This repository This repository contains code for Conditional GAN in TensorFlow and PyTorch blogpost.

This repository trains Conditional GANs in both PyTorch and TensorFlow on the Fashion-MNIST and Rock-Paper-Scissors datasets. The current requirements have been validated with Python 3.12.x.

python3 -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install -r requirements.txt

The PyTorch script now falls back to CPU automatically when the installed CUDA build does not support the available GPU.

├── PyTorch
│   ├── CGAN-PyTorch.ipynb
│   └── cgan_pytorch.py
└── TensorFlow
    ├── CGAN-FashionMnist-TensorFlow.ipynb
    ├── cgan_fashionmnist_tensorflow.py
    ├── CGAN-RockPaperScissor-TensorFlow.ipynb
    └── cgan_rockpaperscissor_tensorflow.py

To train the Conditional GAN with PyTorch, go into the PyTorch folder and execute either the Python script or the notebook.

To train the Conditional GAN with TensorFlow, go into the TensorFlow folder and execute the notebook or script.

Want to become an expert in AI? AI Courses by OpenCV is a great place to start.