Batching and shuffling in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is batching in machine learning?

Batching means splitting the dataset into small groups called batches. Models learn from one batch at a time instead of the whole dataset, which saves memory and speeds up training.

beginner

Why do we shuffle data before training?

Shuffling mixes the data randomly. This helps the model learn better by preventing it from seeing data in the same order every time, which can cause bias.

intermediate

How does batching affect training speed and memory?

Using batches allows the model to update weights more often and use less memory than training on the full dataset at once. Smaller batches use less memory but may be slower overall.

beginner

What TensorFlow function helps to create batches and shuffle data?

The TensorFlow Dataset API uses dataset.shuffle(buffer_size) to shuffle and dataset.batch(batch_size) to create batches.

intermediate

What is the effect of a larger shuffle buffer size in TensorFlow?

A larger shuffle buffer size means better random mixing of data but uses more memory. A small buffer may not shuffle well, causing less randomness.

What does batching do during model training?

A Randomly changes the order of data

B Splits data into smaller groups for training

C Increases the size of the dataset

D Removes data points from the dataset

Batching splits the dataset into smaller groups called batches for efficient training.

Why is shuffling data important before training?

A To prevent the model from learning order bias

B To reduce the dataset size

C To speed up training by sorting data

D To increase batch size automatically

Shuffling prevents the model from learning patterns based on data order, improving generalization.

Which TensorFlow method is used to create batches?

A dataset.shuffle()

B dataset.repeat()

C dataset.batch()

D dataset.map()

dataset.batch() groups data into batches for training.

What happens if the shuffle buffer size is too small?

A Batch size increases automatically

B Data is shuffled perfectly

C Training speed increases drastically

D Data may not be shuffled well, causing bias

A small shuffle buffer leads to poor mixing of data, reducing randomness.

How does batching affect memory usage?

A Decreases memory usage by loading small batches

B Increases memory usage by loading all data

C Has no effect on memory

D Deletes data after each batch

Batching loads small parts of data at a time, reducing memory needs.

Explain in your own words why batching and shuffling are important in training machine learning models.

Think about how a chef prepares ingredients in small bowls and mixes them well before cooking.

Describe how you would use TensorFlow Dataset API to prepare data with batching and shuffling.

Remember the order matters: shuffle first, then batch.

Practice

1. What is the main purpose of batching data in TensorFlow during training?

easy

A. To group data into smaller sets for faster and efficient training

B. To randomly mix data to avoid bias

C. To increase the size of the dataset

D. To convert data into images

Solution

1. Step 1: Understand batching concept

   Batching means grouping data into smaller sets instead of using all data at once.

2. Step 2: Identify batching benefit

   This grouping helps speed up training and uses memory efficiently.

3. Final Answer:

   To group data into smaller sets for faster and efficient training -> Option A

4. Quick Check:

   Batching = grouping data for efficiency [OK]

Hint: Batching groups data; shuffling mixes data [OK]

Common Mistakes:

• Confusing batching with shuffling
• Thinking batching increases dataset size
• Believing batching changes data type

2. Which of the following is the correct way to shuffle and batch a TensorFlow dataset named ds with batch size 32?

easy

A. ds.batch(100).shuffle(32)

B. ds.batch(32).shuffle(100)

C. ds.shuffle(32).batch(100)

D. ds.shuffle(100).batch(32)

Solution

1. Step 1: Recall correct order of operations

   In TensorFlow, you first shuffle the dataset, then batch it.

2. Step 2: Match batch size and shuffle buffer

   Shuffle buffer size is usually larger than batch size; here shuffle(100) and batch(32) is correct.

3. Final Answer:

   ds.shuffle(100).batch(32) -> Option D

4. Quick Check:

   Shuffle before batch = ds.shuffle().batch() [OK]

Hint: Shuffle first, then batch with correct sizes [OK]

Common Mistakes:

• Batching before shuffling
• Using smaller shuffle buffer than batch size
• Mixing batch and shuffle parameters

3. What will be the output shape of batches if you run the following code on a dataset of 100 samples with shape (28, 28, 1)?

batched_ds = ds.batch(20)
for batch in batched_ds:
    print(batch.shape)

medium

A. (20, 28, 28) for all batches

B. (20, 28, 28, 1) for all batches

C. (100, 28, 28, 1) for all batches

D. (28, 28, 1) for all batches

Solution

1. Step 1: Understand batch size effect on shape

   Batching groups samples; each batch has shape (batch_size, sample_shape).

2. Step 2: Calculate batch shapes for 100 samples with batch size 20

   There will be 5 batches; first 4 batches have 20 samples, last batch also 20 (100 divisible by 20).

3. Final Answer:

   (20, 28, 28, 1) for all batches -> Option B

4. Quick Check:

   Batch shape = (batch_size, sample_shape) [OK]

Hint: Batch shape adds batch size as first dimension [OK]

Common Mistakes:

• Ignoring batch dimension in shape
• Assuming last batch is smaller when divisible
• Confusing sample shape with batch shape

4. You wrote this code but the dataset is not shuffled properly:

ds = tf.data.Dataset.range(10)
ds = ds.batch(2).shuffle(5)

What is the main issue?

medium

A. Shuffle should be called before batch to mix individual elements

B. Shuffle buffer size is too large

C. Batch size must be 1 for shuffle to work

D. Dataset.range(10) cannot be shuffled

Solution

1. Step 1: Analyze order of shuffle and batch

   Shuffling after batching shuffles batches, not individual elements.

2. Step 2: Correct order for proper shuffling

   Shuffle should be called before batch to mix individual data points.

3. Final Answer:

   Shuffle should be called before batch to mix individual elements -> Option A

4. Quick Check:

   Shuffle before batch for proper mixing [OK]

Hint: Shuffle before batch to mix single items [OK]

Common Mistakes:

• Calling shuffle after batch
• Using too small shuffle buffer
• Thinking batch size must be 1

5. You have a dataset with 103 samples. You want to shuffle it with a buffer size of 50 and batch it with size 20. How many batches will you get and what will be the size of the last batch if you use:

ds.shuffle(50).batch(20)

hard

A. 6 batches; last batch size 20

B. 5 batches; last batch size 20

C. 6 batches; last batch size 3

D. 5 batches; last batch size 3

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 shuffle effect on batch count

   Shuffling does not change total samples, so batch count remains 6 with last batch smaller.

3. Final Answer:

   6 batches; last batch size 3 -> Option C

4. Quick Check:

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

Hint: Divide samples by batch size; last batch may be smaller [OK]

Common Mistakes:

• Ignoring last partial batch
• Assuming shuffle changes batch count
• Miscounting batches as 5 instead of 6