Model comparison in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained model for image classification.

Computer Vision

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

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

Atrain

Bfit

Cresnet18

Devaluate

Attempts:

3 left

💡 Hint

Common Mistakes

Using training or evaluation functions instead of model names.

The resnet18 model is a common pre-trained model used for image classification in computer vision.

2fill in blank

medium

Complete the code to set the model to evaluation mode before making predictions.

Computer Vision

model.[1]()

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

Aeval

Bfit

Ctrain

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using train() instead of eval().

Calling eval() sets the model to evaluation mode, which disables dropout and batch normalization updates.

3fill in blank

hard

Fix the error in the code to compute accuracy from model outputs and labels.

Computer Vision

correct = (outputs.argmax(dim=1) [1] labels).sum().item()
accuracy = correct / labels.size(0)

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

A!=

B=

C<

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using assignment = instead of comparison ==.

The equality operator == compares predicted labels to true labels to count correct predictions.

4fill in blank

hard

Fill both blanks to create a dictionary of model names and their validation accuracies.

Computer Vision

results = { '[1]': val_acc1, '[2]': val_acc2 }

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

AResNet18

BVGG16

CAlexNet

DDenseNet

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect or misspelled model names.

Common model names like ResNet18 and VGG16 are used as keys to store their accuracies.

5fill in blank

hard

Fill all three blanks to complete the code that compares two models' accuracies and prints the better one.

Computer Vision

if results['[1]'] [2] results['[3]']:
    print('Better model: ResNet18')
else:
    print('Better model: VGG16')

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

AResNet18

B>

CVGG16

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping model names or using wrong comparison operators.

The code compares the accuracy of ResNet18 and VGG16 using the greater than operator to find the better model.