- You might have to modify the code to analyse custom video...
## Possible improvements
- The architecture is only a keras adaptation of the Darknet architecture and use the original with transfer learning might be more efficient.
- The architecture is only a keras adaptation of the Darknet architecture and using the original with transfer learning might be more efficient.
- A lot of new architecture have been released since YOLOV3 and could provide better results. It would be interesting to train model like CenterNet ResNet-18 or DSOD300 + VoVNet-27-slim.
- Only a few pictures has been labeled and with not that much diversity on the content. Create a larger dataset would make a more robust model.