Image generation basics in PyTorch

Introduction

Image generation helps computers create new pictures from scratch. It is useful for art, design, and learning how images work.

Creating new artwork or designs automatically.

Generating images for games or virtual worlds.

Helping computers understand how images are made.

Making variations of photos for data augmentation.

Building fun apps that draw pictures from text or noise.

Syntax

PyTorch

import torch
import torch.nn as nn

class SimpleGenerator(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(SimpleGenerator, self).__init__()
        self.model = nn.Sequential(
            nn.Linear(input_dim, 128),
            nn.ReLU(),
            nn.Linear(128, 256),
            nn.ReLU(),
            nn.Linear(256, output_dim),
            nn.Tanh()
        )

    def forward(self, x):
        return self.model(x)

The generator takes random noise as input and creates an image-like output.

Use nn.Tanh() at the end to keep output values between -1 and 1, which is common for images.

Examples

Create a random noise vector of size 100, then generate a fake 28x28 image flattened to 784 pixels.

PyTorch

noise = torch.randn(1, 100)
generator = SimpleGenerator(100, 784)  # 28x28 image flattened
fake_image = generator(noise)

Generate a batch of 16 fake images at once from random noise.

PyTorch

batch_noise = torch.randn(16, 100)
fake_images = generator(batch_noise)

Sample Model

This program creates a simple generator model that turns random noise into a fake 28x28 image. It prints the shape and pixel value range of the generated image.

PyTorch

import torch
import torch.nn as nn

class SimpleGenerator(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(SimpleGenerator, self).__init__()
        self.model = nn.Sequential(
            nn.Linear(input_dim, 128),
            nn.ReLU(),
            nn.Linear(128, 256),
            nn.ReLU(),
            nn.Linear(256, output_dim),
            nn.Tanh()
        )

    def forward(self, x):
        return self.model(x)

# Set random seed for reproducibility
torch.manual_seed(42)

# Create generator instance
input_dim = 100
output_dim = 28 * 28  # 784 pixels for 28x28 image
generator = SimpleGenerator(input_dim, output_dim)

# Generate one fake image
noise = torch.randn(1, input_dim)
fake_image = generator(noise)

# Check output shape and value range
print(f"Fake image shape: {fake_image.shape}")
print(f"Min pixel value: {fake_image.min().item():.4f}")
print(f"Max pixel value: {fake_image.max().item():.4f}")

Important Notes

Image generation models often start from random noise to create new images.

Output values are usually scaled between -1 and 1 for easier training and normalization.

This example is very simple; real image generators use more layers and special blocks like convolution.

Summary

Image generation creates new pictures from random inputs.

Generators are neural networks that learn to make images from noise.

Output images are often flattened and scaled between -1 and 1.

Practice

1. What is the main role of a generator in image generation using PyTorch?

easy

A. To create new images from random noise

B. To classify images into categories

C. To reduce the size of images

D. To label images with tags

Solution

1. Step 1: Understand the generator's purpose

   A generator is a neural network designed to produce new data, often images, from random noise inputs.

2. Step 2: Differentiate from other network roles

   Unlike classifiers or reducers, generators focus on creating new images, not labeling or compressing them.

3. Final Answer:

   To create new images from random noise -> Option A

4. Quick Check:

   Generator = create images from noise [OK]

Hint: Generators make images from noise, not classify or compress [OK]

Common Mistakes:

• Confusing generator with classifier
• Thinking generator reduces image size
• Assuming generator labels images

2. Which PyTorch code snippet correctly initializes a noise tensor for image generation?

easy

A. noise = torch.randn(16, 100)

B. noise = torch.zeros(16, 100)

C. noise = torch.ones(16, 100)

D. noise = torch.randint(0, 1, (16, 100))

Solution

1. Step 1: Identify noise initialization for generators

   Generators typically use random noise from a normal distribution, which torch.randn provides.

2. Step 2: Check other options

   Zeros or ones do not provide randomness; randint with 0 to 1 range is invalid as upper bound is exclusive.

3. Final Answer:

   noise = torch.randn(16, 100) -> Option A

4. Quick Check:

   Random normal noise = torch.randn [OK]

Hint: Use torch.randn for random normal noise input [OK]

Common Mistakes:

• Using zeros or ones instead of random noise
• Incorrect use of torch.randint with invalid range
• Confusing noise shape dimensions

3. Given this PyTorch generator output code, what is the shape of the generated images?

import torch
noise = torch.randn(8, 100)
generator = torch.nn.Sequential(
    torch.nn.Linear(100, 256),
    torch.nn.ReLU(),
    torch.nn.Linear(256, 784),
    torch.nn.Tanh()
)
fake_images = generator(noise)

medium

A. (8, 28, 28)

B. (100, 256)

C. (8, 784)

D. (256, 784)

Solution

1. Step 1: Trace the generator output shape

   The last Linear layer outputs 784 features per input, so for batch size 8, output shape is (8, 784).

2. Step 2: Understand image reshaping

   784 corresponds to 28x28 pixels flattened; reshaping to (8, 28, 28) is done later, not shown here.

3. Final Answer:

   (8, 784) -> Option C

4. Quick Check:

   Output shape = (batch_size, 784) [OK]

Hint: Output shape matches last Linear layer output size [OK]

Common Mistakes:

• Assuming output is already 2D image shape
• Confusing input noise shape with output
• Mixing intermediate layer shapes

4. Identify the error in this PyTorch generator code snippet:

import torch
class Generator(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = torch.nn.Linear(100, 784)
    def forward(self, x):
        x = self.fc(x)
        x = torch.sigmoid(x)
        return x
noise = torch.randn(16, 100)
gen = Generator()
output = gen(noise).reshape(16, 28, 28)

medium

A. Missing batch normalization layers

B. Not calling super().__init__() in constructor

C. Incorrect reshape dimensions for output

D. Using sigmoid activation instead of tanh

Solution

1. Step 1: Check activation function for image generation

   Image generation often uses tanh to scale outputs between -1 and 1, matching normalized image data.

2. Step 2: Analyze impact of sigmoid

   Sigmoid outputs between 0 and 1, which may mismatch expected scaling and reduce image quality.

3. Final Answer:

   Using sigmoid activation instead of tanh -> Option D

4. Quick Check:

   Activation should be tanh, not sigmoid [OK]

Hint: Use tanh for output scaling in image generation [OK]

Common Mistakes:

• Thinking reshape dimensions are wrong
• Believing batch norm is mandatory here
• Forgetting to call super().__init__()

5. You want to generate 64 images of size 32x32 with pixel values scaled between -1 and 1 using a PyTorch generator. Which output layer and activation setup is best?

hard

A. Linear layer with 1024 outputs followed by sigmoid activation

B. Linear layer with 1024 outputs followed by tanh activation

C. Linear layer with 1024 outputs followed by ReLU activation

D. Linear layer with 1024 outputs followed by softmax activation

Solution

1. Step 1: Calculate output size for 32x32 images

   32x32 = 1024 pixels, so output layer must have 1024 units to represent each pixel.

2. Step 2: Choose activation for scaling pixel values

   Tanh activation scales outputs between -1 and 1, matching the desired pixel value range.

3. Step 3: Evaluate other activations

   Sigmoid outputs 0 to 1, ReLU outputs 0 to infinity, softmax is for classification, so they are unsuitable here.

4. Final Answer:

   Linear layer with 1024 outputs followed by tanh activation -> Option B

5. Quick Check:

   Output size 1024 + tanh for [-1,1] scaling [OK]

Hint: Use tanh activation for output scaled between -1 and 1 [OK]

Common Mistakes:

• Using sigmoid instead of tanh for output scaling
• Choosing softmax for image pixel output
• Ignoring correct output size for image dimensions