Cat(G)AN
Implemented a Generative Adversarial Network (GAN) with 3.5 million parameters from scratch in NumPy, TensorFlow, and Keras to generate cat images.
Cat(G)AN is a Generative Adversarial Network (GAN) with 3.5 million parameters, implemented from scratch in NumPy, TensorFlow, and Keras. The model is trained to generate realistic cat images and includes custom data pipelines and visualization tools.