Installation of SDK on Windows
This section describes how to install Metavision SDK on Windows 10 64-bit.
Metavision SDK comes as pre-built Windows installer of our whole software offer including the Prophesee Camera Plugins. It does not require compilation and installation of OpenEB. The quickest way to begin working with Prophesee technology is to install Metavision Studio only. Follow the guide on the Installation of Studio To install the open source project, OpenEB, follow the specific guide on the Installation of OpenEB.
Table of Contents
Please note the base system requirements for using Metavision:
Operating system: Windows 10 64-bit
Architecture: amd64 (a.k.a. x64)
Graphic card: must support OpenGL 3.0 minimum
CPU: must support AVX2
For the Linux installation, see the page SDK installation on Linux. For other operating systems and architectures, you must clone our open source project OpenEB and contact us if you run into compatibility issues.
First of all, read carefully the Release Notes as some changes may impact your usage of our SDK (e.g. API updates) and cameras (e.g. firmware update might be necessary).
Then, if you have previously installed any Prophesee’s software, you will need to uninstall it first:
Make sure that no Prophesee or Metavision software is running
Open the Start menu
Search for Apps & features via the search
In the list of installed programs, find any Prophesee or Metavision software and click the Uninstall button
Check that there is no
Propheseefolder left in your
Program Filesfolder (if still present, delete it)
Removing the old version of Metavision SDK is mandatory even for patch upgrade (e.g. from 2.2.0 to 2.2.1)
Install Python (version 3.7 or 3.8), if not yet available on your machine:
Download “Windows x86-64 executable installer” for one of these Python versions:
Run the installer and follow the prompt
We advise you to check the box to update the
PATHor update the
PATHmanually with the following paths after replacing the Username to your own and using the Python version you installed (here, we assume that the install is limited to the local user and the default install path was used):
Then, install required Python libraries using pip. Open a command prompt and run the command:
python -m pip install pip --upgrade python -m pip install "opencv-python>=18.104.22.168" "sk-video==1.1.10" "fire==0.4.0" "numpy<=1.21" pandas scipy h5py python -m pip install jupyter jupyterlab matplotlib "ipywidgets==7.6.5"
You can use anaconda to install Python and
conda to manage your Python packages, but be sure to use a Python version that we support.
You will need to adapt the library installation steps accordingly and use
conda whenever we use
In this documentation, we chose to use pip as a package manager.
We recommend using it with virtualenv to avoid conflicts with other installed Python packages.
Finally, install FFMPEG library which is required to write videos:
bindirectory to your
If not yet done, sign-up page Metavision SDK, then:
Follow the link to download the Metavision SDK Windows installer
Among the list of SDK installers (
Metavision_SDK_xyz_Setup.exe), download the one with highest version number
You can safely ignore other files (e.g.
Metavision_Studio_xyz_Setup.exe) as SDK installer contains everything you need
Run the SDK installer
For a given minor release of Metavision Intelligence (e.g. 2.3), all the patch versions (e.g. 2.3.0 and 2.3.1) are available in the file repository link your sign-up gave you access to.
If you want to install an old minor version of Metavision Intelligence (e.g. 2.2), you need the file repository link corresponding to that version. If you don’t have it, you will have to go through the sign-up page of the given version (links for previous minor versions: 2.1, 2.2 and 2.3). Then you should follow the installation guide of this version.
Machine Learning Module Dependencies
To use Machine Learning features, you need to install some additional dependencies. If you have some Nvidia hardware with GPUs, install CUDA (10.2, 11.1 or 11.3) and cuDNN to leverage them with pytorch and libtorch. Make sure that you install a version of CUDA that is compatible with your GPUs by checking Nvidia compatibility page.
At the moment, we don’t support OpenCL and AMD GPUs.
Packages for Python
Metavision ML requires pytorch. Go to pytorch.org to retrieve the pip command for the installation of PyTorch 1.8.2 LTS:
Metavision ML has additional Python requirements that can be installed with pip:
python -m pip install numba llvmlite profilehooks "pytorch_lightning==1.5.10" python -m pip install "pycocotools==2.0.4" "tqdm==4.63.0" python -m pip install "torchmetrics==0.7.2" "seaborn==0.11.2" "kornia==0.6.1"
LibTorch for C++
To compile and run the neural network inference in a C++ pipeline, you need LibTorch (PyTorch’s C++ frontend)
Download the LibTorch version corresponding to your CUDA version (or take the CPU version if you don’t have CUDA):
Unzip the archive to a new folder LIBTORCH_DIR_PATH that you will reference when compiling the C++ inference sample.
You are now ready to use Metavision Intelligence. The best way to start getting familiar with the event-based technology is to open an event-based camera with Metavision Studio to begin data collection and visualization. You can choose to dive directly in the SDK by following a Tutorial or looking at a Code Sample.
When running some Metavision Intelligence applications, you may get the following error message: “Entry Point Not Found. The procedure entry point inflateValidate could not be located in the dynamic link library C:\Program Files\Prophesee\bin\libpng16.dll.” In this case, please check out the Troubleshooting section of our FAQ to fix the issue.