tensorrt_demos
wayvnc
tensorrt_demos | wayvnc | |
---|---|---|
5 | 21 | |
1,720 | 934 | |
- | - | |
3.1 | 8.0 | |
about 1 year ago | 5 days ago | |
Python | C | |
MIT License | ISC License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tensorrt_demos
-
lowering size of YOLOV4 detection model
tensorrt_demo github repository
-
Jetson Nano: TensorFlow model. Possibly I should use PyTorch instead?
https://github.com/NVIDIA-AI-IOT/torch2trt <- pretty straightforward https://github.com/jkjung-avt/tensorrt_demos <- this helped me a lot
-
PyTorch 1.8 release with AMD ROCm support
> I'll also add a caveat that toolage for Jetson boards is extremely incomplete.
A hundred times this. I was about to write another rant here but I already did that[0] a while ago, so I'll save my breath this time. :)
Another fun fact regarding toolage: Today I discovered that many USB cameras work poorly on Jetsons (at least when using OpenCV), probably due to different drivers and/or the fact that OpenCV doesn't support ARM64 as well as it does x86_64. :(
> They supply you with a bunch of sorely outdated models for TensorRT like Inceptionv3 and SSD-MobileNetv2 and VGG-16.
They supply you with such models? That's news to me. AFAIK converting something like SSD-MobileNetv2 from TensorFlow to TensorRT still requires substantial manual work and magic, as this code[1] attests to. There are countless (countless!) posts on the Nvidia forums by people complaining that they're not able to convert their models.
[0]: https://news.ycombinator.com/item?id=26004235
[1]: https://github.com/jkjung-avt/tensorrt_demos/blob/master/ssd... (In fact, this is the only piece of code I've found on the entire internet that managed to successfully convert my SSD-MobileNetV2.)
- I'm tired of this anti-Wayland horseshit
-
H.264 hardware acceleration for surveillance station performance
It was some work getting compiled on nano but I used this guy's work to get started. https://jkjung-avt.github.io/tensorrt-yolov4/ and https://github.com/jkjung-avt/tensorrt_demos
wayvnc
-
Dropping GNOME's X11 session approved for Fedora 41
You can run remote applications with Wayland now: https://access.redhat.com/documentation/en-us/red_hat_enterp...
There is also a VNC server for fullscreen sessions (only supports wlroots compositors for now): https://github.com/any1/wayvnc
-
Is my use case with X.org possible with Wayland?
There's wayvnc.
-
Asahi Linux To Users: Please Stop Using X.Org
It says on their GitHub page that "Gnome, KDE, and Weston are not supported". What does that mean?
-
What kind of applications are missing from the Linux ecosystem?
I thought this existed in the form of wayvnc but from their README it seems they don't support the popular desktop environments (GNOME, KDE).
-
What are my options for remote desktop software on wayland?
Not sure if I would call it hassle free, but wayvnc isn't that hard to set up.
-
When do you think you will switch to Wayland?
And wayvnc
-
Can I run Sway via remote desktop on a Linode server running arch?
There is however a fresh issue on the wayvnc github with what looks like your problem. https://github.com/any1/wayvnc/issues/206
-
Use a laptop as a 2nd display on Linux using FreeRDP
On wayvnc git master and sway 1.8 (or git master), you can script things so that a "virtual" display gets created automatically when someone connects to VNC, and removed when they disconnect.
See https://github.com/any1/wayvnc/pull/200/files
The script in the PR does something a bit different, but it's only an example and can be modified to do what I described in the first paragraph.
-
Intel is using DXVK for their Windows Arc GPU DX9 drivers
No - it's not X, it's doesn't share a screen in the way X does.
That said... if this is a shoddy attempt at a "gotcha" style question - Screen sharing and remote desktop are both supported.
Ex - for Gnome:
https://wiki.gnome.org/Projects/Mutter/RemoteDesktop
LibVNCServer for VNC support, FreeRDP for remote desktop protocol.
For KDE:
https://userbase.kde.org/Krfb
Which mostly just works as long as you have Pipewire and xdg-desktop-portal-kde installed (the base plasma-wayland session usually includes them)
This one is a bit less polished - some users still have problems with keyboard input, depending on the distro and other installed packages.
For Sway:
xdg-desktop-portal-wlr works just fine for screen sharing, and you can use https://github.com/any1/wayvnc for VNC access (including having a completely headless machine).
-
Linux experts, how to start TigerVNC automatically when switching to desktop?
Ah right, looks like the VNC server you're using is xorg only. You can try WayVNC for gaming mode https://github.com/any1/wayvnc .
What are some alternatives?
YOLOX - YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
x11vnc - a VNC server for real X displays
torch2trt - An easy to use PyTorch to TensorRT converter
sway - i3-compatible Wayland compositor
yolov4-custom-functions - A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.
kanshi - Dynamic display configuration (mirror)
tensorflow-yolov4-tflite - YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.3.1, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
FreeRDP - FreeRDP is a free remote desktop protocol library and clients
jetson-inference - Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
noVNC - VNC client web application
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
xdg-desktop-portal-wlr - xdg-desktop-portal backend for wlroots