TensorFlow Tensors and Operations 2

Question 1

What TensorFlow dtype represents a 32-bit floating point number?

Accepted Answer

tf.float32

Answer

tf.float32 is the standard 32-bit floating point data type used by default in most TensorFlow operations.

Question 2

How do you get the shape of a tensor as a Python tuple in TensorFlow?

Accepted Answer

tensor.numpy().shape or tensor.shape.as_list()

Answer

tensor.shape.as_list() returns the shape as a Python list, while tensor.numpy().shape gives a NumPy tuple.

Question 3

Which TensorFlow function stacks tensors along a new axis?

Accepted Answer

tf.stack()

Answer

tf.stack() creates a new dimension and stacks tensors along it, increasing rank by 1.

Question 4

What is the result of tf.constant([1,2,3]) + tf.constant([4,5,6])?

Accepted Answer

tf.Tensor([5 7 9])

Answer

TensorFlow performs element-wise addition, so each pair of corresponding elements is summed.

Question 5

Which function in TensorFlow removes dimensions of size 1?

Accepted Answer

tf.squeeze()

Answer

tf.squeeze() removes dimensions with size 1, reducing the rank of the tensor.

TensorFlow Practice Test