Driver Distraction Prediction Using Machine Learning”, where given driver images, each taken during a car with a driver doing something within the car (texting, eating, talking on the phone, makeup, reaching behind, etc). The goal was to predict the likelihood of what the driving force is doing in each picture.

Implementation Details

• DL Model – CNN’s build from scratch ( 6 Conv Layer, 5 Dropout Layer, 3 Dense Layer)
• Framework – Keras / Pytorch version in the process.
• CNN Model Visualization/Model Interpretability – GradCAM
• Final Accuracy -Train acc – 99.06%, Val acc-99 .46%