Vision Transformer (ViT) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the Vision Transformer model from the torchvision library.

Computer Vision

from torchvision.models import [1]

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

Aalexnet

Bresnet50

Cvgg16

Dvit_b_16

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a CNN model like resnet50 instead of the Vision Transformer.

Confusing ViT with older architectures like alexnet or vgg16.

The Vision Transformer model in torchvision is imported as vit_b_16. Other options are different CNN models.

2fill in blank

medium

Complete the code to create a Vision Transformer model pretrained on ImageNet.

Computer Vision

model = [1](pretrained=True)

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

Adensenet121

Bresnet50

Cvit_b_16

Dmobilenet_v2

Attempts:

3 left

💡 Hint

Common Mistakes

Using a CNN model instead of ViT.

Forgetting to set pretrained=True to get pretrained weights.

To create a pretrained Vision Transformer, use vit_b_16(pretrained=True). Other options are different model architectures.

3fill in blank

hard

Fix the error in the code to correctly reshape the input image tensor for ViT patch embedding.

Computer Vision

patches = x.unfold(2, [1], [1]).unfold(3, [1], [1])

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

A8

B16

C32

D64

Attempts:

3 left

💡 Hint

Common Mistakes

Using patch sizes other than 16 causes shape mismatch errors.

Confusing patch size with image size.

ViT uses 16x16 patches, so the unfold size and step must be 16.

4fill in blank

hard

Fill both blanks to complete the code that applies the multi-head self-attention mechanism in ViT.

Computer Vision

attention_output = self.attn(query, key, value, [1]=mask, [2]=True)

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

Aattn_mask

Bkey_padding_mask

Cbatch_first

Ddropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using key_padding_mask instead of attn_mask for the mask parameter.

Omitting batch_first=True causing shape errors.

The attn_mask parameter applies the attention mask, and batch_first=True specifies the input shape format.

5fill in blank

hard

Fill all three blanks to complete the code that computes the classification output from the ViT model.

Computer Vision

cls_token = x[:, [1]].unsqueeze(1)
output = self.mlp_head(cls_token).squeeze([2])
loss = criterion(output, [3])

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

A0

B1

Clabels

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong index for CLS token.

Squeezing the wrong dimension causing shape errors.

Passing predictions instead of labels to the loss function.

The classification token is at index 0, unsqueezed at dimension 1, and the loss is computed against the true labels.