β βΆ Analyzing your Twitch videos π¬
β β· Giving you a list of highlights back π
β βΈ Taking care of your values π
Requirements
Python : 3.7.0 or later (3.6 may compatible)
Opencv-Python : 4.0.0 or later
Twitch-Chat-Downloader : 3.1.0 referenc link
- Clone this repo to your local machine using
https://github.com/highlightu/server.git
- Later on
To install the current release for Ubuntu server.
sudo apt update
sudo apt install git python3-venv libsm6 libxext6 libxrender1 ffmpeg
git clone https://github.com/highlightu/server.git
cd server/
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
Add your public IP or DNS to allow hosts.
$ vim django_capstone/settings
ALLOWED_HOSTS = [
'ADD YOUR PUBLIC IP or DNS',
'localhost',
'127.0.0.1',
]
This service provides with google login.
So, you have to activate GOOGLE+ API,
and to create OAuth 2.0 Client as a 'web application',
and get API Key/Secret
$ vim Bash_dir/envs.json
{
"GOOGLE_KEY": "YOUR API_KEY",
"GOOGLE_SECRET": "YOUR API_SECRET"
}
$ python manage.py makemigrations
$ python manage.py migrate
$ python manage.py runserver 0.0.0.0:8080
Now, you can use HighlightU service
π Chat analyze
Download a chatlog of a given Twitch video URL.
Analyze it by scoring each time with labeled words.
π² Face recognition
Check resized frames in the video whether there are detected faces.
Use Residual Network model to get face expression percentages
- Check out Final Report
- Check out Use-case scenario
- This will help you use this service from beginning
-
Option 1
- π΄ Fork this repo!
-
Option 2
- π― Clone this repo to your local machine using
https://github.com/highlightu/server
- π― Clone this repo to your local machine using
- HACK AWAY! π¨π¨π¨
- π Create a new pull request
JISU AN | ZINU JEON | HYUNJAE LEE |
---|---|---|
github.com/ajs7270 |
github.com/zinuzian |
github.com/hyunjae-lee |
- MIT license
- Copyright 2019 Β© LAJI