/VisualAtom.jl

Generate the VisualAtom dataset using JuliaLang (within an hour).

Primary LanguageJuliaMIT LicenseMIT

VisualAtom.jl Build Status

⚠️ This implementation is unofficial.

Description

This repository contains Julia implementation of visual_atomic_renderer/render_VisualAtom.py, originally implemented in Python. The original Python implementation can be found at masora1030/CVPR2023-FDSL-on-VisualAtom

Getting Started

Prerequisites

To use this Julia implementation, you will need:

Installation

  1. Clone this repository:
$ git clone https://github.com/AtelierArith/VisualAtom.jl.git
  1. Change directory into the repository:
$ cd VisualAtom.jl
  1. Install the required Julia packages:
$ julia --project=@. -e 'import Pkg; Pkg.instantiate()'
  Activating project at `~/work/atelier_arith/VisualAtom.jl`
Precompiling project...
  Progress [>                                        ]  0/1
  ◓ VisualAtom

Usage

⚠️ Make sure you have enough storage space (200GB).⚠️

Easy! Just run:

$ julia --project=@. --procs auto run.jl

It will create a directory VisualAtom_dataset by default and 1000 * 1000 images will be generated.

image

The following screenshot was captured while running on iMac 2019 with --procs 16.

If you are surprised by these results, you may want to consider moving from Python to Julia.

Tips

--procs {N|auto} Integer value N launches N additional local worker processes "auto" launches as many workers as the number of local CPU threads (logical cores)

Another easy shortcut

Having trouble installing Julia? You can save yourself the trouble of installation by using a Docker container.

$ make && docker compose run --rm shell julia -p auto run.jl

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgments