https://github.com/d3vv3/autofocus-server

Server for autofocus
https://github.com/d3vv3/autofocus-server

ai autofocus autofocus-server faces fotos index indexing library light manager metadata object people photos pictures recognition

Last synced: 10 days ago
JSON representation

Server for autofocus

• Host: GitHub
• URL: https://github.com/d3vv3/autofocus-server
• Owner: d3vv3
• License: gpl-3.0
• Created: 2020-11-15T00:46:26.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2021-01-02T19:09:40.000Z (almost 4 years ago)
• Last Synced: 2024-10-27T11:02:45.970Z (about 2 months ago)
• Topics: ai, autofocus, autofocus-server, faces, fotos, index, indexing, library, light, manager, metadata, object, people, photos, pictures, recognition
• Language: Python
• Homepage:
• Size: 37.1 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# autofocus-server

Server for autofocus.

### What is autofocus?

Autofocus server is a fast, light, scalable photo indexer with automatic face and object recognition.

### How are we indexing?

We are indexing images by:

* Faces: using some fast 'face_recognition' library.

* Places: on a map and quering for names of location coordinates.

* Object recognition: using some YOLO v3 model or others.

* Others: tags will be added automatically or by hand (optional).

This implies if you search for `red car` you will get the results from the most  

matches to the least (till no matches).

### Performance

We are building a blazing fast and light server, in order to be able to run it  

on as many computers as possible. Even if they are old.

### Tools

We have chosen to build autofocus using:

* Python: the language I mostly speak.

* ReactJS: so our web is responsive, functional and scalable.

* Flutter: so our app feels native everywhere.

Obviously the tools are not everything. Code must be built efficiently.

### Install (development)

1. Install `face_recognition` from [here](https://github.com/ageitgey/face_recognition#installation) (dlib included).

2. Install requirements by `pip install -r requirements.txt`.

3. Deploy mongodb with `docker run -d --name mongo -p 27017:27017 -e MONGO_INITDB_ROOT_USERNAME=autofocus -e MONGO_INITDB_ROOT_PASSWORD=apassword mongo`

4. Edit the `.env` file for your setup.

5. Start developing!