Faster R-CNN usage in PyTorch - Model Pipeline Trace

Model Pipeline - Faster R-CNN usage

Faster R-CNN is a model that finds objects in pictures. It looks at the image, guesses where objects might be, and then checks those guesses to say what the objects are.

Data Flow - 6 Stages

1Input Image

1 image x 3 channels x 800 height x 800 width→Load and normalize image pixels→1 image x 3 channels x 800 height x 800 width

A photo of a dog and a cat, pixel values scaled between 0 and 1

↓

2Feature Extraction

1 image x 3 channels x 800 height x 800 width→Pass image through backbone CNN (e.g., ResNet) to get features→1 image x 256 channels x 50 height x 50 width

Feature map highlighting edges and textures of dog and cat

↓

3Region Proposal Network (RPN)

1 image x 256 channels x 50 height x 50 width→Generate candidate boxes where objects might be→1000 proposals x 4 coordinates (x1, y1, x2, y2)

Boxes around dog's head, cat's body, and background areas

↓

4RoI Pooling

Feature map (1x256x50x50) + 1000 proposals→Extract fixed-size feature for each proposal→1000 proposals x 256 channels x 7 height x 7 width

Small feature patches representing each proposed box

↓

5Classification and Bounding Box Regression

1000 proposals x 256 channels x 7 height x 7 width→Classify each proposal and refine box coordinates→1000 proposals x (class scores + 4 refined box coords)

Scores showing high confidence for dog and cat classes

↓

6Post-processing

1000 proposals with class scores and boxes→Apply Non-Maximum Suppression to remove overlapping boxes→Final detected boxes (e.g., 5 boxes) with classes

Boxes tightly around dog and cat with labels and confidence

Training Trace - Epoch by Epoch

Loss
1.2 |*       
1.0 | *      
0.8 |  *     
0.6 |   *    
0.4 |    *   
    +---------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning, loss is high, accuracy low
2	0.9	0.60	Loss decreases, accuracy improves as model learns features
3	0.7	0.72	Better object proposals and classification
4	0.55	0.80	Model refines bounding boxes and class predictions
5	0.45	0.85	Training converges with good detection performance

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: Backbone CNN

Layer 3: Region Proposal Network

Layer 4: RoI Pooling

Layer 5: Classification and Box Regression

Layer 6: Non-Maximum Suppression

Model Quiz - 3 Questions

What does the Region Proposal Network (RPN) do in Faster R-CNN?

A Suggests possible object locations in the image

B Classifies objects into categories

C Normalizes the input image pixels

D Applies Non-Maximum Suppression to boxes

Key Insight

Faster R-CNN works by first suggesting where objects might be, then checking those spots carefully to say what the objects are. Training improves the model by lowering mistakes (loss) and increasing correct guesses (accuracy).