Skip to content

Virtual-Humans-Lab/VisionCrowds

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

49 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Where do we look to survive?

Requirements

  • Unity 2021.3.8f1
  • Python 3.6.8 &
  • CUDA 10
  • cuDNN 7.4

Instructions

Clone the main project from GitHub

git clone https://github.com/Virtual-Humans-Lab/VisionCrowds

Install CUDA 10 from here - Make sure to choose “Custom Installation” and deselect any other options except the actual CUDA drivers.

Download cuDNN 7.4 for CUDA 10 from here

After downloading, extract it to path C:\tools\cuda

Add all necessary references from CUDA and cuDNN to PATH (as explained here - it’s in portuguese because the original english page does not exist anymore)

SET PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\bin;%PATH%
SET PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\extras\CUPTI\lib64;%PATH%
SET PATH=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\include;%PATH%
SET PATH=C:\tools\cuda\bin;%PATH%

Install Python dependencies:

pip install tensorflow-gpu==1.13.1
pip install matplotlib==3.0.3
pip install requests==2.21.0
pip install gdown==4.6.3
pip install scipy==1.4.1
pip install zmq

OR

pip install -r Assets/PythonServer/requirements.txt

Install OpenCV for Python as explained here in the session “Installing OpenCV from prebuilt binaries”.

Prior to running the project in Unity, start the Python server in a separate terminal:

python Assets/PythonServer/main.py

About

Project for experimenting with BioCrowds and Vision

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors