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.