Tensor creation (constant, variable, zeros, ones) in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output shape of this tensor?

Given the following TensorFlow code, what is the shape of the tensor t?

TensorFlow

import tensorflow as tf
t = tf.constant([[1, 2, 3], [4, 5, 6]])
shape = t.shape

A (6,)

B (3, 2)

C (2, 3)

D (1, 6)

💡 Hint

Think about how many rows and columns the list has.

The tensor is created from a list of two lists, each with three elements, so the shape is (2, 3).

❓ Model Choice

intermediate

Which tensor creation method creates a mutable tensor?

In TensorFlow, which method creates a tensor whose values can be changed after creation?

A tf.Variable()

B tf.zeros()

C tf.constant()

D tf.ones()

💡 Hint

Mutable means you can change the values after creation.

tf.Variable creates a tensor that can be updated, unlike tf.constant, tf.zeros, or tf.ones which create immutable tensors.

❓ Predict Output

advanced

What is the output of this code?

What does the following TensorFlow code print?

TensorFlow

import tensorflow as tf
x = tf.zeros(shape=(2, 3), dtype=tf.int32)
print(x.numpy())

A

[[1 1 1]
 [1 1 1]]

B

[[0. 0. 0.]
 [0. 0. 0.]]

C

[[1. 1. 1.]
 [1. 1. 1.]]

D

[[0 0 0]
 [0 0 0]]

💡 Hint

Check the dtype and the function used to create the tensor.

tf.zeros creates a tensor filled with zeros. dtype=tf.int32 means integers, so zeros are printed without decimals.

❓ Hyperparameter

advanced

Which argument changes the data type of a tensor?

When creating a tensor with tf.ones(), which argument sets the data type of the tensor elements?

A dtype

B size

C value

D shape

💡 Hint

This argument controls if the tensor holds integers, floats, or other types.

The dtype argument specifies the data type of the tensor elements.

🔧 Debug

expert

Why does this code raise an error?

Examine the code below. Why does it raise an error?

TensorFlow

import tensorflow as tf
v = tf.Variable(tf.constant([1, 2, 3]))
v.assign([4, 5])

A tf.Variable cannot be created from tf.constant.

B The assign method requires the new value to have the same shape as the variable.

C The list passed to assign must be a tensor, not a Python list.

D The variable v is immutable and cannot be assigned new values.

💡 Hint

Check the shapes of the original variable and the new value.

The assign method requires the new value to have the same shape as the variable. Here, the original variable has shape (3,), but the new value has shape (2,), causing a shape mismatch error.