Batching and shuffling in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output shape after batching?

Given a TensorFlow dataset of 100 samples, each sample is a vector of length 10. If we batch the dataset with batch size 20, what will be the shape of one batch?

TensorFlow

import tensorflow as tf

# Create dataset of 100 samples, each sample shape (10,)
dataset = tf.data.Dataset.from_tensor_slices(tf.random.uniform([100, 10]))

# Batch with size 20
batched_dataset = dataset.batch(20)

for batch in batched_dataset.take(1):
    print(batch.shape)

A (5, 10)

B (10, 20)

C (100, 10)

D (20, 10)

💡 Hint

Batching groups samples along the first dimension.

Batching groups 20 samples together. Each sample has shape (10,), so the batch shape is (20, 10).

🧠 Conceptual

intermediate

Why shuffle a dataset before training?

What is the main reason to shuffle a dataset before training a machine learning model?

A To ensure the model sees data in a random order, preventing learning bias from data order

B To reduce the dataset size by removing duplicates

C To increase the batch size automatically

D To normalize the input features

💡 Hint

Think about how data order might affect learning.

Shuffling prevents the model from learning patterns based on the order of data, which could cause bias and reduce generalization.

❓ Hyperparameter

advanced

Choosing shuffle buffer size

In TensorFlow, the shuffle() method requires a buffer size parameter. What is the effect of increasing the shuffle buffer size?

A It decreases randomness but speeds up training

B It increases randomness of shuffling but uses more memory

C It changes the batch size automatically

D It normalizes the dataset features

💡 Hint

Think about how buffer size affects the number of samples held before shuffling.

A larger buffer size means more samples are held in memory and shuffled, increasing randomness but using more RAM.

🔧 Debug

advanced

Why does this TensorFlow dataset not shuffle properly?

Consider this code snippet: import tensorflow as tf raw_data = tf.data.Dataset.range(10) shuffled_data = raw_data.shuffle(buffer_size=5) for item in shuffled_data: print(item.numpy()) Why might the output order not be fully randomized?

A Because the shuffle buffer size is smaller than the dataset size, limiting randomness

B Because shuffle() requires batch() to work properly

C Because the dataset is not batched before shuffling

D Because shuffle() only works on datasets with more than 100 samples

💡 Hint

Think about how shuffle buffer size relates to dataset size.

If buffer size is smaller than dataset size, only that many samples are shuffled at a time, so full randomization is not guaranteed.

❓ Model Choice

expert

Best practice for shuffling and batching in TensorFlow pipeline

You want to prepare a TensorFlow dataset for training a neural network. Which pipeline order is best for performance and correctness?

A Shuffle and batch simultaneously using batch(shuffle=True)

B Batch the dataset first, then shuffle the batches

C Shuffle the dataset first, then batch it

D Neither shuffle nor batch the dataset

💡 Hint

Consider how shuffling affects individual samples versus batches.

Shuffling before batching ensures samples are randomized before grouping, improving training quality.