The main goal of this project is the classification of sports images with a deep learning approach. The solution identifies, which sport appears on a given picture. There are currently different sports supported, like volleyball, badminton and chess. However, the range of supported sports is freely expandable.
- Nóra Almási (almasinori@gmail.com)
- Barnabás Börcsök (barnabas.borcsok@gmail.com)
For milestone 1 turn in, check out the milestone-1 tag in this repo.
We used this google collab notebook for the work. We uploaded the .ipynb notebook to the current repository.
- ~14000 pictures
- 22 labels
- actual image size varies
- image size read into opencv: 64x64, inter cubic interpolation
- badminton
- baseball
- basketball
- boxing
- chess
- cricket
- fencing
- football
- formula1
- gymnastics
- hockey
- ice hockey
- kabaddi
- motogp
- shooting
- swimming
- table tennis
- tennis
- volleyball
- weight lifting
- wrestling
- wwe
pip3 install tensorflow-gpu
pip3 install tensorflow
pip3 install matplotlib
pip3 install pandas
pip3 install numpy
pip3 install seaborn