Dataset bias in vision in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load images from a folder using torchvision.

Computer Vision

from torchvision import datasets, transforms

transform = transforms.Compose([transforms.Resize((128, 128)), transforms.ToTensor()])
dataset = datasets.ImageFolder(root='data/train', transform=[1])

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

Atransform

Btransforms

Cdatasets

DImageFolder

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the module name 'transforms' instead of the transform pipeline.

Passing the dataset class 'datasets' instead of the transform.

Passing the class 'ImageFolder' instead of the transform.

The transform argument expects a transform pipeline, so 'transform' is the correct choice.

2fill in blank

medium

Complete the code to split the dataset into training and validation sets.

Computer Vision

from torch.utils.data import random_split

train_size = int(0.8 * len(dataset))
val_size = len(dataset) - train_size
train_dataset, val_dataset = random_split(dataset, [[1], val_size])

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

Aval_size

Btrain_size

Clen(dataset)

D0.8

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping train_size and val_size in the split sizes.

Using the dataset length directly instead of the split sizes.

The first argument in the list should be the training size, which is 'train_size'.

3fill in blank

hard

Fix the error in the code that creates a DataLoader for the validation set.

Computer Vision

from torch.utils.data import DataLoader

val_loader = DataLoader(val_dataset, batch_size=32, shuffle=[1])

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

ATrue

BNone

CFalse

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting shuffle to True for validation data.

Passing None or 0 which are invalid for shuffle parameter.

For validation data, shuffling should be False to keep order consistent.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that filters images with labels less than 5 and maps them to their file paths.

Computer Vision

filtered_images = {img_path: label for img_path, label in dataset.imgs if label [1] 5 and img_path.endswith([2])}

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

A<

B>

C'.jpg'

D'.png'

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>' instead of '<' for label filtering.

Using '.png' when images are '.jpg'.

We want labels less than 5 and images ending with '.jpg'.

5fill in blank

hard

Fill all three blanks to define a function that checks if a dataset is biased by comparing class counts and returns True if any class count is less than 10.

Computer Vision

def is_biased(dataset):
    counts = {}
    for _, label in dataset:
        counts[label] = counts.get([1], 0) + 1
    return any(count < [2] for count in counts.values()) or len(counts) < [3]

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

Alabel

B10

C5

Dlen(dataset)

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong key in counts.get().

Using wrong threshold values for counts or class number.

We count labels by key 'label', check if any count is less than 10, and check if number of classes is less than 5.

Practice

1. What does dataset bias in computer vision mean?

easy

A. The data does not fairly represent all types of images or cases

B. The model always predicts perfectly on all images

C. The dataset is too large to process

D. The images are all black and white

Solution

1. Step 1: Understand dataset bias meaning

   Dataset bias means the data used to train a model does not cover all possible cases fairly.

2. Step 2: Compare options to definition

   Only The data does not fairly represent all types of images or cases describes this correctly. Other options describe unrelated issues.

3. Final Answer:

   The data does not fairly represent all types of images or cases -> Option A

4. Quick Check:

   Dataset bias = unfair data representation [OK]

Hint: Bias means data is not fair or balanced [OK]

Common Mistakes:

• Thinking bias means model is perfect
• Confusing bias with dataset size
• Assuming bias means image color

2. Which of the following is the correct way to check for dataset bias in a vision dataset using Python?

easy

A. Use random.shuffle(dataset) to fix bias

B. Use value_counts() on labels to see class distribution

C. Use len(dataset) without checking labels

D. Use print(dataset) only

Solution

1. Step 1: Identify method to check bias

   Checking class distribution with value_counts() helps find imbalance in labels.

2. Step 2: Evaluate other options

   Printing dataset or length alone doesn't show bias. Shuffling data doesn't check bias.

3. Final Answer:

   Use value_counts() on labels to see class distribution -> Option B

4. Quick Check:

   Check label counts = value_counts() [OK]

Hint: Check label counts to find bias [OK]

Common Mistakes:

• Only printing dataset without analysis
• Assuming dataset length shows bias
• Thinking shuffling fixes bias

3. Given this Python code snippet analyzing a vision dataset labels:

import pandas as pd
labels = ['cat', 'dog', 'cat', 'cat', 'dog', 'bird']
label_counts = pd.Series(labels).value_counts()
print(label_counts)

What is the output?

medium

A. bird 3
cat 2
dog 1

B. cat 2
dog 3
bird 1

C. cat 3
dog 2
bird 1

D. dog 3
cat 3
bird 3

Solution

1. Step 1: Count occurrences of each label

   Labels list has 'cat' 3 times, 'dog' 2 times, and 'bird' 1 time.

2. Step 2: Understand value_counts output

   value_counts() returns counts sorted descending by default.

3. Final Answer:

   cat 3\ndog 2\nbird 1 -> Option C

4. Quick Check:

   Count labels correctly = cat:3, dog:2, bird:1 [OK]

Hint: Count each label frequency carefully [OK]

Common Mistakes:

• Mixing counts of dog and cat
• Assuming alphabetical order instead of count order
• Miscounting occurrences

4. You have this code to check dataset bias:

labels = ['car', 'car', 'truck', 'car', 'truck']
counts = {}
for label in labels:
    counts[label] = counts.get(label, 0) + 1
print(counts)

But the output is {}. What is the likely error?

medium

A. The 'get' method is used incorrectly with wrong parameters

B. The print statement is outside the loop and missing indentation

C. The code is correct; output should be {'car': 3, 'truck': 2}

D. The dictionary 'counts' was reinitialized inside the loop

Solution

1. Step 1: Analyze code behavior

   If 'counts' is reset inside the loop, it will be empty after loop ends.

2. Step 2: Identify cause of empty output

   Reinitializing 'counts' inside loop clears previous counts, causing empty dict at print.

3. Final Answer:

   The dictionary 'counts' was reinitialized inside the loop -> Option D

4. Quick Check:

   Resetting dict inside loop empties counts [OK]

Hint: Check if dict is reset inside loop [OK]

Common Mistakes:

• Thinking print indentation causes empty output
• Assuming get() method is wrong
• Ignoring variable scope inside loop

5. You have a vision dataset with 90% images of cats and 10% dogs. Which method best reduces dataset bias to improve model fairness?

hard

A. Collect more dog images to balance classes

B. Remove all cat images to keep only dogs

C. Train model only on cat images

D. Ignore class imbalance and train as is

Solution

1. Step 1: Understand dataset imbalance problem

   Having 90% cats and 10% dogs causes bias favoring cats.

2. Step 2: Choose method to fix bias

   Collecting more dog images balances classes, reducing bias and improving fairness.

3. Final Answer:

   Collect more dog images to balance classes -> Option A

4. Quick Check:

   Balance classes by adding data [OK]

Hint: Balance classes by adding underrepresented data [OK]

Common Mistakes:

• Removing majority class loses useful data
• Training on one class ignores others
• Ignoring imbalance causes biased model