Comments (5)
+1.
There's the one in this repo but it's stuck at 1.1 and seems like the owner of that repo isn't maintaining it.
Would probably be best if you provided it yourselves, assuming that's something you can take on naturally.
from compreface.
That's fine. I forced myself and finally installed in a docker!
from compreface.
I am not sure if this has done it, but I simply updated config.json and Dockerfile from jakowenko's repo to point to v1.2.0, and it seems it's working. The main reason I wanted to move away from v1.1.0 was the huge amount of memory the addon was using, apparently due to memory leaks in that version. However, with v1.2.0, I am seeing an even higher memory usage at a constant 4GB. Before, it was around 2.7GB. @pospielov do you mind sharing some insight in this regard? Is this amount of memory usage normal, or is the way I am creating v1.2.0 of the addon wrong?
from compreface.
There was this advise when 1.1.0 came out. I'm using it on a GTX1650 with only 4GB VRAM
#1034 (comment)
I'm running this on Unraid using docker compose with the following:
ADMIN_VERSION=1.1.0
API_VERSION=1.1.0
FE_VERSION=1.1.0
CORE_VERSION=1.0.0-arcface-r100-gpu
POSTGRES_VERSION=1.1.0
I haven't tried updating any of the individual modules to 1.2.0 yet. Also it looks like that addon uses a single container version. So I'm not sure how you would split it like compose.
Edit:
As you only have the single tag to choose from you might be best using:
1.0.0-mobilenet-gpu
or
1.0.0-arcface-r100-gpu
If your system has a GPU?
from compreface.
There was this advise when 1.1.0 came out. I'm using it on a GTX1650 with only 4GB VRAM #1034 (comment)
I'm running this on Unraid using docker compose with the following:
ADMIN_VERSION=1.1.0 API_VERSION=1.1.0 FE_VERSION=1.1.0 CORE_VERSION=1.0.0-arcface-r100-gpu POSTGRES_VERSION=1.1.0
I haven't tried updating any of the individual modules to 1.2.0 yet. Also it looks like that addon uses a single container version. So I'm not sure how you would split it like compose.
Edit: As you only have the single tag to choose from you might be best using: 1.0.0-mobilenet-gpu or 1.0.0-arcface-r100-gpu If your system has a GPU?
Thanks. There is no .env file for the addon. I am not sure where to put those configs. I am running Home Assistant on an Intel NUC with an integrated GPU. I also have a Google Coral attached, but I don't think CompreFace supports it.
from compreface.
Related Issues (20)
- Migrating from FaceNet to another version
- face-detect-service input no-face image without Exception
- Admin & API Node wont start HOT 1
- Openvino support HOT 1
- Install Compreface on docker desktop.
- Compreface API shows only 1 subject instead of 10 subjects HOT 1
- Port contention with Portainer (i.e. port 8000) HOT 1
- compreface-api service in constant "crash loop". HOT 2
- How to Challenge Millions of Faces HOT 1
- When I synchronize the PostgreSQL database with third-party software, facial recognition fails to work correctly
- Clarification for commerical use
- how to add new model of face recognize
- How to add extra information like introduction for each Subject?
- How to add extra information like introduction for each Subject? HOT 1
- Super-admin role account
- Getting kill signal for uWSGI worker
- Minimum Hardware Specification for SubCenter-ArcFace-r100
- Unable to get running HOT 1
- UI change HOT 2
- JCode.py
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 compreface.