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).

Practice

1. What is the primary purpose of the Faster R-CNN model in PyTorch?

easy

A. To enhance image resolution

B. To generate captions for images

C. To detect objects and their locations in images

D. To classify images into categories without localization

Solution

1. Step 1: Understand Faster R-CNN's role

   Faster R-CNN is designed to find objects and their bounding boxes in images.

2. Step 2: Compare with other tasks

   Unlike captioning or classification without localization, Faster R-CNN outputs object locations and labels.

3. Final Answer:

   To detect objects and their locations in images -> Option C

4. Quick Check:

   Object detection = Faster R-CNN purpose [OK]

Hint: Faster R-CNN = object detection with bounding boxes [OK]

Common Mistakes:

• Confusing detection with classification only
• Thinking it generates image captions
• Assuming it enhances image quality

2. Which of the following is the correct way to load a pretrained Faster R-CNN model in PyTorch?

easy

A. model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT')

B. model = torchvision.models.fasterrcnn_resnet50_fpn(pretrained=False)

C. model = torchvision.models.fasterrcnn_resnet50_fpn(pretrained=True)

D. model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights=None)

Solution

1. Step 1: Check PyTorch's current API for pretrained models

   PyTorch now uses the 'weights' argument with 'DEFAULT' to load pretrained weights.

2. Step 2: Identify correct syntax

   model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT') uses weights='DEFAULT', which is the recommended way to load pretrained Faster R-CNN.

3. Final Answer:

   model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT') -> Option A

4. Quick Check:

   Use weights='DEFAULT' for pretrained models [OK]

Hint: Use weights='DEFAULT' to load pretrained Faster R-CNN [OK]

Common Mistakes:

• Using deprecated pretrained=True argument
• Setting weights=None disables pretrained weights
• Confusing model namespaces in torchvision

3. Given the following code snippet, what is the output type of outputs after the model prediction?

import torchvision
import torch
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT')
model.eval()
image = torch.rand(3, 300, 400)  # Random image tensor
outputs = model([image])

medium

A. A list of dictionaries with keys 'boxes', 'labels', and 'scores'

B. A single tensor with class probabilities

C. A dictionary with keys 'boxes' and 'labels' only

D. A tensor of shape (3, 300, 400) identical to input

Solution

1. Step 1: Understand Faster R-CNN output format

   Faster R-CNN returns a list of dictionaries, one per input image, each containing 'boxes', 'labels', and 'scores'.

2. Step 2: Analyze the code snippet

   Since input is a list with one image, output is a list with one dictionary containing detection results.

3. Final Answer:

   A list of dictionaries with keys 'boxes', 'labels', and 'scores' -> Option A

4. Quick Check:

   Output = list of dicts with boxes, labels, scores [OK]

Hint: Faster R-CNN outputs list of dicts with boxes, labels, scores [OK]

Common Mistakes:

• Expecting a single tensor output
• Missing 'scores' key in output
• Confusing input and output tensor shapes

4. Identify the error in the following code snippet for using Faster R-CNN for prediction:

import torchvision
import torch
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT')
model.eval()
image = torch.rand(3, 224, 224)
outputs = model(image)

medium

A. Model.eval() should be called after prediction

B. Input image should be a list of tensors, not a single tensor

C. Weights argument 'DEFAULT' is invalid

D. Image tensor shape should be (224, 224, 3) instead of (3, 224, 224)

Solution

1. Step 1: Check input format for Faster R-CNN

   Faster R-CNN expects a list of image tensors, even if only one image is passed.

2. Step 2: Identify the error in the code

   The code passes a single tensor instead of a list, causing a runtime error.

3. Final Answer:

   Input image should be a list of tensors, not a single tensor -> Option B

4. Quick Check:

   Input = list of tensors for Faster R-CNN [OK]

Hint: Wrap input image in a list before passing to model [OK]

Common Mistakes:

• Passing single tensor instead of list
• Calling eval() after prediction
• Confusing channel order in tensor shape

5. You want to fine-tune a pretrained Faster R-CNN model on a custom dataset with 5 classes (including background). Which step is necessary before training?

hard

A. Change the input image size to (5, 224, 224)

B. Freeze all layers except the backbone

C. Set model.train() before loading pretrained weights

D. Replace the model's box predictor head with a new one having 5 output classes

Solution

1. Step 1: Understand model adaptation for new classes

   The box predictor head controls class outputs; it must match the number of classes in your dataset.

2. Step 2: Replace the box predictor head

   Replace the existing head with a new one configured for 5 classes to fine-tune properly.

3. Final Answer:

   Replace the model's box predictor head with a new one having 5 output classes -> Option D

4. Quick Check:

   Adjust box predictor for new class count [OK]

Hint: Change box predictor head to match your classes [OK]

Common Mistakes:

• Changing input image channels incorrectly
• Not replacing box predictor head
• Freezing all layers prevents fine-tuning