This week, I mostly worked together with my teammates on fixing the dispenser. We identified various hurdles compromising our overall progress towards integrating the whole system. On my end, I was able to complete training the model, making it achieve an average of 95% confidence on all the cards. This was very consistent and I was confident that the card detection part of the system is production ready. However, as the dispenser wasn’t functioning well, we went through various fixes that essentially created some gaps between the previous card detection model training environment. While the dispenser is still not perfect, we’re planning to move on to integrating all the components.
Next week, I will have to see if the old model performs well on the new dispenser environment. If it fails to do so, I will have to train the model again by collecting new data on the new environment.