Variational Autoencoder in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define the encoder layer in a Variational Autoencoder.

PyTorch

self.fc1 = nn.Linear(input_dim, [1])

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

Ahidden_dim

Blatent_dim

Coutput_dim

Dbatch_size

Attempts:

3 left

💡 Hint

Common Mistakes

Using latent_dim directly instead of hidden_dim.

Confusing output_dim with latent_dim.

The encoder first maps the input to a hidden dimension before producing latent variables.

2fill in blank

medium

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

PyTorch

z = mu + [1] * std

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

Atorch.rand_like(mu)

Btorch.zeros_like(mu)

Ctorch.ones_like(mu)

Dtorch.randn_like(mu)

Attempts:

3 left

💡 Hint

Common Mistakes

Using zeros or ones instead of random noise.

Using uniform random noise instead of normal.

The reparameterization trick samples from a normal distribution with mean mu and std deviation std by adding noise from a standard normal distribution.

3fill in blank

hard

Fix the error in the KL divergence calculation between the latent distribution and standard normal.

PyTorch

kl_divergence = -0.5 * torch.sum(1 + logvar - [1] - mu.pow(2))

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

Alogvar

Blogvar.exp()

Cmu

Dlogvar.log()

Attempts:

3 left

💡 Hint

Common Mistakes

Using logvar directly instead of its exponential.

Using log of logvar which is incorrect.

The KL divergence formula requires the variance, which is the exponential of log variance.

4fill in blank

hard

Fill in the blank to complete the decoder forward pass that reconstructs the input.

PyTorch

x = F.relu(self.fc3(z))
reconstruction = torch.sigmoid(self.fc4([1]))
return reconstruction, mu, logvar

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

Alogvar

Bz

Cx

Dmu

Attempts:

3 left

💡 Hint

Common Mistakes

Passing mu or logvar instead of the hidden layer x.

Using z in place of the hidden layer before final output.

The decoder applies a ReLU activation to the hidden layer x, then uses x as input to the final layer for reconstruction.

5fill in blank

hard

Fill all three blanks to complete the loss function combining reconstruction loss and KL divergence.

PyTorch

reconstruction_loss = F.binary_cross_entropy(recon_x, [1], reduction='sum')
kl_divergence = -0.5 * torch.sum(1 + [2] - [3] - mu.pow(2))
return reconstruction_loss + kl_divergence

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

Ax

Blogvar

Clogvar.exp()

Drecon_x

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up recon_x and x in reconstruction loss.

Using logvar directly instead of its exponential in KL divergence.

The reconstruction loss compares the reconstructed output with the original input x. The KL divergence uses logvar and its exponential to compute variance.

Practice

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

easy

A. To calculate the loss function

B. To produce the mean and variance for the latent space distribution

C. To generate new data samples from noise

D. To directly reconstruct the input data

Solution

1. Step 1: Understand the role of the encoder in VAE

   The encoder processes input data and outputs parameters of a probability distribution, typically mean and variance, representing the latent space.

2. Step 2: Differentiate encoder from decoder and loss

   The decoder reconstructs data, and loss measures reconstruction and latent space closeness. Encoder specifically outputs mean and variance.

3. Final Answer:

   To produce the mean and variance for the latent space distribution -> Option B

4. Quick Check:

   Encoder outputs mean and variance = D [OK]

Hint: Encoder outputs distribution parameters, not data directly [OK]

Common Mistakes:

• Confusing encoder with decoder
• Thinking encoder reconstructs data
• Assuming encoder calculates loss

2. Which PyTorch function is typically used to sample from the latent space in a VAE using the reparameterization trick?

easy

A. torch.randn()

B. torch.sigmoid()

C. torch.softmax()

D. torch.exp()

Solution

1. Step 1: Identify sampling method in VAE

   The reparameterization trick samples from a normal distribution using random noise, typically generated by torch.randn() in PyTorch.

2. Step 2: Understand other functions' roles

   torch.sigmoid() and torch.softmax() are activation functions, torch.exp() computes exponentials, none sample noise.

3. Final Answer:

   torch.randn() -> Option A

4. Quick Check:

   Sampling noise uses torch.randn() = A [OK]

Hint: Sampling noise uses torch.randn(), not activations [OK]

Common Mistakes:

• Using torch.sigmoid() to sample noise
• Confusing softmax with sampling
• Using torch.exp() incorrectly for sampling

3. Given the following PyTorch code snippet for the reparameterization trick in a VAE, what is the shape of the output z if mu and log_var have shape (batch_size, latent_dim)?

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

medium

A. (batch_size, latent_dim)

B. (latent_dim, batch_size)

C. (batch_size, 1)

D. (1, latent_dim)

Solution

1. Step 1: Analyze shapes of mu and log_var

   Both mu and log_var have shape (batch_size, latent_dim), so std and epsilon will have the same shape due to torch.exp and torch.randn_like.

2. Step 2: Calculate shape of z

   Since z = mu + epsilon * std, all operands have shape (batch_size, latent_dim), so z also has shape (batch_size, latent_dim).

3. Final Answer:

   (batch_size, latent_dim) -> Option A

4. Quick Check:

   Output shape matches input batch and latent dims = A [OK]

Hint: Output shape matches mu and log_var shapes [OK]

Common Mistakes:

• Swapping batch_size and latent_dim
• Assuming output is reduced to (batch_size, 1)
• Confusing shape broadcasting rules

4. Identify the error in this VAE loss function implementation in PyTorch:

def vae_loss(recon_x, x, mu, log_var):
    BCE = nn.functional.binary_cross_entropy(recon_x, x)
    KLD = -0.5 * torch.sum(1 + log_var - mu.pow(2) - log_var.exp())
    return BCE + KLD

medium

A. Incorrect sign in KLD calculation

B. Using torch.sum instead of torch.mean for KLD

C. Missing reduction='sum' in binary_cross_entropy causing scale mismatch

D. Not detaching mu and log_var before loss

Solution

1. Step 1: Check binary_cross_entropy usage

   By default, binary_cross_entropy returns mean loss per element. Summing KLD but not BCE causes scale mismatch.

2. Step 2: Fix BCE reduction

   Adding reduction='sum' to BCE matches scale with KLD, ensuring proper combined loss.

3. Final Answer:

   Missing reduction='sum' in binary_cross_entropy causing scale mismatch -> Option C

4. Quick Check:

   BCE needs reduction='sum' to match KLD scale = B [OK]

Hint: Match loss scales by using reduction='sum' in BCE [OK]

Common Mistakes:

• Ignoring BCE reduction parameter
• Changing KLD sign incorrectly
• Detaching mu/log_var unnecessarily

5. You want to train a VAE on images of size 28x28 pixels with a latent dimension of 20. Which of the following model architectures is most appropriate for the encoder part in PyTorch?

hard

A. A recurrent neural network processing images as sequences, outputting 20 values

B. A single linear layer flattening input and outputting 20 values directly

C. A fully connected network with no nonlinearities outputting 28x28 values

D. A convolutional network with Conv2d layers reducing spatial size, ending with linear layers outputting mean and log variance vectors of size 20

Solution

1. Step 1: Consider input data type and size

   Images of 28x28 pixels are spatial data; convolutional layers efficiently extract features and reduce spatial dimensions.

2. Step 2: Match output to latent dimension

   The encoder must output two vectors (mean and log variance) each of size 20, so linear layers after convolutions are suitable.

3. Step 3: Evaluate other options

   Single linear layer ignores spatial structure; RNNs are not typical for images; fully connected without nonlinearities won't learn complex features.

4. Final Answer:

   A convolutional network with Conv2d layers reducing spatial size, ending with linear layers outputting mean and log variance vectors of size 20 -> Option D

5. Quick Check:

   Conv layers + linear output for mean/log_var = C [OK]

Hint: Use conv layers for images, linear for latent params [OK]

Common Mistakes:

• Using only linear layers ignoring image structure
• Choosing RNNs for image encoding
• Omitting nonlinearities in encoder