sokharsamb / LeicaGAN

Reproduicing the paper : learn-imagine-and-create-text-to-image-generation-from-prior-knowledge.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

LeicaGAN

Pytorch re-implementation for Paper [Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge] by Tingting Qiao, Jing Zhang, Duanqing Xu, Dacheng Tao. (The work was performed when Tingting Qiao was a visiting student at UBTECH Sydney AI Centre in the School of Computer Science, FEIT, the University of Sydney).

The official (original) repository of the paper can be found here.

This repository contains an effort of some student(See list below) of the African Master in Machine INtelligence (https://aimsammi.org/) to reproduice the paper.

Project Overview

The LeicaGAN framework is a follow :

LeicaGAN framework

Instructions

  1. Clone the repository and navigate to the downloaded folder.

    	git clone https://github.com/Kabongosalomon/LeicaGAN.git
    	cd LeicaGAN
    
  2. Download the CUB bird dataset.

CUB bird dataset

  1. Download the Oxford flower dataset.

Oxford flower dataset

About

Reproduicing the paper : learn-imagine-and-create-text-to-image-generation-from-prior-knowledge.

License:MIT License


Languages

Language:Python 72.9%Language:Shell 27.1%