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.

Practice

1. What is the main purpose of splitting an image into patches in a Vision Transformer (ViT)?

easy

A. To reduce the image size by cropping

B. To convert the image into smaller parts that the transformer can process as tokens

C. To apply convolution filters on each patch separately

D. To increase the image resolution for better detail

Solution

1. Step 1: Understand ViT input processing

   ViT splits images into fixed-size patches to treat each patch like a word token in language models.

2. Step 2: Purpose of patch splitting

   This allows the transformer to process image patches as a sequence, enabling attention mechanisms to learn relationships.

3. Final Answer:

   To convert the image into smaller parts that the transformer can process as tokens -> Option B

4. Quick Check:

   Image patches = tokens for transformer [OK]

Hint: Think of patches as words in a sentence for the transformer [OK]

Common Mistakes:

• Confusing patch splitting with image resizing
• Thinking patches are processed by convolution
• Assuming patches increase image resolution

2. Which of the following is the correct way to add a class token to the patch embeddings in ViT using Python-like pseudocode?

easy

A. patches = torch.cat([class_token, patches], dim=1)

B. patches = torch.cat([patches, class_token], dim=1)

C. patches = torch.cat([patches, class_token], dim=0)

D. patches = torch.cat([class_token, patches], dim=0)

Solution

1. Step 1: Understand tensor concatenation dimension

   Patch embeddings are sequences along dimension 1 (batch, seq, embed); class token must be prepended along this dimension.

2. Step 2: Correct concatenation syntax

   Using torch.cat with dim=1 adds class_token at the start of the sequence correctly.

3. Final Answer:

   patches = torch.cat([class_token, patches], dim=1) -> Option A

4. Quick Check:

   Class token prepended along sequence dim = patches = torch.cat([class_token, patches], dim=1) [OK]

Hint: Class token goes first, concat along sequence dimension (dim=1) [OK]

Common Mistakes:

• Concatenating along wrong dimension (dim=0)
• Appending class token at the end instead of start
• Mixing order of tensors in concat

3. Given the following simplified ViT patch embedding code, what is the shape of patch_embeddings after processing a batch of 8 images of size 32x32 with patch size 8 and embedding dimension 64?

patch_size = 8
embedding_dim = 64
batch_size = 8
image_size = 32
num_patches = (image_size // patch_size) ** 2
patch_embeddings = torch.randn(batch_size, num_patches, embedding_dim)

medium

A. (16, 8, 64)

B. (8, 64, 16)

C. (8, 8, 64)

D. (8, 16, 64)

Solution

1. Step 1: Calculate number of patches

   Number of patches = (32 / 8)^2 = 4^2 = 16 patches per image.

2. Step 2: Determine patch_embeddings shape

   Shape is (batch_size, num_patches, embedding_dim) = (8, 16, 64).

3. Final Answer:

   (8, 16, 64) -> Option D

4. Quick Check:

   Batch=8, patches=16, embed=64 [OK]

Hint: Calculate patches as (image/patch)^2, then batch x patches x embed [OK]

Common Mistakes:

• Mixing embedding dimension and patch count order
• Calculating patches incorrectly
• Confusing batch size with patch count

4. You have this ViT code snippet that throws an error:

class_token = torch.randn(1, 1, 64)
patches = torch.randn(8, 16, 64)
input_seq = torch.cat([class_token, patches], dim=1)

What is the cause of the error?

medium

A. Embedding dimensions do not match

B. Wrong concatenation dimension; should be dim=0

C. class_token shape should be (8, 1, 64) to match batch size

D. Dimension mismatch because class_token sequence size is 1 but patches sequence size is 16

Solution

1. Step 1: Check batch size compatibility

   class_token has batch size 1, patches have batch size 8; they must match for concatenation.

2. Step 2: Fix class_token shape

   class_token should be repeated or created with shape (8, 1, 64) to match patches batch size.

3. Final Answer:

   class_token shape should be (8, 1, 64) to match batch size -> Option C

4. Quick Check:

   Batch sizes must match for concat [OK]

Hint: Match batch sizes before concatenating tensors [OK]

Common Mistakes:

• Ignoring batch size mismatch
• Changing wrong concat dimension
• Assuming embedding dims cause error

5. In a Vision Transformer model, why is the class token important for image classification tasks?

hard

A. It aggregates information from all patches via attention to produce a final image representation

B. It stores the positional information of patches

C. It applies convolution to patches before transformer layers

D. It normalizes the patch embeddings before feeding to the transformer

Solution

1. Step 1: Understand class token role

   The class token is a special token that attends to all patch tokens and gathers their information.

2. Step 2: Use in classification

   After transformer layers, the class token embedding is used as the image's summary representation for classification.

3. Final Answer:

   It aggregates information from all patches via attention to produce a final image representation -> Option A

4. Quick Check:

   Class token = image summary for classification [OK]

Hint: Class token collects info from patches for final decision [OK]

Common Mistakes:

• Confusing class token with positional encoding
• Thinking class token applies convolution
• Assuming class token normalizes embeddings