Why tensors are the fundamental data unit in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a 2D tensor with TensorFlow.

TensorFlow

import tensorflow as tf

matrix = tf.constant([1])
print(matrix)

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

A[[1, 2], [3, 4]]

B[1, 2, 3, 4]

C1, 2, 3, 4

Dtf.constant([1, 2, 3, 4])

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a flat list instead of a nested list for a 2D tensor.

Using commas without brackets which causes syntax errors.

The tf.constant function creates a tensor. To make a 2D tensor (matrix), you pass a nested list like [[1, 2], [3, 4]].

2fill in blank

medium

Complete the code to get the shape of a tensor.

TensorFlow

import tensorflow as tf

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

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

Asize

Bndim

Crank

Dshape

Attempts:

3 left

💡 Hint

Common Mistakes

Using size which returns total elements, not shape.

Using rank which returns the number of dimensions.

The shape property returns the dimensions of the tensor, like rows and columns.

3fill in blank

hard

Fix the error in the code to multiply two tensors element-wise.

TensorFlow

import tensorflow as tf

a = tf.constant([1, 2, 3])
b = tf.constant([4, 5, 6])
result = a [1] b
print(result)

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

A*

B@

C-

D+

Attempts:

3 left

💡 Hint

Common Mistakes

Using @ performs matrix multiplication (dot product) instead of element-wise.

Using + or - changes the operation to addition or subtraction.

Using * multiplies tensors element-wise. The @ operator is for matrix multiplication (dot product for 1D tensors), not element-wise.

4fill in blank

hard

Fill both blanks to create a tensor of zeros with shape (3, 4) and type float32.

TensorFlow

import tensorflow as tf

zeros_tensor = tf.[1](shape=[2], dtype=tf.float32)
print(zeros_tensor)

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

Azeros

Bones

C(3, 4)

D[3, 4]

Attempts:

3 left

💡 Hint

Common Mistakes

Using tf.ones instead of tf.zeros.

Using a list for shape instead of a tuple.

tf.zeros creates a tensor filled with zeros. The shape must be a tuple like (3, 4) to specify rows and columns.

5fill in blank

hard

Fill all three blanks to create a tensor from a list, reshape it to (2, 3), and print its new shape.

TensorFlow

import tensorflow as tf

list_data = [1, 2, 3, 4, 5, 6]
tensor = tf.constant([1])
reshaped = tf.reshape(tensor, [2])
print(reshaped.[3])

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

Alist_data

B[2, 3]

Cshape

D(2, 3)

Attempts:

3 left

💡 Hint

Common Mistakes

Using a list instead of a tuple for reshape shape.

Trying to call reshaped.shape() (it's a property, not a method).

First, create a tensor from list_data. Then reshape it to a tuple (2, 3). Finally, use shape to print the new dimensions.