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().