SemLog Web is an integrated framework written in Python with a concise web UI that bridges between knownledge-based virtual environment and numerous computer vision models.
Go to "semlog_web/web/example" and click "DEMO.ipynb" to directly get a picture of SemLog Web's main features. You can also install dependencies to deploy the framework locally
You need to retrieve an instance of SemLog database to use this framework.
- Install Miniconda - Python 3.7 from https://docs.conda.io/en/latest/miniconda.html
- In "Advanced options", tick both options (Add Anaconda to my PATH environment)
- Note: You can test if Python is installed by enter "python" in your terminal.
- clone the repo
git clone https://github.com/robcog-iai/semlog_web.git
- Open a terminal with the project root path, run
pip install -r requirements.txt
To install all required libraries.
Install pytorch to enable real time model training. If you don't have a GPU, simply run
pip install torch==1.4.0+cpu torchvision==0.5.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
-
make sure the local MongoDB is running.
-
In the terminal, run
python manage.py runserver
To start the server.
- Open your browser and visit the website via the address "localhost:8000".
Open your browser and visit the website via the address "localhost:8000" to deploy it locally, or use
python manage.py runserver TARGET_IP
To deploy the website in local network
- Django - The web framework used
- MongoDB - The database used
- Pytorch - The deep learning framework used to build the detection demo
- Three.js - The UI JavaScript framework used for dynamic point cloud generation.
- Xiaoyue Zhang - Author - xinliy
This project is licensed under the BSD-3-Clause License
- This framework is developed by Xiaoyue Zhang in the Institute of Artificial Intelligence, University of Bremen, under the supervision of Andrei Haidu.