Autoencoder architecture in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - Autoencoder architecture

Which metric matters for Autoencoder architecture and WHY

Autoencoders learn to copy input data to output. The key metric is Reconstruction Loss. It measures how close the output is to the input. Lower loss means the model is better at capturing important features.

Common losses are Mean Squared Error (MSE) or Binary Cross-Entropy (BCE) depending on data type. Accuracy is not used because autoencoders do not classify but reconstruct.

Confusion matrix or equivalent visualization

Autoencoders do not use confusion matrices because they are not classifiers. Instead, we look at reconstruction error per sample.

Sample 1: Input = [0.1, 0.5, 0.3], Output = [0.12, 0.48, 0.29], MSE = 0.0009
Sample 2: Input = [0.9, 0.2, 0.7], Output = [0.85, 0.25, 0.72], MSE = 0.0025
...
    

Plotting reconstruction loss distribution helps see if model learns well or struggles on some inputs.

Precision vs Recall tradeoff equivalent

Autoencoders balance compression and reconstruction quality. A smaller latent space compresses data more but may lose details, increasing reconstruction loss.

Think of it like packing a suitcase: packing tightly saves space (compression) but may wrinkle clothes (loss). Packing loosely keeps clothes neat but uses more space.

Choosing latent size is a tradeoff: too small hurts reconstruction, too large wastes resources.

What "good" vs "bad" metric values look like

Good: Low reconstruction loss close to zero, meaning output is very similar to input. Loss decreases steadily during training.

Bad: High or constant reconstruction loss, meaning model fails to learn meaningful features. Loss may jump or not improve.

Example: MSE loss dropping from 0.1 to 0.001 is good. Staying around 0.1 means bad.

Common pitfalls in metrics for Autoencoders

• Ignoring reconstruction loss type: Using wrong loss (e.g., MSE for binary data) can mislead training.
• Overfitting: Very low training loss but high validation loss means model memorizes data, not generalizes.
• Data leakage: Using test data in training inflates performance falsely.
• Ignoring latent space size: Too large latent space can trivially copy input, hiding poor feature learning.

Self-check question

Your autoencoder has a training reconstruction loss of 0.001 but validation loss of 0.1. Is it good?

Answer: No. The big gap means overfitting. The model memorizes training data but fails to generalize to new data. You should try regularization, more data, or smaller latent space.

Key Result

Reconstruction loss (e.g., MSE) is key to evaluate how well an autoencoder learns to compress and reconstruct data.

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