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 Plugin. It does not require compilation and installation of our open source project OpenEB. Though if you want to work from source, you should use OpenEB and follow the specific guide on the Installation of OpenEB.
Table of Contents
Before following this installation guide, you may want to watch our EVK4 unboxing video as it includes an overview of the installation of Metavision SDK on Windows along the first steps with the EVK.
If you want to use a Prophesee EVK that is not in the list above, it might have been discontinued. Refer to the Prophesee EVKs Support section to find out which previous version of the SDK is supporting it.
If you own a third-party vendor event-based camera, refer to the Camera Plugin Installation page to see how it can be deployed and configured.
Please note the base system requirements for using Metavision SDK:
Operating system: Windows 10 64-bit
Architecture: amd64 (a.k.a. x64)
Graphic card: must support OpenGL 3.0 minimum
CPU: must support AVX2
To install the SDK on Linux, 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.
Whether you are installing the SDK for the first time or are currently using a previous version, you must download our Windows installer which is hosted in an installer repository. The URL of this repository can be retrieved this way:
Once you have access to our installer repository, among the list of SDK installers (
download the one with highest version number.
If you are upgrading Metavision from a previous version, you should first 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 x.y.0 to x.y.1)
Download the installer for one of the supported Python versions:
Run the installer and follow the prompt
Add Python install and script directories in your
PATHand make sure they are listed before the
WindowsAppsfolder which contains a Python alias launching the Microsoft Store. So, if you installed Python 3.8 in the default path, your user
PATHshould contain those three lines in that order:%USERPROFILE%\AppData\Local\Programs\Python\Python38 %USERPROFILE%\AppData\Local\Programs\Python\Python38\Scripts %USERPROFILE%\AppData\Local\Microsoft\WindowsApps
Then install some extra libraries (note that you can skip this step if you don’t plan to use our Python samples/API and are willing to use Metavision Studio only for now). Open a command prompt and run the command:
python -m pip install pip --upgrade python -m pip install "opencv-python==220.127.116.11" "sk-video==1.1.10" "fire==0.4.0" "numpy==1.23.4" "h5py==3.7.0" pandas scipy python -m pip install 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 addition, check that conda
PYTHONPATH contains the aforementioned
PATH. For example for Python 3.8:
If not, add them. For example with
sys.path.append() method of python module
# Add %USERPROFILE%\AppData\Local\Programs\Python\Python38 to PYTHONPATH if the output of print(sys.path) does not mention it.
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 of FFMPEG to your
Just run the SDK installer and follow the instructions.
Prophesee camera plugin is included in the SDK and the drivers for most of the Prophesee cameras are deployed during the installation. But if you own an EVK2 or an RDK2, you will need to install the driver manually.
First, download wdi-simple.exe from our file server.
Then, verify in your device manager that you have the three following interfaces when your camera is connected:
fastboot, displayed as below with a
(from left to right,
picture 1). If not, uninstall the device already installed as shown in
picture 2 and
(generally the already installed device is, either EVK2 if you connect an EVK2 device or fastboot if you connect an RDK2 device).
Kindly note that you should repeat this uninstall operation until your device (EVK2/fastboot) is not recognized anymore and appears in
other devices with a
Also, we recommend to double check the interface number of your device (the number just after the
-i option when using
wdi-simple.exe as presented in the next paragraph).
To do so, right click on the name of the interface you want to install (
EVK2``or ``fastboot) in your device manager and follow the steps depicted in the pictures below:
For example, we can see on the right picture that the interface number is
Now, you can install the relevant driver with the following command:
wdi-simple.exe -n "EVK" -m "Prophesee" -v 0x03fd -p 0x5832 -i <INTERFACE_NUMBER>
You are now ready to use Metavision SDK. 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 getting started guide or looking at a Code Sample.
If you want to use the Machine Learning modules, please follow the next section that describes the required additional dependencies.
Additional Dependencies for Machine Learning Module
To use Machine Learning features, you need to install some additional dependencies.
If you have some Nvidia hardware with GPUs, you can optionally install CUDA (11.6 or 11.7) 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.
Then install some extra Python libraries:
python -m pip install "numba==0.56.3" "profilehooks==1.12.0" "pytorch_lightning==1.8.6" "tqdm==4.63.0" "kornia==0.6.8"
python -m pip install "llvmlite==0.39.1" "pycocotools==2.0.7" "seaborn==0.11.2" "torchmetrics==0.7.2" "pillow==9.3.0"
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.
We also provide pre-trained models for inference in automotive applications. They can be downloaded during the sign-up. (if you are a Prophesee customer, retrieve the link to the model by accessing to your SDK version in the Knowledge Center Download section).