learnopencv/Image-to-Image-Translation-with-GAN

Pix2Pix: Image-to-Image Translation with GAN in PyTorch & TensorFlow

This repository contains code for Pix2Pix: Image-to-Image Translation with GAN in PyTorch & TensorFlow blogpost.

Package Dependencies

The repository trains the Pix2Pix GAN in both Pytorch and Tensorflow on the Edges2Shoes dataset. It is tested with:

• Cuda-11.1
• Cudnn-8.0

The Pytorch and Tensorflow scripts require numpy, tensorflow, 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 

Directory Structure

├── PyTorch
│   ├── torch
│   │   ├── images
│   │   └── training_weights
│   ├── pix2pix_pytorch.ipynb
│   └── pix2pix_pytorch.py
├── TensorFlow
│   ├── model_single
│   ├── results_images_single
│   ├── pix2pix-tensorflow-multi_gpu.py
│   ├── pix2pix-tensorflow_single_gpu.ipynb
│   └── pix2pix-tensorflow-single_gpu.py

Instructions

PyTorch

To train the Pix2Pix GAN with Pytorch, please go into the PyTorch folder and execute the Jupyter Notebook.

TensorFlow

To train the Pix2Pix GAN with TensorFlow, please go into the TensorFlow folder and execute the Jupyter Notebook.

AI Courses by OpenCV

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