You've learned how to access data within tensors using indexing and slicing, and how to change a tensor's shape with reshape, squeeze, and unsqueeze. Let's combine these skills to manipulate tensors like a pro.

Engagement Message

Ready to test your tensor navigation and shaping abilities?

Type

Fill In The Blanks

Markdown With Blanks

Fill in the blanks to reshape the 1D tensor data into a 2x3 tensor. The code will then select the element 5.

Suggested Answers

• 2
• 3
• 1
• 6

Type

Multiple Choice

Practice Question

A tensor has a shape of (1, 5, 1, 3). What will its shape be after applying .squeeze()?

A. (1, 5, 1, 3) B. (5, 3) C. (1, 5, 3) D. (5, 1, 3)

Suggested Answers

• A
• B - Correct
• C
• D

Type

Sort Into Boxes

Practice Question

Sort these operations based on their primary function.

Labels

• First Box Label: Changes Shape
• Second Box Label: Selects Data

First Box Items

• reshape
• squeeze
• unsqueeze
• transpose

Second Box Items

• indexing
• slicing

Type

Swipe Left or Right

Practice Question

A tensor has 18 elements. Is the target shape a valid reshape operation? Swipe left for valid and right for invalid.

Labels

• Left Label: Valid Reshape
• Right Label: Invalid Reshape

Left Label Items

• (2, 9)
• (3, 6)
• (18, 1)
• (2, 3, 3)

Right Label Items

• (3, 7)
• (2, 8)

Type

Multiple Choice

Practice Question

You have a single image tensor with shape (28, 28). To process it in a batch, a model expects an input shape of (1, 28, 28). Which operation should you use?

A. tensor.squeeze(0) B. tensor.reshape(1, 28, 28) C. tensor.unsqueeze(0) D. Both B and C are correct

Suggested Answers

• A
• B
• C
• D - Correct

Type

Fill In The Blanks

Markdown With Blanks

Complete the code to select the first element of the tensor and then expand it into a shape of (1, 1).

Suggested Answers

• 0
• unsqueeze
• squeeze