Tensorflow + OpenCV web application
The web app support the listing function on the organization's Official trading photocard website by helping seller to classifying their products into appropriate category
The app contains a few key features:
- Classifying most of SEVENTEEN photocards into provided categories
- Identifying K-pop group members' faces from these groups: Blackpink, SEVENTEEN, Big Bang
- Identify photocard's faces, smile, eyes
- Adjust photocard colors grading
 |
 |
 |
|---|---|---|
| Classify photocards category | Identify Idol face and group | Edit photocard image |
We used Python 3.8 or conda using Python 3.8, Pycharm as an IDE installed on our system. No other software or libraries required.
- Clone the forked repo to your local machine using the IDE of your interest (we used Pycharm here).
git clone https://github.com/Kronicle-team/ml-web-app.git- Ensure that you have the prerequisite Python libraries installed on your local machine:
pip install -r requirements.txt- Navigate to the base of the cloned repo, and start the Streamlit app.
cd ml-web-app/
streamlit run app.py- If the web server was able to initialise successfully, the following message should be displayed within your bash/terminal session:
You can now view your Streamlit app in your browser.
Local URL: http://localhost:8501
Network URL: http://192.168.43.41:8501
You should also be automatically directed to the base page of your web app. This should look something like:
ml-web-app
│
├── .streamlit
│ └── config.toml
│
├── app
│ ├── main.py
│ └── utils.py
│
├── assets
│ ├── background.png
│ └── icon.png
│
├── data
│
└── requirements.txt
│
└── test
├── test_app.py
Our app was built with Streamlit - a completely free and open-source and licensed under the Apache 2.0 license.
- Papers
Label Propagation:
Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2019). Label propagation for deep semi-supervised learning. https://arxiv.org/pdf/1904.04717.pdf