CompreFace

CompreFace

Docker app from corgan's Repository

Overview

CompreFace (CPU) is a leading free and open-source face recognition system
You can choose between different Builds

FaceNet(default), (compreface:0.6.1) - For general purposes. Support CPU without AVX2
Arcface-R100, (compreface:0.6.1-arcface-r100) - The most accurate model, but the most slowest
MobileNet, (compreface:0.6.1-mobilenet) - The fastest model among CPU only models

More Infos: https://github.com/exadel-inc/CompreFace/blob/master/custom-builds/README.md Database

by default this App install a PostgresSQL Server. The Data are stored in the given Appdata Folder.
If you allready have your own Postgres Server running, you can setup a external Server.
1. Click on "Show more settings"
2. Enter the Username and URL of your PostgresSQL Server. Note: The User has to be SuperUser Rights
3. Set the Variable EXTERNAL_DB to "True"
The URL should look like this:

jdbc:postgresql://IP:PORT/DATABASENAME
like:
jdbc:postgresql://192.168.1.254:5432/compreface

Runtime arguments

Web UI
http://[IP]:[PORT:80]
Network
bridge
Shell
sh
Privileged
false

Template configuration

WebUI HTTP PortPorttcp

Container Port: 8000

Target
80
Default
8000
Value
8800
Data FolderPathrw

Container Path: /var/lib/postgresql/data

Target
/var/lib/postgresql/data
Value
/mnt/user/appdata/compreface
EXTERNAL_DBVariable

Container Variable: EXTERNAL_DB

Value
false
POSTGRES_URLVariable

Container Variable: POSTGRES_URL

Value
jdbc:postgresql://192.168.2.254:5432/compreface
POSTGRES_PASSWORDVariable

Container Variable: POSTGRES_PASSWORD

Value
corgan80982
POSTGRES_USERVariable

Container Variable: POSTGRES_USER

Value
compreface

Download Statistics

196,581
Total Downloads
4,216
This Month
2,801
Avg / Month

Total Downloads Over Time

Loading chart...

Details

Repository
exadel/compreface:1.2.0
Last Updated2023-08-17
First Seen2024-03-17

Run CompreFace on Unraid.

CompreFace is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.