TensorFlow Tensors and Operations 2

Question 1

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

Accepted Answer

tf.float32

Answer

tf.float16

Answer

tf.double

Answer

tf.real32

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.get_dims()

Answer

tensor.size()

Answer

tf.shape_tuple(tensor)

Question 3

Which TensorFlow function stacks tensors along a new axis?

Accepted Answer

tf.stack()

Answer

tf.concat()

Answer

tf.merge()

Answer

tf.join()

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

tf.Tensor([1,2,3,4,5,6])

Answer

tf.Tensor([4,10,18])

Answer

Error

Question 5

Which function in TensorFlow removes dimensions of size 1?

Accepted Answer

tf.squeeze()

Answer

tf.flatten()

Answer

tf.reduce()

Answer

tf.trim()

Question 6

What does tf.expand_dims(tensor, axis=0) do?

Accepted Answer

Inserts a new axis at position 0

Answer

Removes axis 0

Answer

Transposes axis 0

Answer

Doubles axis 0