Numpy interoperability in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to convert a TensorFlow tensor to a NumPy array.

TensorFlow

import tensorflow as tf

tensor = tf.constant([1, 2, 3])
array = tensor.[1]()

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

Aarray

Btolist

Cnumpy

Dconvert

Attempts:

3 left

💡 Hint

Common Mistakes

Using tolist() returns a Python list, not a NumPy array.

Using array() or convert() are not valid TensorFlow tensor methods.

Use the numpy() method to convert a TensorFlow tensor to a NumPy array.

2fill in blank

medium

Complete the code to create a TensorFlow tensor from a NumPy array.

TensorFlow

import tensorflow as tf
import numpy as np

np_array = np.array([4, 5, 6])
tensor = tf.[1](np_array)

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

Acreate_tensor

Bfrom_numpy

Ctensor_from_array

Dconvert_to_tensor

Attempts:

3 left

💡 Hint

Common Mistakes

Using from_numpy or tensor_from_array are not TensorFlow functions.

create_tensor is not a valid TensorFlow function.

The tf.convert_to_tensor() function converts a NumPy array to a TensorFlow tensor.

3fill in blank

hard

Fix the error in the code to correctly convert a TensorFlow tensor to a NumPy array.

TensorFlow

import tensorflow as tf

tensor = tf.constant([7, 8, 9])
array = tensor.[1]

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

Anumpy()

Bnumpy

Cto_numpy()

Dtoarray()

Attempts:

3 left

💡 Hint

Common Mistakes

Using numpy without parentheses returns the method itself, not the array.

to_numpy() and toarray() are not TensorFlow tensor methods.

The numpy() method must be called with parentheses to convert the tensor to a NumPy array.

4fill in blank

hard

Fill both blanks to create a TensorFlow tensor from a NumPy array and then convert it back to a NumPy array.

TensorFlow

import tensorflow as tf
import numpy as np

np_array = np.array([10, 11, 12])
tensor = tf.[1](np_array)
back_to_np = tensor.[2]()

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

Aconvert_to_tensor

Bnumpy

Dfrom_numpy

Attempts:

3 left

💡 Hint

Common Mistakes

Using from_numpy instead of convert_to_tensor.

Using numpy without parentheses for conversion.

Use tf.convert_to_tensor() to create a tensor from a NumPy array, then numpy() to convert it back.

5fill in blank

hard

Fill all three blanks to create a NumPy array, convert it to a TensorFlow tensor, and then get its shape.

TensorFlow

import tensorflow as tf
import numpy as np

np_array = np.array([[1], [2], [3]])
tensor = tf.convert_to_tensor(np_array)
shape = tensor.shape

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

A1

B2

C3

D4

Attempts:

3 left

💡 Hint

Common Mistakes

Using non-integer or missing values in the array.

Not matching the number of blanks with the number of elements.

The NumPy array is created with elements 1, 2, and 3, then converted to a tensor. The shape will be (3,).