https://github.com/gazeux33/generative-adversial-network

Implementation of a WGAN-GP on the CelebA dataset with PyTorch for face generation
https://github.com/gazeux33/generative-adversial-network

ai deep-learning face-generation gan

Last synced: 19 days ago
JSON representation

Implementation of a WGAN-GP on the CelebA dataset with PyTorch for face generation

• Host: GitHub
• URL: https://github.com/gazeux33/generative-adversial-network
• Owner: Gazeux33
• Created: 2024-06-05T19:32:00.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-07-10T14:54:55.000Z (6 months ago)
• Last Synced: 2024-07-10T17:49:30.080Z (6 months ago)
• Topics: ai, deep-learning, face-generation, gan
• Language: Jupyter Notebook
• Homepage:
• Size: 29 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Generative Adversial Network (WGAN-GP)

This project is an impletation of a WGAN-GP on the datatset CelebA with PyTorch.



 

 


 ## What is GANs ?

### Generator

The role of the **Generator** is to create images that appear realistic enough to fool the Critic.

- **Objective**: Produce images that mimic the original dataset.

- **Functioning**: It takes a random noise vector and transforms it into an image.

- **Expected Outcome**: That the Critic cannot distinguish the generated images from those actually from the dataset.

### Critic (or Discriminator)

The **Critic**'s task is to differentiate generated images from real images from the dataset.

- **Objective**: Correctly identify whether an image is generated by the Generator or is from the original dataset.

- **Functioning**: It evaluates images one by one and delivers its verdict.

- **Expected Outcome**: Maximize its ability to make the correct distinction.

## How to train a GAN ?



 

 


 ## Technical specifications

 | Property       | Value         |

|----------------|---------------|

| Device         | MAC M2        |

| Training Time  | 15 hours      |

| Epochs         | 15            |

| Training Data  | CelebA        |

| Framework      | PyTorch       |

| Learning rate  | 0.0002        |

|Z_DIM           |128            |

|BATCH_SIZE      |128            |

|Images size     |(64,64)        |

|LAMBDA          |10             |

|N_CRITIC        |4              |

|Optimizer       |Adam           |

 ## How to improve this model ?

 This model is not perfect and to improve it we need to consolidate its architecture and increase the number of epochs.