Comments (4)
@florianporada Thanks for the assessment! Agreed! :) We should buy one once it becomes available. I signed up for a notification at nvidia ... let's wait.
from opendatacam.
First benchmark of Jetson Xavier π
Running YOLO
Our YOLO implem "mesos" fork doesn't work out of the box on Xavier, running it leads to a Seg fault π , might be because of opencv, might be because of CUDA or any other dependency, not idea on why is failing, error doesn't give any info
After a bit of research, found out that the current "state of the art" implem of YOLO (v3) seems to be this repo: https://github.com/AlexeyAB/darknet , which has improvement over the "official" pjreddie/darknet one regarding specific architecture like Jetson Xavier or other GPUs hardware
So I went ahead, and after compiling and running it, turns out performances are really good π, significantly faster than the TX2, seeing a 4-10x perf boost :
YOLOv2 & VOC (same as current open data cam)
Power mode | FPS |
---|---|
Default (15W) | 25 FPS |
Max out (30W+) | 30+ FPS (webcam steam can't go higher) |
We were getting max 7 FPS with TX2
YOLOv3 & COCO
Power mode | FPS |
---|---|
Default (15W) | 11.5 FPS |
Max out (30W+) | 22.5 FPS |
We were getting max 2 FPS with TX2 on YOLOv2 + COCO
FFServer + YOLO v3
From a really quick benchmark, seems to be possible without much perf hit ( 1 FPS penalty..), see full notes for more on this
Full notes
I wrote more notes on all the setup + perf exploration: https://docs.google.com/document/d/1oDk7Nf95Pm2eJqHsC2TL24v87CsHW8wtENbJlkBSmNE/edit#heading=h.6px293e6d645
Further potential exploration:
- Try to run this new darknet implementation on Jetson TX2 to see if perfs improves
- Test a lighter implementation of yolov3: https://github.com/AlexeyAB/yolo2_light , claim +30% speedup for only -1% "accuracy"
Up next
I think this is promising as perfs are significantly better this can enable:
- a live preview of counting / detection to improve UX
- potential better detection and tracking, more FPS + Yolov3 trained with COCO dataset should be better at detecting things and more reliable
But we won't avoid to update our darknet implementation / port the websocket feature if we want to go further with Jetson Xavier... I'm not sure of the complexity of this but I remember looking in the C code done on the mesos fork and it didn't seem much.. but things are always more complex than they seem, and I don't have much expertise on both darknet source code and C code..
from opendatacam.
If 20x the performance of its predecessor
statement is true we could use higher resolution video footage and a higher framerate to boost accuracy. (maybe use a better trained model as well).
Also the base-system will be Ubuntu+JetPack which should provide us with the necessary libraries to run the code. (if the versions are compatible).
One downside is, that the board does not come with build-in WiFi anymore. So the parts (usb-dongle) we need to build the project will increase (+ another spof).
I'm in for testing it and doing a port if we get one of the boards in our hands π
from opendatacam.
Order! Shipping Sep 20 2018, should arrive beginning of Oct.
from opendatacam.
Related Issues (20)
- Problem with random crashing HOT 4
- Saving counter locations and names HOT 2
- Yolo Simulation in Live Mode does not increment frame ID correctly
- Add missing docker-compose file for cpu-amd64 platform
- Path View: Keep color if ID does not change
- Fix urlHelper
- MongoDB CPU usage increasing over time HOT 1
- Update to NodeJS v20 HOT 1
- Run Darknet in Docker with Jetpack v5 HOT 11
- Update Darknet for to latest upstream HOT 3
- Update GitHub Actions to latest version in Darknet repo HOT 1
- Think about merging those changes from opendatacam/[email protected]:darknet:odc into https://github.com/vsaw/darknet/tree/607-darknet-jetpack5 HOT 3
- Detection in 3.0.2 is not working on desktop HOT 15
- Fix annnoying failing Darknet builds
- Update Darknet Desktop Docker Image HOT 2
- Update Documentation and make CUDA 11 a minimum requirement to run OpenDataCam
- Builld Darknet CPU Image from main branch HOT 1
- Get yolov4-416x416.cfg into Darknet main branch
- Rename Docker Repository to OpenDataCam/Darknet
- Update NextJS and React HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from opendatacam.