Bounding box handling in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the width of a bounding box.

PyTorch

width = bbox[[1]] - bbox[0]

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

A2

B4

C1

D3

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong index for x_max.

Subtracting y-coordinates instead of x-coordinates.

The width of a bounding box is calculated by subtracting the x-coordinate of the left edge (bbox[0]) from the x-coordinate of the right edge (bbox[2]).

2fill in blank

medium

Complete the code to compute the area of a bounding box.

PyTorch

area = (bbox[2] - bbox[0]) * (bbox[[1]] - bbox[1])

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

A3

B2

C1

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong index for y_max.

Forgetting to subtract y_min from y_max.

The area is width times height. Width is bbox[2] - bbox[0], height is bbox[3] - bbox[1]. So the height uses index 3 for y_max.

3fill in blank

hard

Fix the error in the code to correctly compute the center of a bounding box.

PyTorch

center_x = (bbox[0] + bbox[[1]]) / 2

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

A3

B2

C1

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using y-coordinates instead of x-coordinates.

Using the wrong index for x_max.

The center x-coordinate is the average of x_min (bbox[0]) and x_max (bbox[2]). So the correct index is 2.

4fill in blank

hard

Fill both blanks to create a dictionary of bounding box widths and heights for a list of boxes.

PyTorch

sizes = {i: (bbox[[1]] - bbox[0], bbox[[2]] - bbox[1]) for i, bbox in enumerate(boxes)}

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

A2

B3

C1

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up x and y indices.

Using y_min or x_min incorrectly.

Width is x_max - x_min (bbox[2] - bbox[0]) and height is y_max - y_min (bbox[3] - bbox[1]).

5fill in blank

hard

Fill all three blanks to filter bounding boxes with area greater than 1000 and create a dictionary of their centers.

PyTorch

centers = {i: ((bbox[[1]] + bbox[0]) / 2, (bbox[[2]] + bbox[[3]]) / 2) for i, bbox in enumerate(boxes) if (bbox[2] - bbox[0]) * (bbox[3] - bbox[1]) > 1000}

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

A2

B1

C3

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up indices for y_min and y_max.

Using width or height instead of center coordinates.

The center x is average of x_min (bbox[0]) and x_max (bbox[2]). The center y is average of y_min (bbox[1]) and y_max (bbox[3]). So the indices are 2, 1, and 3 respectively.