Batching and shuffling in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a TensorFlow dataset from a list of numbers.

TensorFlow

import tensorflow as tf
numbers = [1, 2, 3, 4, 5]
dataset = tf.data.Dataset.[1](numbers)

Drag options to blanks, or click blank then click option'

Afrom_tensor_slices

Bbatch

Cshuffle

Dmap

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'batch' instead of 'from_tensor_slices' will cause an error because batch expects a dataset.

Using 'shuffle' directly on a list is invalid.

The from_tensor_slices method creates a dataset from a list or array by slicing it into elements.

2fill in blank

medium

Complete the code to shuffle the dataset with a buffer size of 10.

TensorFlow

dataset = dataset.[1](buffer_size=10)

Drag options to blanks, or click blank then click option'

Amap

Bbatch

Crepeat

Dshuffle

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'batch' instead of 'shuffle' will group elements but not shuffle them.

Using 'repeat' will repeat the dataset but not shuffle.

The shuffle method randomly shuffles the elements of the dataset using the specified buffer size.

3fill in blank

hard

Fix the error in the code to batch the dataset with batch size 4.

TensorFlow

dataset = dataset.[1](4)

Drag options to blanks, or click blank then click option'

Abatch

Bshuffle

Cmap

Drepeat

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'shuffle' instead of 'batch' will shuffle elements but not group them.

Using 'map' applies a function but does not batch.

The batch method groups elements into batches of the given size.

4fill in blank

hard

Fill both blanks to create a dataset from a list, shuffle it with buffer size 5.

TensorFlow

dataset = tf.data.Dataset.[1](data).[2](buffer_size=5)

Drag options to blanks, or click blank then click option'

Afrom_tensor_slices

Bbatch

Cshuffle

Drepeat

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'batch' before 'shuffle' will cause errors if the dataset is not created first.

Using 'repeat' instead of 'shuffle' will not randomize the data.

First, create the dataset from the list using from_tensor_slices, then shuffle it with shuffle.

5fill in blank

hard

Fill all three blanks to create a dataset from a list, shuffle with buffer size 8, and batch with size 3.

TensorFlow

dataset = tf.data.Dataset.[1](items).[2](buffer_size=8).[3](3)

Drag options to blanks, or click blank then click option'

Afrom_tensor_slices

Bshuffle

Cbatch

Drepeat

Attempts:

3 left

💡 Hint

Common Mistakes

Changing the order of methods can cause unexpected behavior.

Using 'repeat' instead of 'shuffle' will not randomize the data.

Create the dataset with from_tensor_slices, shuffle it with shuffle, then group into batches with batch.