Introduction to Generative Adversarial Network in TensorFlow and PyTorch

Package Dependencies

This repository trains the Generative Adversarial Network in both Pytorch and Tensorflow on Fashion-MNIST dataset. It is tested with:

• Cuda-11.1
• Cudnn-8.0

The Pytorch and Tensorflow scripts require numpy, tf-nightly-gpu, torch. To get the versions of these packages you need for the program, use pip: (Make sure pip is upgraded: python3 -m pip install -U pip)

pip3 install -r requirements.txt 

Instructions

PyTorch

To train the Generative Adversarial Network with Pytorch, please go into the Pytorch folder and execute either the Python script or the Jupyter Notebook.

TensorFlow

To train the Generative Adversarial Network with TensorFlow, please go into the Tensorflow folder and execute either the Python script or the Jupyter Notebook.

AI Courses by OpenCV

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