Predictions using your model over videos from the database are coming to be wrong!

rezaghoddoosian / Early-Drowsiness-Detection

The supporting code used for the baseline temporal method on the UTA-RLDD dataset

https://sites.google.com/prod/view/utarldd/home

MIT License

71 stars 24 forks source link

Predictions using your model over videos from the database are coming to be wrong! #5

Open arnavw96 opened 4 years ago

arnavw96 commented 4 years ago

Using the model files you have provided, I have developed a testing code that generates inference over the videos from your database and I have tested it over video feed from the web camera as well. Most of the predictions are skewed towards the output '10' -> i.e. Drowsy person.

The results do not seem to align with the results that you have shown in your YouTube video.

Could you please share your testing file code so that we can be sure of the correctness of this pipeline?

rezaghoddoosian commented 4 years ago

I do not have the exact code which was used for that Youtube demo, however, that code was mostly the same code provided here, so you should be able to work it out using the provided code here to see sensible output. Be curious about why your results are wrong.