Installation
Follow comprehensive installation guides for PySDK, covering virtual environments, Docker images, and verification.
Last updated
Was this helpful?
Follow comprehensive installation guides for PySDK, covering virtual environments, Docker images, and verification.
Last updated
Was this helpful?
PySDK currently supports these operating systems, CPU architectures, and Python versions.
Below is a summary of what hardware we support, including the runtime, devices, and model binary formats.
pip install
in a Virtual EnvironmentWe recommend creating a Python virtual environment for PySDK and other DeGirum python packages.
Open a command prompt or terminal, then follow the steps for your system below.
Installing PySDK in a Python Virtual Environment on Windows
To install PySDK, ensure a Python version supported by PySDK is installed, then follow this video or the steps below:
Create a Python Virtual Environment
Create a virtual environment with the command:
If you have Python Launcher and multiple Python versions installed, use py
to create the virtual environment:
Activate the Python Virtual Environment
After creating the virtual environment with venv
, navigate to the Scripts
folder in your virtual environment's folder.
When you cd
into this folder, you will need to run activate
.
After activating the virtual environment, you will see the name of your virtual environment prefixed before the terminal prompt.
Install PySDK with pip install
With your virtual environment activated, use pip
to install PySDK and optionally degirum-tools
. We call the PySDK package degirum
. We provide the degirum-tools
package to help you write AI applications with PySDK.
Verify PySDK Installation
In the Python virtual environment, run this command:
If you see a list of devices detected by PySDK, then PySDK you have successfully installed onto your system.
Ensure you have a Python version supported by PySDK installed.
Create a Python Virtual Environment
Create a virtual environment with the command:
If you have multiple Python versions installed, you can specify a Python release version to create the virtual environment:
Activate the Python Virtual Environment
After creating the virtual environment with venv
, navigate to the bin
folder in your virtual environment's folder and set activate
as source.
After activating the virtual environment, you will see the name of your virtual environment prefixed before the terminal prompt.
Install PySDK with pip install
With your virtual environment activated, use pip
to install PySDK and optionally degirum-tools
. We call the PySDK package degirum
. We provide the degirum-tools
package to help you write AI applications with PySDK.
After installing required runtimes and any needed device drivers, you can verify PySDK access to the runtimes and the devices by running this command in a terminal:
The output should contain all the devices available to PySDK and some information about them.
If you encounter errors such as:
Try creating a new virtual environment and reinstalling PySDK.
You can also try upgrading the pip
package. In your virtual environment, run the following command:
If you do not already have Python installed, we recommend disabling the Windows Python App Execution Alias before trying to install Python and PySDK. You should also ensure you have installed.
Install a Python version supported by PySDK: After disabling the App Execution Alias, install Python from the or with winget
. If you will install Python with , install both Python.Python.<version>
and Python.Launcher
.
We also provide Docker images for the and installations.
Follow for details on how to run these images and for corresponding source Dockerfiles.
We support multiple hardware options and runtime environments. PySDK comes with support for N2X and TFLite runtimes. Follow for more details.
Additionally, on Windows, ensure you have installed the .
python.exe
and python3.exe
.degirum-windows
virtual environmentdegirum-wsl
virtual environmentUbuntu Linux 20.04, 22.04, 24.04
x86-64
3.9 ... 3.12
Ubuntu Linux 20.04, 22.04, 24.04
ARM AArch64
3.9 ... 3.12
Raspberry Pi OS (64 bit)
ARM AArch64
3.9
Windows 10/11
x86-64
3.9 ... 3.12
macOS 12
ARM AArch64
3.9
Hailo
HAILORT
HAILO8, HAILO8L
.hef
TFLITE
EDGETPU
.tflite
Intel
OPENVINO
CPU, GPU, NPU
.onnx, .bin & .xml
BrainChip
AKIDA
NSoC_v2, AKD1500
.bin
DeGirum
N2X
ORCA1
.n2x
Rockchip
RKNN
RK3588, RK3568, RK3566
.rknn
MemryX
MEMRYX
MX3
.dfp
AMD
ONNX
VITIS_NPU
.onnx
NVIDIA
TENSORRT
DLA, GPU
.onnx