Autoencoder architecture in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define the encoder layer in a simple autoencoder.

PyTorch

import torch.nn as nn

class Autoencoder(nn.Module):
    def __init__(self):
        super(Autoencoder, self).__init__()
        self.encoder = nn.Sequential(
            nn.Linear(784, 128),
            nn.ReLU(),
            nn.Linear(128, [1]),
            nn.ReLU()
        )

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

A64

B256

C512

D1024

Attempts:

3 left

💡 Hint

Common Mistakes

Using a bottleneck size larger than the input size defeats compression.

Choosing a bottleneck size too large reduces the model's ability to learn compact features.

The encoder compresses the input from 784 to 64 features before decoding. 64 is a common bottleneck size for simple autoencoders.

2fill in blank

medium

Complete the code to define the decoder layer in the autoencoder.

PyTorch

class Autoencoder(nn.Module):
    def __init__(self):
        super(Autoencoder, self).__init__()
        self.decoder = nn.Sequential(
            nn.Linear(64, 128),
            nn.ReLU(),
            nn.Linear(128, [1]),
            nn.Sigmoid()
        )

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

A512

B64

C784

D256

Attempts:

3 left

💡 Hint

Common Mistakes

Setting the output size smaller than the input causes incomplete reconstruction.

Using a non-matching output size causes shape errors during training.

The decoder reconstructs the original input size of 784 from the bottleneck size.

3fill in blank

hard

Fix the error in the forward method of the autoencoder.

PyTorch

def forward(self, x):
    encoded = self.encoder(x)
    decoded = self.decoder([1])
    return decoded

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

Aself.decoder

Bx

Cself.encoder

Dencoded

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the original input to the decoder instead of the encoded representation.

Passing the decoder or encoder functions themselves instead of data.

The decoder should take the encoded output as input to reconstruct the original data.

4fill in blank

hard

Fill both blanks to complete the training loop for the autoencoder.

PyTorch

for data in dataloader:
    inputs, _ = data
    optimizer.zero_grad()
    outputs = model([1])
    loss = criterion(outputs, [2])
    loss.backward()
    optimizer.step()

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

Ainputs

Boutputs

Cinputs.detach()

Dinputs.float()

Attempts:

3 left

💡 Hint

Common Mistakes

Using outputs as input to the model causes infinite loops.

Not converting inputs to float causes type errors in loss calculation.

The model input is the raw inputs, and the loss compares outputs to the original inputs converted to float for proper calculation.

5fill in blank

hard

Fill all three blanks to create a dictionary that stores the encoded representations for each input batch.

PyTorch

encoded_data = {}
for i, data in enumerate(dataloader):
    inputs, _ = data
    encoded = model.encoder([1])
    encoded_data[[2]] = [3]

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

Ainputs

Bi

Cencoded.detach()

Dinputs.float()

Attempts:

3 left

💡 Hint

Common Mistakes

Not detaching encoded tensors causes memory leaks.

Using inputs as dictionary keys causes errors.

Not converting inputs to float causes type errors.

Inputs are converted to float before encoding, the batch index i is used as the dictionary key, and the encoded tensor is detached from the computation graph before storing.

Practice

1. What is the main purpose of the encoder part in an autoencoder?

easy

A. To generate new random data samples

B. To reconstruct the original input from compressed data

C. To classify the input data into categories

D. To compress the input data into a smaller representation

Solution

1. Step 1: Understand the role of encoder

   The encoder compresses input data into a smaller form called latent space or code.

2. Step 2: Differentiate encoder from decoder

   The decoder rebuilds the original data from this compressed form, not the encoder.

3. Final Answer:

   To compress the input data into a smaller representation -> Option D

4. Quick Check:

   Encoder compresses data = A [OK]

Hint: Encoder compresses, decoder reconstructs [OK]

Common Mistakes:

• Confusing encoder with decoder
• Thinking encoder classifies data
• Assuming encoder generates new data

2. Which of the following is the correct way to define a simple encoder layer in PyTorch?

easy

A. self.encoder = nn.Linear(input_dim, hidden_dim)

B. self.encoder = nn.Conv2d(hidden_dim, input_dim)

C. self.encoder = nn.ReLU(input_dim, hidden_dim)

D. self.encoder = nn.MaxPool2d(input_dim, hidden_dim)

Solution

1. Step 1: Identify correct PyTorch layer for encoding

   Encoding usually uses a linear layer to reduce dimensions: nn.Linear(input_dim, hidden_dim).

2. Step 2: Check other options for correctness

   Conv2d requires 4D input and different parameters; ReLU is an activation, not a layer; MaxPool2d is for downsampling images, not linear encoding.

3. Final Answer:

   self.encoder = nn.Linear(input_dim, hidden_dim) -> Option A

4. Quick Check:

   Linear layer for encoding = B [OK]

Hint: Use nn.Linear for encoder layers in simple autoencoders [OK]

Common Mistakes:

• Using activation functions as layers
• Confusing convolution with linear layers
• Wrong parameter order in layers

3. Given this PyTorch autoencoder snippet, what is the shape of the output tensor after encoding if input shape is (batch_size=10, features=784)?

class Autoencoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.encoder = nn.Linear(784, 32)
    def forward(self, x):
        x = self.encoder(x)
        return x
model = Autoencoder()
input_tensor = torch.randn(10, 784)
output = model(input_tensor)

medium

A. (784, 32)

B. (10, 32)

C. (10, 784)

D. (32, 784)

Solution

1. Step 1: Understand input and encoder layer

   Input tensor shape is (10, 784). Encoder is nn.Linear(784, 32), so it maps 784 features to 32 features per sample.

2. Step 2: Calculate output shape after encoder

   Output shape keeps batch size 10, features become 32, so output shape is (10, 32).

3. Final Answer:

   (10, 32) -> Option B

4. Quick Check:

   Batch size unchanged, features to 32 = D [OK]

Hint: Linear layer output shape = (batch_size, output_features) [OK]

Common Mistakes:

• Swapping batch size and feature dimensions
• Confusing input and output feature sizes
• Assuming shape changes batch size

4. Identify the error in this autoencoder decoder definition:

class Decoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.decoder = nn.Linear(32, 784)
    def forward(self, x):
        x = self.decoder(x)
        x = nn.ReLU(x)
        return x

medium

A. Missing activation function after linear layer

B. The decoder input and output dimensions are swapped

C. nn.ReLU is used incorrectly as a function instead of a layer

D. The forward method should return x before applying ReLU

Solution

1. Step 1: Check usage of nn.ReLU

   nn.ReLU is a class and must be instantiated before use, e.g. nn.ReLU()(x), not nn.ReLU(x).

2. Step 2: Verify decoder dimensions and flow

   Decoder maps 32 to 784 correctly, and activation after linear is common, so no issue there.

3. Final Answer:

   nn.ReLU is used incorrectly as a function instead of a layer -> Option C

4. Quick Check:

   Activation must be instantiated = C [OK]

Hint: Instantiate nn.ReLU() before calling it on tensor [OK]

Common Mistakes:

• Calling nn.ReLU as a function directly
• Swapping input/output dims in Linear
• Forgetting to apply activation

5. You want to build an autoencoder that compresses 1000-dimensional input to 10 dimensions and then reconstructs it. Which architecture below correctly defines encoder and decoder layers in PyTorch?

hard

A. ""class Autoencoder(nn.Module):
def __init__(self):
super().__init__()
self.encoder = nn.Sequential(
nn.Linear(1000, 100),
nn.ReLU(),
nn.Linear(100, 10)
)
self.decoder = nn.Sequential(
nn.Linear(10, 100),
nn.ReLU(),
nn.Linear(100, 1000),
nn.Sigmoid()
)
def forward(self, x):
x = self.encoder(x)
x = self.decoder(x)
return x"""

B. ""class Autoencoder(nn.Module):
def __init__(self):
super().__init__()
self.encoder = nn.Sequential(
nn.Linear(10, 100),
nn.ReLU(),
nn.Linear(100, 1000)
)
self.decoder = nn.Sequential(
nn.Linear(1000, 100),
nn.ReLU(),
nn.Linear(100, 10)
)
def forward(self, x):
x = self.encoder(x)
x = self.decoder(x)
return x"""

C. ""class Autoencoder(nn.Module):
def __init__(self):
super().__init__()
self.encoder = nn.Sequential(
nn.Linear(1000, 20),
nn.ReLU()
)
self.decoder = nn.Sequential(
nn.Linear(20, 1000),
nn.Sigmoid()
)
def forward(self, x):
x = self.encoder(x)
x = self.decoder(x)
return x"""

D. ""class Autoencoder(nn.Module):
def __init__(self):
super().__init__()
self.encoder = nn.Sequential(
nn.Linear(1000, 500),
nn.ReLU(),
nn.Linear(500, 50)
)
self.decoder = nn.Sequential(
nn.Linear(50, 500),
nn.ReLU(),
nn.Linear(500, 1000),
nn.Sigmoid()
)
def forward(self, x):
x = self.encoder(x)
x = self.decoder(x)
return x"""

Solution

1. Step 1: Check encoder input and output sizes

   Input is 1000, compressed to 10. ""class Autoencoder(nn.Module): def __init__(self): super().__init__() self.encoder = nn.Sequential( nn.Linear(1000, 100), nn.ReLU(), nn.Linear(100, 10) ) self.decoder = nn.Sequential( nn.Linear(10, 100), nn.ReLU(), nn.Linear(100, 1000), nn.Sigmoid() ) def forward(self, x): x = self.encoder(x) x = self.decoder(x) return x""" correctly reduces 1000 -> 100 -> 10. Others have wrong input/output sizes.

2. Step 2: Check decoder mirrors encoder

   Decoder in A expands 10 -> 100 -> 1000, matching encoder compression steps. ""class Autoencoder(nn.Module): def __init__(self): super().__init__() self.encoder = nn.Sequential( nn.Linear(1000, 500), nn.ReLU(), nn.Linear(500, 50) ) self.decoder = nn.Sequential( nn.Linear(50, 500), nn.ReLU(), nn.Linear(500, 1000), nn.Sigmoid() ) def forward(self, x): x = self.encoder(x) x = self.decoder(x) return x""" has wrong final layer input size (50 to 1000 is correct, but encoder compresses to 50, not 10). Options B and C have reversed or incorrect sizes.

3. Final Answer:

   Option A correctly defines encoder and decoder layers for 1000 to 10 compression and reconstruction -> Option A

4. Quick Check:

   Encoder compresses 1000 to 10, decoder reverses = A [OK]

Hint: Encoder reduces dims stepwise; decoder reverses steps [OK]

Common Mistakes:

• Swapping input/output sizes in layers
• Skipping intermediate compression layers
• Mismatching encoder and decoder sizes