Why generative models create data in PyTorch - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Purpose of Generative Models

Why do generative models create new data samples?

A To learn the underlying data distribution and generate similar new examples

B To reduce the size of the dataset by compressing data

C To classify data into predefined categories

D To remove noise from existing data samples

💡 Hint

Think about what it means to 'generate' data in machine learning.

Generative models learn the patterns and structure of the original data so they can create new, similar data points. This is different from classification or compression.

❓ Model Choice

intermediate

Choosing a Generative Model for Image Creation

Which model is best suited to generate new images similar to a training set?

A Convolutional Neural Network (CNN) for classification

B Generative Adversarial Network (GAN)

C Recurrent Neural Network (RNN) for sequence prediction

D Support Vector Machine (SVM)

💡 Hint

Look for a model designed to create new data, not just analyze or classify.

GANs are designed to generate new data samples, especially images, by learning the data distribution through a generator and discriminator.

❓ Predict Output

advanced

Output Shape of Generated Data

What is the shape of the output tensor from the generator in this PyTorch GAN code snippet?

PyTorch

import torch
import torch.nn as nn

class Generator(nn.Module):
    def __init__(self):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(100, 256),
            nn.ReLU(),
            nn.Linear(256, 784),
            nn.Tanh()
        )
    def forward(self, x):
        return self.net(x)

g = Generator()
noise = torch.randn(16, 100)
output = g(noise)
output_shape = output.shape

A torch.Size([16, 784])

B torch.Size([100, 16])

C torch.Size([16, 256])

D torch.Size([784, 16])

💡 Hint

Check the input batch size and the final layer output size.

The input noise has shape (16, 100). The generator outputs a tensor with shape (batch_size, 784), so (16, 784).

❓ Metrics

advanced

Evaluating Generative Model Quality

Which metric is commonly used to evaluate the quality of images generated by a GAN?

A Accuracy

B Mean Squared Error (MSE)

C Inception Score (IS)

D Cross-Entropy Loss

💡 Hint

This metric measures how realistic and diverse generated images are.

Inception Score evaluates both the quality and diversity of generated images by using a pretrained classifier.

🔧 Debug

expert

Identifying the Cause of Mode Collapse in GAN Training

During GAN training, the generator produces very similar images repeatedly, showing mode collapse. What is the most likely cause?

A The discriminator is too weak and cannot distinguish real from fake images

B The generator's learning rate is too low, causing slow updates

C The generator is overfitting the training data

D The discriminator is too strong, overpowering the generator

💡 Hint

Mode collapse often happens when one part of the GAN dominates the other.

If the discriminator is too strong, the generator struggles to improve and collapses to producing limited outputs.