Basically there is no nice module (that I know of) for adding annotations to images in python. People use either openCV or Pillow. The code in this integration is from Home Assistant, and I worked on it. If you can come up with a better way let me know!
so are you saying this is the right module? thatās where the font is specified? if so, I changed what was there (8) to 15, then to 25 but I saw no subsequent change in the font size. I therefore assumed that the file coral_image_processing.py was not the right file. Now Iām really confused.
We can take this conversation onto github via an issue on the repo, cheers
Is there a way to use the current Tensorflow component with the coral or must it be done through a separate install of tensorflow? And how hard is it to integrate that back to HA?
I think this may be the only way to utilise the Coral with Tensorflow - https://github.com/robmarkcole/coral-pi-rest-server
Integration is quite straight forward per the README
I think the only way possible to use a coral is with tensorflow-lite
coral is for use with tensorflow-lite models. The official HA Tensorflow is for full tensorflow models
some people are hoping the coral code i wrote will perform as well as the official deepstack docker container - that is not the case. The coral code is very alpha, and doesnāt handle multiple requests
what do you mean exactly by āmultiple requestsā?
If deepstack receives multiple request it will queue them. Coral is very fast so should be fine, but I have not stress tested it
Just ordered mine. Would be interested to see how many FPS you can get from this stick 
Hi Robin,
I read here:
you arenāt working anymore on Coral stick.
Donāt you see still advantages of high FPS capabilities and no need to rely upon internet connection?
for HA deepstack type integration I need at most 1-2 FPS. For video rate processing there is frigate or doods.
First off, thanks for making this project. I bought a coral accelerator just to use for this application.
However, Iām seeing high memory and CPU usage after running either the coral-pi-reset-server or the tensorflow-lite-rest-server for about a day.
Is anyone else having this issue?
Might be an idea to have it restart daily, I wouldnt know where to begin debugging this kind of issue
Good news, the issue seems to have gone away on itās own after upgrading to Home Assistant 0.113.1. It makes sense that it was on the HA side since it was affecting both the coral-pi-reset-server and the tensorflow-lite-rest-server. Keeping my fingers crossed that the issue is gone for good.
2 Likes
@robmarkcole Hello Iāve just bought Google Coral USB Accelerator and I cannot make it work on synology DS918+. Did you managed to get it working on your syno ?
Not something I tried, I do recall someone did it
did u try to make it work with synology with docker device mount ?
I was planning to do the same (DS1618+ here) can you elaborate a little bit more, what you tried, and how it failed?
Yea at the moment Iām running it in docker. Itās plausible but quite hard to run it on VM not mentioned that after extensive talk with Google Coral Stick Dev Team there is a huge performance bottleneck (their claim).
With docker itās basically hassle free and itās really 10x faster than without the stick. Iām having 8~10ms processing time.
1 Like