[Neural_SDFs tutorial]

1.Turn on Virtualization Technology in BIOS.


2.Under "Enable or disable Windows features", check "Hyper-V".
3.Check "Windows Subsystem for Linux" and "Virtual Machine Platform" as well.


4.Update to Windows 10 version 21H2 or later.


5.Make sure your Nvidia drivers are up to date. (GameReady available).
https://www.nvidia.co.jp/Download/index.aspx

Install the Linux Kernel Update Package
https://wslstorestorage.blob.core.windows.net/wslblob/wsl_update_x64.msi

Run Windows Terminal or PowerShell as administrator and execute the following command

dism.exe /online /enable-feature /featurename:Microsoft-Windows-Subsystem-Linux /all /norestart

dism.exe /online /enable-feature /featurename:VirtualMachinePlatform /all /norestart

wsl --set-default-version 2

Open the Microsoft Store and install "Ubuntu 20.04 LTS".

wsl --set-version Ubuntu-20.04 2
wsl -l -v

Will Install the necessary programs in ubuntu

sudo apt -y update
sudo apt -yV upgrade

wsl --install -d Ubuntu-20.04

curl https://get.docker.com | sh

distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
curl -s -L https://nvidia.github.io/libnvidia-container/experimental/$distribution/libnvidia-container-experimental.list | sudo tee /etc/apt/sources.list.d/libnvidia-container-experimental.list
sudo apt-get update
sudo apt-get install -y nvidia-docker2
sudo service docker start

sudo docker run --gpus all nvcr.io/nvidia/k8s/cuda-sample:nbody nbody -gpu -benchmark

Continue to install the necessary programs within ubuntu.

sudo apt -y install build-essential python3-dev python3-pip

pip install -U pip

pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html

pip install numpy
pip install pandas
pip install matplotlib
pip install scikit-image
pip3 install mesh-to-sdf

sudo apt-get install libglu1-mesa-dev mesa-common-dev

sudo pip3 install jupyterlab

sudo wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb
sudo dpkg -i google-chrome-stable_current_amd64.deb
sudo apt install --fix-broken -y

DL and install MobaXterm in order to run ubuntu GUI on windows.
Press Download now for the Free version to install it.
https://mobaxterm.mobatek.net/download.html

When the screen opens, the setup is complete.

※Possible with VcXsrv

Open the ubuntu console by double-clicking on it.
Download the neural_experiments project from Blackle Mori's googleDrive, unzip it, and copy it to your ubuntu folder.
https://drive.google.com/drive/folders/13-ks7iyLyI0vcS38xq1eeFdaMdfNlUC8

Open two ubumtu consoles and start the program

sudo service docker start 
google-chrome

jupyter-notebook

Paste the URL listed in the jupyter-notebook into the google-chrome URL launched from ubuntu.


The ubuntu folder will appear, click on sdf.ipynb to open it.


You can do this by clicking on the Is[n] part and pressing RUN as explained in the video.


※Note: The line serialize_to_shadertoy(sdf_siren, "f") here must be removed or an error will occur.


If all goes well, you will get the results from here, and you can check them by pasting them into shadertoy.




In the project folder, you will also find sad_cat, a cat image, and a sample distance function that includes colors. This method has a wide range of applications, so you can use it to create distance functions for waveforms, convert 2D images, or process them with post-processing shaders.