Indexing and slicing tensors in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to select the first row of the tensor.

TensorFlow

import tensorflow as tf

tensor = tf.constant([[1, 2], [3, 4], [5, 6]])
first_row = tensor[1]

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

A[0]

B[:, 0]

C[0, :]

D[1]

Attempts:

3 left

💡 Hint

Common Mistakes

Using [0] alone returns a 1D tensor but may not be explicit about columns.

Using [:, 0] selects the first column, not the first row.

The correct way to select the first row of a 2D tensor is using [0, :], which means row 0 and all columns.

2fill in blank

medium

Complete the code to slice the tensor to get the last two rows.

TensorFlow

import tensorflow as tf

tensor = tf.constant([[10, 20], [30, 40], [50, 60], [70, 80]])
last_two_rows = tensor[1]

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

A[1:3]

B[:2]

C[-3:-1]

D[-2:]

Attempts:

3 left

💡 Hint

Common Mistakes

Using [:2] gets the first two rows, not the last two.

Using [1:3] gets the middle rows, not the last two.

Using [-2:] slices the tensor to get the last two rows.

3fill in blank

hard

Fix the error in the code to select the second column of the tensor.

TensorFlow

import tensorflow as tf

tensor = tf.constant([[5, 10, 15], [20, 25, 30], [35, 40, 45]])
second_column = tensor[1]

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

A[:, 1]

B[1, :]

C[1]

D[:, 2]

Attempts:

3 left

💡 Hint

Common Mistakes

Using [1, :] selects the second row, not the column.

Using [:, 2] selects the third column, not the second.

To select the second column, use [:, 1] which means all rows and column index 1.

4fill in blank

hard

Fill both blanks to create a tensor slice with the first two rows and last two columns.

TensorFlow

import tensorflow as tf

tensor = tf.constant([[1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12]])
slice_tensor = tensor[1][2]

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

A[0:2,

B[1:3,

C2:]

D1:]

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong row indices like [1:3, 2:] gets the wrong rows.

Using column slice 1:] gets the wrong columns.

To get the first two rows and last two columns, slice rows with [0:2, and columns with 2:].

5fill in blank

hard

Fill both blanks to create a slice selecting the middle row and middle two columns.

TensorFlow

import tensorflow as tf

tensor = tf.constant([[10, 20, 30, 40], [50, 60, 70, 80], [90, 100, 110, 120])
slice_tensor = tensor[1][2]]

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

A[1,

B[1:2,

C1:3

D]

Attempts:

3 left

💡 Hint

Common Mistakes

Using [1, 1:3] returns a 1D tensor, losing the row dimension.

Using wrong column indices like 2:4 selects wrong columns.

To select the middle row and middle two columns, slice rows with [1:2, and columns with 1:3. The last blank is the closing bracket ].