Faster R-CNN usage in PyTorch

Introduction

Faster R-CNN helps find and label objects in pictures quickly and accurately.

You want to detect cars and people in street photos.

You need to find animals in wildlife images.

You want to count items on a store shelf from photos.

You want to spot defects in product images on a factory line.

Syntax

PyTorch

import torchvision
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()

# To predict on an image:
# 1. Load and transform the image
# 2. Pass it to the model
# 3. Get predictions with boxes, labels, and scores

Use pretrained=True to get a model already trained on common objects.

Call model.eval() to set the model for prediction (not training).

Examples

Load the Faster R-CNN model with pretrained weights and set it to evaluation mode.

PyTorch

import torchvision
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()

Load an image and convert it to a tensor for the model.

PyTorch

from PIL import Image
from torchvision import transforms

image = Image.open('image.jpg')
transform = transforms.Compose([
    transforms.ToTensor()
])
image_tensor = transform(image)

Run the model on the image tensor without tracking gradients to get predictions.

PyTorch

import torch
with torch.no_grad():
    predictions = model([image_tensor])

Sample Model

This code loads a pretrained Faster R-CNN model, creates a blank image, transforms it, and runs prediction. It prints the keys in the prediction dictionary and some example outputs.

PyTorch

import torch
from PIL import Image
from torchvision import transforms
import torchvision

# Load pretrained Faster R-CNN model
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()

# Load and transform image
image = Image.new('RGB', (300, 300), color='white')  # blank white image
transform = transforms.Compose([
    transforms.ToTensor()
])
image_tensor = transform(image)

# Predict
with torch.no_grad():
    predictions = model([image_tensor])

# Print prediction keys and example outputs
print('Prediction keys:', predictions[0].keys())
print('Boxes shape:', predictions[0]['boxes'].shape)
print('Labels:', predictions[0]['labels'])
print('Scores:', predictions[0]['scores'])

Important Notes

Faster R-CNN expects input images as tensors with shape [3, height, width] and values between 0 and 1.

Predictions include bounding boxes, labels (class IDs), and confidence scores.

On images without detectable objects, predictions may be empty (zero boxes).

Summary

Faster R-CNN finds objects in images and gives their locations and labels.

Use pretrained models for quick start and evaluation mode for prediction.

Transform images to tensors before passing to the model.

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