Image generation basics in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main goal of image generation in machine learning?

The main goal is to create new images that look realistic or meaningful, often by learning patterns from a set of example images.

intermediate

What is a Generative Adversarial Network (GAN)?

A GAN is a type of model with two parts: a generator that creates images and a discriminator that tries to tell real images from fake ones. They learn together to improve image quality.

intermediate

In PyTorch, which function is commonly used to initialize the weights of a neural network for image generation?

The functions torch.nn.init.normal_ or torch.nn.init.xavier_uniform_ are commonly used to initialize weights to help the model learn better.

beginner

What does the 'latent vector' mean in image generation?

A latent vector is a set of numbers that the generator uses as a starting point to create an image. Changing this vector changes the generated image.

beginner

Why do we use a loss function in training image generation models?

A loss function measures how different the generated images are from real images or desired outputs. It guides the model to improve by reducing this difference.

What are the two main parts of a GAN?

A Generator and Discriminator

B Encoder and Decoder

C Input and Output

D Feature Extractor and Classifier

A GAN consists of a Generator that creates images and a Discriminator that evaluates them.

What does a latent vector represent in image generation?

A A starting point of numbers to generate images

B The final output image

C The loss value during training

D The label of an image

The latent vector is the input to the generator that determines the generated image.

Which PyTorch module is typically used to build the generator network?

A torch.optim.Adam

B torch.nn.CrossEntropyLoss

C torch.utils.data.DataLoader

D torch.nn.Sequential

torch.nn.Sequential helps stack layers to build the generator network.

Why do GANs train the generator and discriminator together?

A To speed up data loading

B To reduce the size of the model

C To improve the generator's image quality by competing with the discriminator

D To increase the number of training images

The generator learns to fool the discriminator, improving image realism.

What is the purpose of the loss function in image generation?

A To display images on screen

B To measure how close generated images are to real images

C To initialize model weights

D To load images from disk

The loss function guides the model to generate better images by measuring errors.

Explain how a Generative Adversarial Network (GAN) works for image generation.

Think of a game where one player makes fake images and the other tries to spot fakes.

Describe the role of the latent vector in generating images.

It's like a secret code that decides what the picture looks like.