Installation of SDK on Windows

This section describes how to install Metavision SDK on Windows 10 64-bit.

Note

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.

See also

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.

Supported Cameras

Metavision SDK comes with a Prophesee camera plugin, enabling to stream data from our event-based cameras and to read recordings of event-based data. The supported cameras are:

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.

Required Configuration

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.

Required Artifacts

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 (Metavision_SDK_xyz_Setup.exe), download the one with highest version number.

Note

If the SDK version you are looking for is not in the installer repository, please look for your version in the Knowledge Center Download section (request an account if you don’t have one yet).

Upgrading Metavision

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:

  1. Make sure that no Prophesee or Metavision software is running

  2. Open the Start menu

  3. Click Settings

  4. Search for Apps & features via the search

  5. In the list of installed programs, find any Prophesee or Metavision software and click the Uninstall button

  6. Check that there is no Prophesee folder left in your Program Files folder (if still present, delete it)

Warning

Removing the old version of Metavision SDK is mandatory even for patch upgrade (e.g. from x.y.0 to x.y.1)

Installing Dependencies

To execute our Python Samples and use the Python API, you will need Python and some additional libraries. If Python is not available on your system, install it:

  • 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 PATH and make sure they are listed before the WindowsApps folder which contains a Python alias launching the Microsoft Store. So, if you installed Python 3.8 in the default path, your user PATH should 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==4.5.5.64" "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"

Note

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 pip.

In addition, check that conda PYTHONPATH contains the aforementioned PATH. For example for Python 3.8:

%USERPROFILE%\AppData\Local\Programs\Python\Python38
%USERPROFILE%\AppData\Local\Programs\Python\Python38\Scripts
%USERPROFILE%\AppData\Local\Microsoft\WindowsApps

If not, add them. For example with sys.path.append() method of python module sys:

import sys
print(sys.path)
# Add %USERPROFILE%\AppData\Local\Programs\Python\Python38 to PYTHONPATH if the output of print(sys.path) does not mention it.
sys.path.append("%USERPROFILE%\AppData\Local\Programs\Python\Python38")

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:

Installation

Just run the SDK installer and follow the instructions.

Camera Plugins

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: CDC NCM; EVK2; fastboot, displayed as below with a warning sign (from left to right, picture 1). If not, uninstall the device already installed as shown in picture 2 and 3 (generally the already installed device is, either EVK2 if you connect an EVK2 device or fastboot if you connect an RDK2 device).

pic1 pic2 pic3

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 warning sign.

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 (CDC NCM, EVK2``or ``fastboot) in your device manager and follow the steps depicted in the pictures below:

pic4 pic5

For example, we can see on the right picture that the interface number is 03.

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>

Get started!

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.

Note

At the moment, we don’t support OpenCL and AMD GPUs.

Python Packages

You need to install PyTorch 1.13.1. Retrieve and execute the pip command of version 1.13.1 from the previous versions install guide section.

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)

Pre-trained Models

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).

Get Started with Machine Learning

To see the different tools, samples and tutorials available for our ML module, check out our Machine Learning guide.