R-CNN family overview in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the R-CNN model from torchvision.

Computer Vision

from torchvision.models.detection import [1]

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

Afasterrcnn_resnet50_fpn

Bmaskrcnn_resnet50_fpn

Cresnet50

Dretinanet_resnet50_fpn

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing Mask R-CNN or RetinaNet instead of Faster R-CNN.

Importing a backbone model like resnet50 instead of the detection model.

The fasterrcnn_resnet50_fpn is the Faster R-CNN model implementation in torchvision.

2fill in blank

medium

Complete the code to create a Faster R-CNN model pre-trained on COCO dataset.

Computer Vision

model = [1](pretrained=True)

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

Afasterrcnn_resnet50_fpn

Bretinanet_resnet50_fpn

Cmaskrcnn_resnet50_fpn

Dssd300_vgg16

Attempts:

3 left

💡 Hint

Common Mistakes

Using Mask R-CNN or RetinaNet functions instead.

Forgetting to set pretrained=True.

The fasterrcnn_resnet50_fpn function creates a Faster R-CNN model with a ResNet-50 backbone and Feature Pyramid Network, pretrained on COCO.

3fill in blank

hard

Fix the error in the code to get the number of classes for the Faster R-CNN model.

Computer Vision

num_classes = model.roi_heads.box_predictor.[1]

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

Apredictor

Bcls_score

Cscore

Dnum_classes

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'cls_score' which is a layer, not the number of classes.

Using 'predictor' which is a module, not a number.

The attribute num_classes holds the number of classes the Faster R-CNN model predicts.

4fill in blank

hard

Fill both blanks to replace the Faster R-CNN box predictor with a new one for a custom number of classes.

Computer Vision

in_features = model.roi_heads.box_predictor.[1]
model.roi_heads.box_predictor = FastRCNNPredictor(in_features, [2])

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

Acls_score.in_features

Bnum_classes

C5

Dcls_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'num_classes' instead of 'cls_score.in_features' for the first blank.

Putting the attribute 'num_classes' in the second blank instead of an integer.

The cls_score.in_features gives the input features for the box predictor. We replace the box predictor with FastRCNNPredictor using the new number of classes, here 5.

5fill in blank

hard

Fill all three blanks to create a Mask R-CNN model with a ResNet-50 backbone and set it to evaluation mode.

Computer Vision

from torchvision.models.detection import [1]
model = [2](pretrained=True)
model.[3]()

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

Amaskrcnn_resnet50_fpn

Ceval

Dtrain

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train()' instead of 'eval()' to set the model mode.

Importing Faster R-CNN instead of Mask R-CNN.

Import maskrcnn_resnet50_fpn, create the model with pretrained weights, and set it to evaluation mode with eval().

Practice

1. What is the main purpose of the R-CNN family of models in computer vision?

easy

A. To enhance image resolution

B. To generate captions for images

C. To detect edges in images

D. To find and classify objects in images by proposing regions

Solution

1. Step 1: Understand R-CNN model goal

   The R-CNN family is designed to locate objects by proposing regions and then classify them.

2. Step 2: Compare options with model purpose

   Only To find and classify objects in images by proposing regions matches the goal of finding and classifying objects using region proposals.

3. Final Answer:

   To find and classify objects in images by proposing regions -> Option D

4. Quick Check:

   R-CNN purpose = find and classify objects [OK]

Hint: R-CNN = Region proposals + Classification [OK]

Common Mistakes:

• Confusing R-CNN with image captioning models
• Thinking R-CNN enhances image quality
• Mixing edge detection with object detection

2. Which of the following is the correct sequence of steps in the original R-CNN pipeline?

easy

A. Classify entire image, extract regions, refine bounding boxes

B. Refine bounding boxes, extract regions, classify regions

C. Extract regions, classify regions, refine bounding boxes

D. Extract regions, refine bounding boxes, classify entire image

Solution

1. Step 1: Recall R-CNN pipeline steps

   R-CNN first extracts region proposals, then classifies each region, and finally refines bounding boxes.

2. Step 2: Match steps with options

   Extract regions, classify regions, refine bounding boxes correctly lists the steps in order: extract regions, classify, then refine boxes.

3. Final Answer:

   Extract regions, classify regions, refine bounding boxes -> Option C

4. Quick Check:

   R-CNN steps = extract, classify, refine [OK]

Hint: Remember: Propose regions first, then classify [OK]

Common Mistakes:

• Classifying before extracting regions
• Refining boxes before classification
• Mixing order of steps

3. Given the following code snippet for Faster R-CNN, what is the output shape of the feature map if the input image is 224x224 and the backbone reduces size by a factor of 16?

input_image = torch.randn(1, 3, 224, 224)
features = backbone(input_image)
print(features.shape)

medium

A. [1, C, 14, 14]

B. [1, C, 7, 7]

C. [1, C, 28, 28]

D. [1, C, 224, 224]

Solution

1. Step 1: Calculate spatial size after backbone

   The backbone reduces the input size by factor 16, so 224 / 16 = 14.

2. Step 2: Determine output shape format

   Output shape is batch size 1, channels C (depends on backbone), height 14, width 14.

3. Final Answer:

   [1, C, 14, 14] -> Option A

4. Quick Check:

   224/16 = 14, so output height and width = 14 [OK]

Hint: Divide input size by backbone stride for output size [OK]

Common Mistakes:

• Using 7 instead of 14 for output size
• Confusing channels with spatial dimensions
• Assuming no size reduction

4. You have a Mask R-CNN model but it is not producing masks for detected objects. Which of the following is the most likely cause?

medium

A. The backbone network is too shallow

B. The model was trained without the mask branch enabled

C. The input images are grayscale instead of RGB

D. The bounding box proposals are too large

Solution

1. Step 1: Understand Mask R-CNN mask output

   Mask R-CNN produces masks only if the mask branch is included and trained.

2. Step 2: Analyze options for mask absence

   If the mask branch is disabled during training, no masks will be produced, making The model was trained without the mask branch enabled correct.

3. Final Answer:

   The model was trained without the mask branch enabled -> Option B

4. Quick Check:

   Mask branch enabled = masks output [OK]

Hint: Masks need mask branch enabled and trained [OK]

Common Mistakes:

• Blaming backbone depth for missing masks
• Assuming grayscale input stops mask output
• Thinking bounding box size affects mask generation

5. You want to improve the speed of an R-CNN model without losing much accuracy. Which approach from the R-CNN family is best suited for this?

hard

A. Use Faster R-CNN with a Region Proposal Network (RPN)

B. Use Fast R-CNN with selective search region proposals

C. Use Mask R-CNN with added mask prediction

D. Use the original R-CNN with SVM classifiers

Solution

1. Step 1: Identify speed improvements in R-CNN family

   Faster R-CNN improves speed by integrating a Region Proposal Network to generate proposals efficiently.

2. Step 2: Compare options for speed and accuracy

   Fast R-CNN still uses slow selective search; Mask R-CNN adds mask overhead; original R-CNN is slow. So Faster R-CNN is best.

3. Final Answer:

   Use Faster R-CNN with a Region Proposal Network (RPN) -> Option A

4. Quick Check:

   Faster R-CNN = speed + accuracy via RPN [OK]

Hint: Faster R-CNN uses RPN for faster proposals [OK]

Common Mistakes:

• Choosing Fast R-CNN which still uses slow proposals
• Adding mask prediction which slows model
• Using original R-CNN which is slow