 samples

C. 6 batches; the last batch is padded to 20 samples

D. 5 batches; all batches have exactly 20 samples

Solution

1. Step 1: Calculate number of batches

   103 samples divided by batch size 20 gives 5 full batches (20*5=100) plus 1 partial batch with 3 samples.

2. Step 2: Understand default DataLoader behavior

   By default, DataLoader includes the last smaller batch unless drop_last=True is set, so last batch has 3 samples.

3. Final Answer:

   6 batches; the last batch has 3 samples -> Option B

4. Quick Check:

   103/20 = 5 full + 1 partial batch [OK]

Hint: Last batch included unless drop_last=True [OK]

Common Mistakes:

• Assuming last batch is dropped by default
• Thinking last batch is padded automatically
• Calculating wrong number of batches