Custom object detection dataset in Computer Vision - Model Pipeline Trace

Model Pipeline - Custom object detection dataset

This pipeline shows how a custom object detection dataset is prepared, used to train a model, and then how the model predicts objects in new images.

Data Flow - 5 Stages

1Raw dataset

1000 images x varying sizes→Collect images and bounding box annotations with labels→1000 images with bounding boxes and labels

Image1: cat at (50,30,150,130), dog at (200,100,300,250)

↓

2Preprocessing

1000 images with bounding boxes→Resize images to 224x224, normalize pixel values, adjust bounding boxes accordingly→1000 images 224x224 x 3 channels with normalized pixel values and updated bounding boxes

Image1 resized to 224x224, cat box now (20,12,60,52)

↓

3Data augmentation

1000 images 224x224 with bounding boxes→Apply random flips and color jitter, update bounding boxes for flips→1000 augmented images 224x224 with updated bounding boxes

Image1 flipped horizontally, cat box coordinates adjusted accordingly

↓

4Train/test split

1000 augmented images with bounding boxes→Split dataset into 800 training and 200 testing images→800 training images, 200 testing images with bounding boxes

Training set: 800 images, Testing set: 200 images

↓

5Model input preparation

800 training images 224x224 with bounding boxes→Convert bounding boxes and labels into model-specific tensor format→800 training samples with image tensors and target tensors

Sample: image tensor shape (3,224,224), target dict with boxes tensor shape (N,4), labels tensor shape (N)

Training Trace - Epoch by Epoch

Loss
2.5 |*****
2.0 |**** 
1.5 |***  
1.0 |**   
0.5 |*    
0.0 +-----
      1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.5	0.15	High loss and low accuracy as model starts learning
2	1.8	0.35	Loss decreases, accuracy improves as model learns object features
3	1.2	0.55	Model better detects objects, bounding box predictions improve
4	0.9	0.70	Loss continues to decrease, accuracy rises steadily
5	0.7	0.78	Model converging, good detection performance

Prediction Trace - 6 Layers

Layer 1: Input image preprocessing

Layer 2: Feature extraction (CNN layers)

Layer 3: Region proposal network

Layer 4: Bounding box regression and classification

Layer 5: Non-maximum suppression

Layer 6: Output prediction

Model Quiz - 3 Questions

What happens to the bounding boxes during image resizing in preprocessing?

A They are adjusted to match the new image size

B They remain the same as original image

C They are removed and recreated later

D They are converted to grayscale

Key Insight

This visualization shows how preparing a custom object detection dataset carefully and training a model step-by-step leads to improved detection accuracy and reliable bounding box predictions.

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