Custom object detection dataset in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

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

Computer Vision

import cv2
image = cv2.imread([1])
print(image.shape)

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

A'image.jpg'

Bimage.jpg

C['image.jpg']

Dimage

Attempts:

3 left

💡 Hint

Common Mistakes

Not putting the filename in quotes causes an error.

Passing a list instead of a string.

You need to provide the image filename as a string to cv2.imread(). So, it must be in quotes.

2fill in blank

medium

Complete the code to create a list of image file paths from a directory using pathlib.

Computer Vision

from pathlib import Path
image_dir = Path('images')
image_files = list(image_dir.glob([1]))
print(len(image_files))

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

A'*.jpg'

B'*jpg'

C'jpg*'

D'*.jpeg'

Attempts:

3 left

💡 Hint

Common Mistakes

Missing the * wildcard causes no files to be found.

Using incorrect file extension pattern.

The glob method needs a pattern string with a wildcard and file extension, like '*.jpg', to find all JPG files.

3fill in blank

hard

Fix the error in this code that reads bounding box annotations from a CSV file.

Computer Vision

import pandas as pd
annotations = pd.read_csv([1])
print(annotations.head())

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

Acsv.annotations

Bannotations.csv

Cannotations

D'annotations.csv'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a variable name instead of a string filename.

Forgetting quotes around the filename.

The filename must be a string in quotes when passed to pd.read_csv().

4fill in blank

hard

Fill both blanks to create a dictionary of image filenames and their bounding boxes from a DataFrame.

Computer Vision

bbox_dict = {row[[1]]: (row['xmin'], row['ymin'], row['xmax'], row[[2]]) for _, row in annotations.iterrows()}

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

A'filename'

B'xmax'

D'ymax'

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong column names for keys or bounding box coordinates.

Mixing up xmax and ymax columns.

The dictionary key is the filename from the 'filename' column. The bounding box tuple uses 'xmin', 'ymin', 'xmax', and 'ymax' columns. Here, the last blank should be 'ymax'.

5fill in blank

hard

Fill all three blanks to filter annotations for a specific class and create a list of bounding boxes.

Computer Vision

class_name = 'cat'
filtered = annotations[annotations[[1]] == [2]]
bboxes = [(row['xmin'], row['ymin'], row[[3]], row['ymax']) for _, row in filtered.iterrows()]

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

A'class'

B'cat'

C'xmax'

D'filename'

Attempts:

3 left

💡 Hint

Common Mistakes

Filtering by wrong column name.

Using wrong bounding box coordinate names.

We filter rows where the 'class' column equals 'cat'. Then we extract bounding boxes using 'xmin', 'ymin', 'xmax', and 'ymax'. The third blank is 'xmax'.

Practice

1. What is the main purpose of creating a custom object detection dataset?

easy

A. To compress images for faster loading

B. To improve image resolution automatically

C. To generate random images for testing

D. To teach a computer to find specific objects in images

Solution

1. Step 1: Understand the goal of object detection datasets

   Custom object detection datasets are made to help computers learn to recognize and locate specific objects in images.

2. Step 2: Identify the correct purpose

   Among the options, only teaching a computer to find specific objects matches the goal of such datasets.

3. Final Answer:

   To teach a computer to find specific objects in images -> Option D

4. Quick Check:

   Custom dataset purpose = teach detection [OK]

Hint: Custom datasets train models to detect your objects [OK]

Common Mistakes:

• Confusing dataset purpose with image enhancement
• Thinking dataset creates images instead of labeling
• Assuming dataset compresses images

2. Which of the following is the correct format for an annotation line in a YOLO custom dataset label file?

easy

A. class_id x_center y_center width height (all normalized between 0 and 1)

B. image_width image_height class_id x y (pixel values)

C. class_name x_min y_min x_max y_max (absolute pixel coordinates)

D. class_id x_min y_min width height (normalized coordinates)

Solution

1. Step 1: Recall YOLO annotation format

   YOLO uses normalized coordinates with class_id, x_center, y_center, width, and height all between 0 and 1.

2. Step 2: Match options to YOLO format

   class_id x_center y_center width height (all normalized between 0 and 1) matches this format exactly; others use pixel values or different coordinate types.

3. Final Answer:

   class_id x_center y_center width height (all normalized between 0 and 1) -> Option A

4. Quick Check:

   YOLO labels use normalized center coords [OK]

Hint: YOLO labels use normalized center coordinates [OK]

Common Mistakes:

• Using pixel coordinates instead of normalized
• Confusing bounding box corners with center format
• Mixing class name with class id

3. Given this label file line for an image of size 640x480:
2 0.5 0.5 0.25 0.25
What are the pixel coordinates of the bounding box corners (x_min, y_min, x_max, y_max)?

medium

A. (200, 150, 360, 270)

B. (160, 120, 320, 240)

C. (240, 180, 400, 300)

D. (320, 240, 480, 360)

Solution

1. Step 1: Calculate center pixel coordinates

   x_center = 0.5 * 640 = 320, y_center = 0.5 * 480 = 240

2. Step 2: Calculate width and height in pixels

   width = 0.25 * 640 = 160, height = 0.25 * 480 = 120

3. Step 3: Calculate bounding box corners

   x_min = 320 - 160/2 = 240, y_min = 240 - 120/2 = 180
   x_max = 320 + 160/2 = 400, y_max = 240 + 120/2 = 300

4. Final Answer:

   (240, 180, 400, 300) -> Option C

5. Quick Check:

   Center ± half width/height = corners [OK]

Hint: Multiply normalized by image size, then subtract/add half box [OK]

Common Mistakes:

• Using width/height as full coordinates instead of half
• Mixing up x and y calculations
• Forgetting to multiply by image dimensions

4. You have a dataset folder with images and label files. The labels are missing for some images. What is the best way to fix this before training?

medium

A. Remove images without label files from the dataset

B. Create empty label files for those images

C. Rename images to match existing label files

D. Ignore missing labels and train anyway

Solution

1. Step 1: Understand dataset consistency needs

   Training requires each image to have a matching label file with annotations.

2. Step 2: Choose the best fix

   Removing images without labels avoids errors and ensures clean training data. Creating empty labels may confuse the model, renaming won't help if labels don't exist, ignoring missing labels causes errors.

3. Final Answer:

   Remove images without label files from the dataset -> Option A

4. Quick Check:

   Dataset must have matching image-label pairs [OK]

Hint: Keep only images with labels to avoid training errors [OK]

Common Mistakes:

• Creating empty label files that confuse training
• Ignoring missing labels causing crashes
• Renaming files without creating labels

5. You want to add a new object class to your existing custom dataset. Which steps should you follow to update your dataset correctly?

hard

A. Only add new images with the new class, no config changes needed

B. Add the new class to the class list, label new images with it, and update training config

C. Replace old class labels with the new class in all files

D. Add new class images but keep old labels unchanged without config update

Solution

1. Step 1: Update class list

   Add the new object class to your dataset's class list file so the model knows about it.

2. Step 2: Label new images with the new class

   Annotate images containing the new object using the new class id in label files.

3. Step 3: Update training configuration

   Modify your training config to include the new class count and class names.

4. Final Answer:

   Add the new class to the class list, label new images with it, and update training config -> Option B

5. Quick Check:

   Update classes, labels, and config for new objects [OK]

Hint: Update classes, label new data, and config for new objects [OK]

Common Mistakes:

• Not updating class list causing training errors
• Forgetting to label new objects
• Ignoring config updates leading to wrong class counts