Variational Autoencoder in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define the encoder input layer for a Variational Autoencoder.

Computer Vision

inputs = Input(shape=[1])

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

A(64, 64, 3)

B(32, 32, 3)

C(28, 28, 1)

D(100,)

Attempts:

3 left

💡 Hint

Common Mistakes

Using a shape with 3 channels for grayscale images.

Confusing the batch size with the input shape.

The input shape for the encoder in a VAE working on grayscale 28x28 images is (28, 28, 1).

2fill in blank

medium

Complete the code to sample latent variables z using the reparameterization trick.

Computer Vision

z = [1](mean, log_var)

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

Areparametrize

Blatent_sample

Csample_latent

Dsampling

Attempts:

3 left

💡 Hint

Common Mistakes

Using a function name that is not defined in the code.

Confusing the sampling function with the encoder or decoder.

The function 'sampling' is commonly used to implement the reparameterization trick in VAEs.

3fill in blank

hard

Fix the error in the loss function by completing the KL divergence term.

Computer Vision

kl_loss = -0.5 * K.sum(1 + [1] - K.square(mean) - K.exp(log_var), axis=-1)

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

Amean

Blog_var

Cz

Dinputs

Attempts:

3 left

💡 Hint

Common Mistakes

Using mean instead of log variance in the KL divergence term.

Using the sampled latent variable z instead of log variance.

The KL divergence term uses the log variance (log_var) in the formula.

4fill in blank

hard

Fill both blanks to complete the decoder output layer and activation function.

Computer Vision

outputs = Dense([1], activation=[2])(decoder_hidden)

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

A784

Bsigmoid

Crelu

D256

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu activation in the output layer instead of sigmoid.

Setting output units to a hidden layer size instead of image size.

The decoder output layer should have 784 units (28*28) with sigmoid activation to output pixel probabilities.

5fill in blank

hard

Fill all three blanks to complete the VAE model compilation with optimizer, loss, and metrics.

Computer Vision

vae.compile(optimizer=[1], loss=[2], metrics=[[3]])

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

A'adam'

Bvae_loss

C'accuracy'

D'sgd'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sgd' optimizer which may be slower to converge.

Using a standard loss instead of the custom VAE loss.

Not including any metrics or using incorrect metric names.

The VAE is commonly compiled with the 'adam' optimizer, a custom loss function 'vae_loss', and 'accuracy' as a metric.

Practice

1. What is the main purpose of a Variational Autoencoder (VAE) in computer vision?

easy

A. To compress data into a smaller, meaningful representation and generate new data samples

B. To classify images into different categories

C. To detect edges in images

D. To increase the resolution of images

Solution

1. Step 1: Understand VAE's role in data compression

   VAEs encode input data into a smaller latent space that captures important features.

2. Step 2: Recognize VAE's generative ability

   VAEs can generate new data by sampling from the latent space, unlike simple compression methods.

3. Final Answer:

   To compress data into a smaller, meaningful representation and generate new data samples -> Option A

4. Quick Check:

   VAE purpose = compress + generate [OK]

Hint: Remember: VAE compresses and creates new data [OK]

Common Mistakes:

• Confusing VAE with classifiers
• Thinking VAE only compresses without generation
• Mixing VAE with image enhancement methods

2. Which part of the Variational Autoencoder architecture introduces randomness during training?

easy

A. The encoder output layer

B. The reparameterization trick

C. The decoder input layer

D. The loss function calculation

Solution

1. Step 1: Identify where randomness is needed

   Randomness is introduced to sample from the latent space during training.

2. Step 2: Recognize the reparameterization trick's role

   This trick allows gradients to flow through random sampling by expressing sampling as a deterministic function plus noise.

3. Final Answer:

   The reparameterization trick -> Option B

4. Quick Check:

   Randomness in VAE = reparameterization trick [OK]

Hint: Randomness comes from reparameterization trick [OK]

Common Mistakes:

• Thinking encoder output is random by itself
• Confusing decoder input with randomness source
• Assuming loss function adds randomness

3. Given the following PyTorch snippet for sampling latent variables in a VAE, what is the shape of z if mu and log_var have shape (batch_size, latent_dim)?

std = torch.exp(0.5 * log_var)
eps = torch.randn_like(std)
z = mu + eps * std

medium

A. (latent_dim, batch_size)

B. (1, latent_dim)

C. (batch_size, 1)

D. (batch_size, latent_dim)

Solution

1. Step 1: Analyze shapes of mu and log_var

   Both have shape (batch_size, latent_dim), so std and eps will match this shape.

2. Step 2: Calculate z shape from element-wise operations

   Since z = mu + eps * std is element-wise, z keeps the same shape as mu and std.

3. Final Answer:

   (batch_size, latent_dim) -> Option D

4. Quick Check:

   z shape = mu shape = (batch_size, latent_dim) [OK]

Hint: Element-wise ops keep shape same as inputs [OK]

Common Mistakes:

• Swapping batch_size and latent_dim dimensions
• Assuming z is a vector, not a batch
• Confusing shape of eps with mu

4. You implemented a VAE but notice the generated images are very blurry. Which debugging step is most likely to improve image sharpness?

medium

A. Use a smaller batch size during training

B. Remove the KL divergence term from the loss function

C. Increase the latent space dimension to capture more details

D. Replace the decoder with a simple linear layer

Solution

1. Step 1: Understand cause of blurry images

   Blurriness often means the latent space is too small to capture enough detail.

2. Step 2: Choose the fix that increases detail capacity

   Increasing latent dimension allows encoding more features, improving sharpness.

3. Final Answer:

   Increase the latent space dimension to capture more details -> Option C

4. Quick Check:

   More latent dims = better detail [OK]

Hint: Bigger latent space means clearer images [OK]

Common Mistakes:

• Removing KL divergence breaks training stability
• Changing batch size rarely fixes blurriness
• Simplifying decoder reduces model power

5. You want to generate new images similar to your training set using a trained VAE. Which step correctly describes how to generate these images?

hard

A. Sample random points from a standard normal distribution, then pass them through the decoder

B. Feed random noise directly into the encoder and use its output as images

C. Use the encoder to compress training images, then output those compressed vectors as images

D. Train the VAE again with random noise as input to generate images

Solution

1. Step 1: Understand VAE latent space distribution

   The latent space is modeled as a standard normal distribution after training.

2. Step 2: Generate images by sampling and decoding

   Sampling random points from this distribution and decoding them produces new images similar to training data.

3. Final Answer:

   Sample random points from a standard normal distribution, then pass them through the decoder -> Option A

4. Quick Check:

   Generate = sample latent + decode [OK]

Hint: Sample latent space, decode to generate images [OK]

Common Mistakes:

• Feeding noise into encoder instead of decoder
• Using encoder outputs as images directly
• Retraining VAE unnecessarily for generation