Batch size and epochs in TensorFlow - 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 always slows down training because more data is processed at once.

B Increasing batch size generally speeds up training per epoch but may require more memory.

C Batch size does not affect training speed; it only changes model accuracy.

D Smaller batch sizes always use less memory and train faster than larger batch sizes.

💡 Hint

Think about how processing more samples at once affects computation and memory.

Larger batch sizes process more samples in parallel, which can speed up training per epoch but require more memory. Smaller batches use less memory but may be slower overall.

❓ Predict Output

intermediate

Number of Weight Updates with Different Batch Sizes

Consider a dataset with 1000 samples. You train a model for 5 epochs with batch size 100. How many weight updates occur during training?

TensorFlow

dataset_size = 1000
batch_size = 100
epochs = 5
updates = (dataset_size // batch_size) * epochs
print(updates)

A 50

B 5

C 500

D 100

💡 Hint

Calculate how many batches fit in one epoch, then multiply by epochs.

Each epoch has 1000/100 = 10 batches. Over 5 epochs, total updates = 10 * 5 = 50.

❓ Hyperparameter

advanced

Choosing Batch Size for Memory Constraints

You want to train a deep neural network on a GPU with limited memory. Which batch size choice is best to avoid out-of-memory errors while maintaining reasonable training speed?

A Batch size does not affect memory usage; focus on learning rate instead.

B Use a batch size of 1 to minimize memory usage but expect slower training.

C Use the largest batch size that fits in memory without causing errors.

D Use a very large batch size to reduce the number of updates.

💡 Hint

Think about balancing memory limits and training efficiency.

The largest batch size that fits in memory maximizes GPU usage and speeds training without causing errors. Too small batches slow training; too large cause memory errors.

❓ Metrics

advanced

Effect of Epochs on Model Performance Metrics

You train a model for 10 epochs and observe training accuracy improves but validation accuracy plateaus after 5 epochs. What does this indicate?

A The model is overfitting; training longer may reduce validation accuracy.

B The model is underfitting and needs more epochs.

C The batch size is too large, causing poor validation accuracy.

D The learning rate is too high, causing unstable training.

💡 Hint

Consider what happens when training accuracy improves but validation does not.

When training accuracy improves but validation accuracy stops improving, the model is likely overfitting the training data.

🔧 Debug

expert

Identifying Epochs and Batch Size Impact in TensorFlow Training Loop

Given the code below, what will be the printed output for the number of batches processed per epoch?

TensorFlow

import tensorflow as tf

# Dataset with 120 samples
x = tf.random.normal([120, 10])
y = tf.random.uniform([120], maxval=2, dtype=tf.int32)

batch_size = 25
epochs = 3

dataset = tf.data.Dataset.from_tensor_slices((x, y)).batch(batch_size)

for epoch in range(epochs):
    batch_count = 0
    for batch_x, batch_y in dataset:
        batch_count += 1
    print(f"Epoch {epoch+1} batches: {batch_count}")

A

Epoch 1 batches: 6
Epoch 2 batches: 6
Epoch 3 batches: 6

B

Epoch 1 batches: 4
Epoch 2 batches: 4
Epoch 3 batches: 4

C

Epoch 1 batches: 3
Epoch 2 batches: 3
Epoch 3 batches: 3

D

Epoch 1 batches: 5
Epoch 2 batches: 5
Epoch 3 batches: 5

💡 Hint

Calculate how many batches of size 25 fit into 120 samples.

120 samples divided by batch size 25 gives 4 full batches (25*4=100) plus 1 batch with remaining 20 samples, totaling 5 batches per epoch.