Comments (12)
Can a patched file be mounted over the old one for now? There are a relatively small number of downloads of the tensorrt builds and an even smaller number with this issue. I would target dev for now. We could always add it to master later.
from frigate.
@NateMeyer we can defer to @blakeblackshear but currently I don't believe another bug fix update is planned so probably dev is my guess.
from frigate.
@jaharkes Can you proof read this gist and make sure this works for you? Thanks!
https://gist.github.com/NateMeyer/a689b4462e57b3de0ebcc40e6538fc03
from frigate.
CC @NateMeyer
In general some issues with older GPUs are not unexpected and we have seen some others with similar issues. The updat was done because 40 series GPUs were not working. I don't know that we would want to use a custom compiled version of the library as that may cause other issues for other users.
from frigate.
I'm not an nvidia compiler expert, but from my brief research it looks like it should be possible to build a single binary that at least supports all architectures (although it may not be optimized for any specific one) by setting computes=50 60 70 80 90
in the Makefile that builds libyolo_layer.so.
https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html#virtual-architecture-feature-list
https://kaixih.github.io/nvcc-options/
Compatibility:
-arch=compute_Xa is compatible with -code=sm_Xb when a≤b
-arch=compute_X* is incompatible with -code=sm_Y*
from frigate.
Good find. This wasn't an issue before because the libyolo_layer was built as part of the setup instructions for TRT on 0.12, so it always used the user's GPU compute level. I'll take a look at the nvcc flags and see if there is a good way to do that universally for the CI build. One bloated library is sure to be better than making every user download the whole toolchain to recompile it.
from frigate.
I don't know that we would want to use a custom compiled version of the library as that may cause other issues for other users.
We already build libyolo_layer.so as part of the docker build process. It is mostly an extra cuda kernel to transform the output of the yolo model to something more usable.
from frigate.
ah good to know, thanks for the clarification
from frigate.
@NickM-27 , if I submitted a PR that adds the computes="50 60 70 80 90"
to the libyolo_layer.so script, should that target master or dev? I view it a little more as a bug fix for maxwell cards on 0.13. We'll need a couple people who've had problematic Maxwell cards to test also.
This computes
value would only be set for the amd64 trt build, not jetpack. I don't think those have had issues with this? But it wouldn't be hard to also add a unique set of compute flags for each of those either.
from frigate.
@jaharkes Thank you very much for your solution, I was stuck for 4 days :)
from frigate.
Can a patched file be mounted over the old one for now? There are a relatively small number of downloads of the tensorrt builds and an even smaller number with this issue. I would target dev for now. We could always add it to master later.
I can throw together a gist with instructions to rebuild and mount the updated library for v0.13
from frigate.
Works like a charm.
from frigate.
Related Issues (20)
- Timeline HOT 1
- Send to Frigate+ behavior HOT 2
- Request: an option in the Logs to either "Jump to Bottom", or show in Reverse order HOT 1
- Zoom in on camera view HOT 1
- Click on camera in birdseye to open that camera HOT 1
- Issue with masks not matching image after saving them HOT 6
- Easy way to share a camera stream HOT 8
- Edge agent scenario (multiple decentralized locations) HOT 3
- Unable to downgrade to v0.12.1 HOT 1
- Frigate wont generate tensorrt models. Truenas scale HOT 1
- Ability to ignore objects that do not travel through frame/or do not enter *multiple* zones HOT 5
- When "No frames have been received, check error logs", reflect true FPS in system/API HOT 1
- do you know how to disable motion record and how to disable best image?thanks!
- About v0.13.2 version of Zones HOT 1
- Frigate Addon won't start HOT 1
- Bug? - Unknown Error, see supervisor logs HOT 2
- Add support for vehicle types HOT 1
- Record events with honouring motion mask HOT 2
- Ability to unselect all sub labels (currently only select seems available) and remove sublabels HOT 4
- Improve send to frigate+ ui HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from frigate.