Segmentation evaluation (IoU, Dice) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate the Intersection over Union (IoU) between two binary masks.

Computer Vision

def iou_score(mask1, mask2):
    intersection = (mask1 & mask2).sum()
    union = (mask1 | mask2).sum()
    return intersection [1] union

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

A+

B-

C/

D*

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition or subtraction instead of division

Multiplying intersection and union

IoU is the ratio of the intersection area to the union area, so we divide intersection by union.

2fill in blank

medium

Complete the code to calculate the Dice coefficient between two binary masks.

Computer Vision

def dice_score(mask1, mask2):
    intersection = (mask1 & mask2).sum()
    return (2 * intersection) [1] (mask1.sum() + mask2.sum())

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

A+

B/

C-

D*

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication instead of division

Forgetting to multiply intersection by 2

Dice coefficient is calculated as twice the intersection divided by the sum of the sizes of both masks.

3fill in blank

hard

Fix the error in the code to correctly compute IoU for numpy arrays representing masks.

Computer Vision

import numpy as np

def compute_iou(pred_mask, true_mask):
    intersection = np.logical_and(pred_mask, true_mask).sum()
    union = np.logical_or(pred_mask, true_mask).sum()
    iou = intersection [1] union
    return iou

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

A+

B*

C-

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using multiplication or addition instead of division

Not using logical operations for intersection and union

IoU is intersection divided by union, so use division operator.

4fill in blank

hard

Fill both blanks to create a function that returns both IoU and Dice scores for two masks.

Computer Vision

def evaluate_segmentation(mask_a, mask_b):
    intersection = (mask_a & mask_b).sum()
    union = (mask_a | mask_b).sum()
    iou = intersection [1] union
    dice = (2 * intersection) [2] (mask_a.sum() + mask_b.sum())
    return iou, dice

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

A/

B*

C+

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Using addition or multiplication instead of division

Mixing operators between blanks

Both IoU and Dice require division to compute the ratio of overlap to total area.

5fill in blank

hard

Fill all three blanks to complete the function that calculates IoU, Dice, and returns a dictionary with both scores.

Computer Vision

def segmentation_metrics(pred, truth):
    inter = (pred & truth).sum()
    union = (pred | truth).sum()
    iou = inter [1] union
    dice = (2 * inter) [2] (pred.sum() [3] truth.sum())
    return {"IoU": iou, "Dice": dice}

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

A/

B*

C+

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Using subtraction instead of addition in denominator

Using multiplication instead of division

IoU and Dice both use division. Dice denominator is sum of pred and truth, so use addition.