Skip to main content

Recent Topics

53
mcunha
Ensign
mcunhaEnsign
 Voyager SDK
Support to zsh

I am using zsh as my shell application. While activating the environment, I encountered this error:   voyager-sdk git:(release/v1.3) ✗ source venv/bin/activate _AX_set_env:4: bad substitutionDo you think providing support for shells other than bash would help? 

202
emustafa
Axelera Team
S
Ensign
skroedelEnsign
 Project Challenge: Recognize & React
See and Hear (Pioneer10 project)

Hello together we are Sebastian Krödel and Lorenzo Gualniera  and we are super excited to having been selected for the Pioneer 10 Project Challenge. Sebastian is a machine learning engineer and Lorenzo is an embedded machine learning engineer, both with a background in the biomedical field. What are we Building?We will build See & Hear, a table-top companion for two-to-four–person meetings.The headphone wearer receives a private, noise-reduced feed of the talker they are looking at – and can instantly switch sides by simply raising the matching hand (left hand → left seat, right hand → right seat).This gives interpreters, note-takers and non-native speakers a fatigue-free, captioned audio channel while the room conversation remains untouched.Why Does This Project Matter to Us?For seven years Sebastian developed beam-forming and noise-reduction systems that help people with hearing loss follow conversations.  Users, and even perfectly normal-hearing colleagues, sink into fatigue dur

10811
V
Axelera Team
mcunha
Ensign
mcunhaEnsign
 Metis M.2
Firmware update

I am having a problem while updating the firmware version to 1.3.0, which is present in the release of voyager-sdk 1.3.1 on GitHub (branch - release/v1.3). I am using the Aetina RK3588 Evaluation Kit. Here is the filename containing the firmware:firmware_release_public_v1.3.0.tar.gzThe output of axdevice command is : Device 0: metis-0:1:0 1GiB m2 flver=1.3.0-rc3 bcver=1.4 clock=800MHz(0-3:800MHz) mvm=0-3:100%Here is the error I am facing:(venv) aetina@aetina:~/devel/axelera/firmware/firmware_release_public_v1.3.0$ ./flash_update.sh --fw-update>>> Metis Firmware update>>> the following operations updates the flash content Make sure to only run this operation if really needed Also make sure to not power cycle the devices or it might be rendered non-functional.Do you want to continue? [y/n] y>>> loading new AIPU runtime stage0[00:15:56.989,227] <inf> app: Start pcie check thread 0x833a00>>> set flash force flag>>> flash firmware[

192
mcunha
Ensign
llrds
Cadet
llrdsCadet
 Project Challenge: Recognize & React
Pre-porting planning (Pioneer 10 - Brobot)

Annoyingly I’ve not yet used the new hardware Axelera shipped to us, but I will move over soon…If you have followed my other posts, you will have seen that I got a basic webapp running using OpenCV. At the time that was just very simple HTML5 App.The whole purpose of this is to check the form of the workout is correct, and count the reps.Generally, all I need to do is work out an angle of 3 chosen key points, and simply track the range for “down rep” and the range for “up rep”, that allows me to count reps and track the range of motion. Then I can compare left and right side, are they nearly equal? If yes, that means the form must be strong. If they start to drift, that could show that one side is getting tired - time to stop.To simplify he magic this is only simple Pythagoras and a state machines, however I have still decided to port the app to React so everything is processed client side, then the server just worries about inference and supplying an API endpoint for the data.This mea

111
Spanner
Axelera Team
Spanner
Axelera Team
SpannerAxelera Team
 Project Challenge: Recognize & React
New deadline for Pioneer 10 Project Challenge submissions

Hi everyone!I think deliveries of kits have pretty much been sorted at this point. It took a little longer than expected to get them all on the various doorsteps around the world 😄So I’m looking at the calendar to adjust the submission deadline, in order to give you guys the time you need to build a working project. How does 16th August sound to you guys? Enough time to get things up and running?It’s about the same duration as originally planned, but with the start date adjusted. Let me know what you think!

244
llrds
Cadet
Steven Hunsche
Axelera Team
Steven HunscheAxelera Team
 The Axelera Forum
Running Edge AI on Orange Pi 5 Plus with Metis

I've put together a quick walkthrough of how to set up the Voyager SDK with a Metis M.2 card on the Orange Pi 5 Plus, and wanted to share the full process with you all. This has turned out to be a fantastic low-cost dev setup to start experimenting with edge AI using our Metis platform.Here’s what we cover:Installing the Metis M.2 card Setting up the Orange Pi with the proper OS image Installing the Voyager SDK (using SSH, so you can do it headless) Running a YOLOv5 demo with live inferenceEverything is done using standard tools like Balena Etcher, SSH, and a few terminal commands. Whether you’re building a prototype or just exploring Metis on embedded platforms, this setup is a great place to start on a device that's cheap, powerful, and very easy to use.Got questions or ran into snags? Let me know! These resources should help, too:📚 Setup guide reference: https://support.axelera.ai/hc/en-us/articles/27059519168146-Bring-up-Voyager-SDK-in-Orange-Pi-5-Plus📦 Source & SDK: https://

420
Steven Hunsche
Axelera Team
shabaz
Ensign
shabazEnsign
 Project Challenge: Recognize & React
ANPR-for-All: Axelera Hardware! And connecting to a WLAN

A huge box arrived today! It’s thoughtfully packed full of hardware for getting going with Axelera.The most interesting bit of course is the compact (131 x 120 mm) Axelera M.2 Eval System (PDF Product Brief). The Eval System contains the  Metis AI Inference Acceleration Card on top of a standard single-board computer (SBC). You can run the Metis Acceleration Card using standard interfaces (PCIe via an M.2 hardware socket), therefore you can use legacy SBCs with M.2 that you may already have deployed, as well as new compute hardware, depending on needs.The Metis M.2 Eval System SBC uses a Rockchip RK3588 (PDF datasheet) system-on-chip (SoC). Internally, the RK3588 contains two quad-core Cortex-A series processors plus a GPU, and lots of useful interfaces including the required PCIe.  The board supports built-in storage (eMMC) pre-installed with Ubuntu 22.04  and for additional storage there’s a micro SD card slot, as well as an M.2 socket (M-Key) for inserting an optional solid-state dr

1155
shabaz
Ensign
S
Ensign
skroedelEnsign
 Project Challenge: Recognize & React
Problems install Voyager SDK

I am following these instructions: https://github.com/axelera-ai-hub/voyager-sdk/blob/release/v1.3/docs/tutorials/install.md Unfortunately, when running the install script I am getting this error:./install.sh --all --media --user XXX --token XXXInstall/update prerequisite apt packages required by the installer itself (y/n): y[1/0] sudo DEBIAN_FRONTEND=noninteractive apt-get --no-install-recommends install -y -qqq python3-pip[1/0] E: Unable to correct problems, you have held broken packages.Installing python3-pip failed due to held/conflicting dependencies - attempt to resolve by also updating the dependencies: python3-setuptools python3-pkg-resources (y/n): yInstall/update prerequisite pip packages required by the installer itself (y/n): y[1/0] python3 -m pip install --user pip pyYAML[1/0] /usr/bin/python3: No module named pipERROR: Installer requirements not met I did not install any packages before (just build the WLAN adapter packages as descibed by ​@shabaz )Did anybody have simila

315
S
Ensign
K
Cadet
ku15921Cadet
 Metis M.2
Error installing metis-dkms

Hi,I'm having trouble installing the metis-dkms driver. Can you help me?The device is a NanoPC-T6 from Friendly Elec, and the operating system is Ubuntu 22.04, also provided by Friendly Elec.I'm leaving the error message and OS information below. If there is any more information I should provide, please let me know. Thank you. The Error:$ sudo dpkg -i metis-dkms_0.07.16_all.deb(Reading database ... 155441 files and directories currently installed.)Preparing to unpack metis-dkms_0.07.16_all.deb ...Deleting module metis-0.07.16 completely from the DKMS tree.Unpacking metis-dkms (0.07.16) over (0.07.16) ...Setting up metis-dkms (0.07.16) ...Loading new metis-0.07.16 DKMS files...Building for 6.1.99Building for architecture aarch64Building initial module for 6.1.99ERROR (dkms apport): kernel package linux-headers-6.1.99 is not supportedError! Bad return status for module build on kernel: 6.1.99 (aarch64)Consult /var/lib/dkms/metis/0.07.16/build/make.log for more information.dpkg: error pro

21513
V
Axelera Team
dbrenes
Cadet
dbrenesCadet
 Metis M.2
Metis M.2 Not Recognized by lspci on Intel system

Hello! I’ve been trying to connect and use the Axelera Metis M.2 card with no success. The same M.2 on a different PC was recognized correctly by using:lspci | grep AxeleraBut now the card cannot be recognized at all on the new system. Here are some specs of the current host:Dell 5820 CPU: Intel(R) Core(TM) i7-7820X CPU @ 3.60GHz RAM: 32 GB GPU: 2 Quadro RTX 5000 OS: Ubuntu 24.04 I’ve also tried lspci | grep 1f9d with no success. The Metis driver is already installed and loaded with modprobe.I'd appreciate any help or insight on additional steps I could try.Additionally, this is the adapter I’m using for the Axelera card: 

396
V
Axelera Team
S
Ensign
saadtiwanaEnsign
 
SDK example(s) on how to use detection models from OpenCVNew

The examples that come with the SDK mostly use pipelines that do all the work of getting the data from the source (files or usb camera), sending for inference, and then displaying the inference results on the images. This is great for many use cases, I am sure, and enable a high degree of efficiency. However, for many users, the AI inference is part of a C/C++/python application where the images are obtained via OpenCV, processed (scale/crop/etc) in opencv based on application logic, and then a part of the image is sent for AI detection. Once the result is obtained, then the application can display the results over the opencv image using it’s own custom logic.So in summary, it would be great to have some examples that demonstrate this process. A simple example that shows how to use a detection model from the model zoo in C or Python along with opencv for obtaining image and displaying the results. Another good example would be running the model inference as a gstreamer pipeline. This w

3
171
J
Axelera Team
G
Cadet
GillesCadet
 Voyager SDK
Compiling yolov5 doesn't give correct input/output shapes

I’ve used the yolov5s.pt file provided from the official yolov5 repository and converted it to onnx with this command:  python3 export.py --weights yolov5s.pt --imgsz 640 --batch-size 1 --include onnx --opset 17  . I’ve then tried to compile this with this command:  compile -i /home/axelera/Vision.AxeleraTesting/data/yolov5s.onnx -o /home/axelera/Vision.AxeleraTesting/data/compile --overwriteI got this output:09:49:45 [INFO] Dump used CLI arguments to: /home/vintecc/axelera/Vision.AxeleraTesting/data/compile/cli_args.json09:49:45 [INFO] Dump used compiler configuration to: /home/vintecc/axelera/Vision.AxeleraTesting/data/compile/conf.json09:49:45 [INFO] Input model has static input shape(s): ((1, 3, 640, 640),). Use it for quantization.09:49:45 [INFO] Data layout of the input model: NCHW09:49:45 [INFO] Using dataset of size 100 for calibration.09:49:45 [INFO] In case of compilation failures, turn on 'save_error_artifact' and share the archive with Axelera AI.09:49:45 [INFO] Quantizing

375
J
Axelera Team
llrds
Cadet
llrdsCadet
 Project Challenge: Recognize & React
Porting from OpenCV (Pioneer 10 - Brobot)

Hi All,I’ve got a PoC running using OpenCV+M1 Mac while I wait for my Metis hardware. In preparation for the kit arrival, I want to plan the porting process and get ahead on refracturing so I can compare the performance. I plan to use inferenceStream with Python to keep it really simple.Any experience here going from OpenCV to Voyager? Is it a drop in replacement or are they used in parallel?If there is a better development environment than OpenCV i’d be glad to hear it - my application is taking shape so I want to make sure I do not stray to far down the wrong path!

334
S
Ensign
llrds
Cadet
llrdsCadet
 Project Challenge: Recognize & React
When can we expect hardware ship?

it will help with planning tasks and meeting the project deadline

383
Spanner
Axelera Team
S
Ensign
saraEnsign
 Voyager SDK
inference on a frame obtained from the memory space

Hi again ​@Spanner ! 😊I need to infer an image obtained from byte data stored in a memory space (https://docs.python.org/3/library/mmap.html) and after converting the bytes I get an image.I've seen the sources available for create_inference_stream and I know that I can make inferences to images (https://github.com/axelera-ai-hub/voyager-sdk/blob/release/v1.2.5/docs/tutorials/application.md), but I have to specify the/path/to/file. But in this case I won't have that information.In the code I'll have this line where I read the bytes in the memory space:        frame_size=image_width*image_height*3 //RGB        frame_bytes = mm.read(frame_size)And then I get the new image:      frame = np.frombuffer(frame_bytes,dtype=np.uint8).reshape((image_height,image_width, 3))Is there any way to infer “frame”?Thank you!

20512
Spanner
Axelera Team
P
Cadet
PepijnCadet
 Metis PCIe
deploy.py takes really long yolov8 model

Hi, I’m trying to deploy and inference with a yolov8 segmentation model. I tried to follow the tutorial, but I just get:INFO: deploying model yolov8sseg-coco for 4 cores. This may take a while… How long should this run? I left it on for 3.5 hours and nothing happened (except the loading bar). This seems to be a model included in your library: yolov8sseg-coco.Any idea if I can turn on more extensive logging to see what is happening? Thank you in advance!  

192
Steven Hunsche
Axelera Team
G
Cadet
GiodstCadet
 Voyager SDK
Yolo11l custom weigts deploy

Hi, I’m getting very pool performance on Yolo11l custom weigts after the conversion in onnx.I’ve used opset 17 and 16, do you have any suggestions?Thanks.

131
G
Cadet
A
Cadet
AfikCadet
 Metis M.2
Yocto Driver\Layer for Metis

Hi, We are considering adding an AI Accelerator for our board (i.MX8, yocto).Do you support yocto OS?Is there any reference design or example that runs Metis on yocto platform? Thanks,Afik

213
Steven Hunsche
Axelera Team
N
Cadet
negredoCadet
 Metis M.2
QNAP NAS compatibility

Will Metis M.2 ( AXE-BME20M1AR01B02) work with QNAP NAS?

51
Spanner
Axelera Team
M
Cadet
mgrunerCadet
 Metis M.2
Low performance of the Metis M2 on the Raspberry Pi5

Hi! I'm testing the Metis M2 on a Rapsberry Pi 5 using the Ubuntu 22.04 container. I can successfully get results using the inference test suggested by the article:./inference.py yolov8s-coco-onnx ./media/traffic1_480p.mp4 Unfortunately, I get around 4FPS. Is this expected? If I profile the device and the host separately (using --show-host-fps and --show-device-fps) I see that the device is running at ~800FPS while the host is the one bottlenecking at ~4FPS.I tried enabling GLES processing using export AXELERA_OPENGL_BACKEND=gles,3,1but, unfortunately, it makes not much of a difference. I also tried setting the PCI to gen3 by setting the following in the /boot/firmware/config.txt, without any luck:dtparam=pciex1_gen=3As a reference: these are the instructions I'm following:- https://support.axelera.ai/hc/en-us/articles/26362016484114-Bring-up-Voyager-SDK-in-Raspberry-Pi-5- https://support.axelera.ai/hc/en-us/articles/25953148201362-Install-Voyager-SDK-in-a-Docker-ContainerIs this perfo

503
M
Cadet
G
Cadet
GiodstCadet
 Metis M.2
WASB model for tennis ball detection

How can I deploy WASB model on metis m2?

242
G
Cadet
Spanner
Axelera Team
SpannerAxelera Team
 Project Challenge: Recognize & React
The Pioneer 10 Project Challenge - How It WorksNews

Build AI that doesn’t just see—it acts. Do you have what it takes to turn AI vision into real-world action? Join our Pioneer 10 project challenge and show us what you can do with Axelera AI’s powerful Metis platform and a project kit with some great hardware to get you where you’re going.Your mission: Detect something in the real world—and make something happen. 🎯 The ChallengeCreate a project where computer vision triggers a meaningful, real-world response. Think smart notifications, voice alerts, automated systems, IoT interactions—anything that goes beyond detection and does something in the physical world around you.Get creative, and show us how AI can interact with us in real, engaging ways. 📦 What You’ll GetTen successful participants will be selected from the proposals, and receive an Axelera AI Project Kit worth €1,500+ that they’ll use to build their project: 🧠 Metis AI Accelerator System with M.2 Metis card pre-installed 🎥 2 x USB Cameras (1080p) 💾 MicroSD Card (for

67964
Hope3.16
mcunha
Ensign
mcunhaEnsign
 Project Challenge: Recognize & React
Summer Sidekick: Your essential summer companion for plants and pets (Pioneer10 project)

Hi everyone,I am Marcos, a software engineer who has worked primarily in embedded systems across South America and Europe. I am currently based in Toulouse, France.What am I building?I am building a smart summer assistant called "Summer Sidekick" that uses Vision AI to help summer travelers manage the feeding of their pets and plants while they are away. This system ensures that pets and plants are fed properly and on time, allowing users to enjoy their vacation without worry. The entire system will be composed of actuators to trigger the food and water dispensers. For pets, AI algorithms will detect the pet's presence and food and water levels. For plants, their health will be monitored, as well as ensuring their water needs are met.Why does this project matter to me?Some summer travels can turn into a nightmare when organizing care for your companions (plants and pets) while you are away. Especially this summer, I will need to travel for almost 40 days far from home, and currently, t

1075
Spanner
Axelera Team
F
Cadet
fatima-zahra.chenaniCadet
 Voyager SDK
axelera-runtime.tar.gz

Bonjour,Je n’arrive pas à récupérer le fichier `axelera-runtime.tar.gz`. Le script `install.sh` affiche “Runtime Installed OK” mais ne télécharge ni n’extrait quoi que ce soit.Aucune URL n’apparaît dans les logs et `libaxruntime.so` est absent de mon système.Merci de me fournir un lien de téléchargement direct pour installer le runtime manuellement.Cordialement,   

412
F
Cadet
lorenzo.lamberti
Cadet
lorenzo.lambertiCadet
 Voyager SDK
Voyager-sdk on singularity

Dear all, I am trying to set up the metis PCIe accelerator on a intel workstation. Later we will move to a full risc-v embedded setup.In out lab workstation we are forced to use singularity instead of docker, so i am trying to translate the docker container into a singularity one.I think i am very close to make everything work. However, i am now stuck with a problem i can’t figure how to solve. in particular, i get a weird error when i try to run a simple ./inference.py with one of the pre-trained models. Below the full description on how i create, run the container, and how i run the example from the voyager sdk my `voyager-sdk-1.2.5.def` fileBootstrap: dockerFrom: ubuntu:22.04%labels Author You Version voyager-sdk-1.2.5%environment export DISPLAY=$DISPLAY%post apt-get update && apt-get install -y \ sudo \ git \ pciutils \ lsb-release \ x11-utils curl \ wget \ gnupg2 \ lsb-release \ software-prop

675
P
Cadet

Badge Winners

Show all badges
Code of Conduct

Address

HTC5, High Tech Campus
5656 AE Eindhoven
The Netherlands
Email: info@axelera.ai

Menu

AI Accelerators

AI Software

Metis Evaluation Systems

Partners

Product Inquiry

Company

Our Story

Our Team

Careers

News

Contact

Reducing CO₂ with
Axelera’s Forest

Follow Us

LinkedIn

Twitter

Sign Up for Our Newsletter

EU flag Axelera AI is co-funded by the European Union’s Horizon research and innovation programme.

Privacy Policy  |  Cookie Policy  |  Terms of Sale  |  Vulnerability Disclosure Policy

Copyright 2025 © All rights Reserved.