The goal of this project is to develop a computer vision model that solves some of the multiple tasks that the system of self-driving cars must execute to be able to drive autonomously. For this task, we are going to implement one of the best-known models in object detection which is YOLO. But we also want to see how this compares with another well recognized model called Faster R-CNN and thus see which of the two gives better results.
To be able to run the Faster R-CNN model, you will need to add the following folder to your own "My Drive" in Google Drive to be able to download the database used by it:
https://drive.google.com/drive/folders/1tItHnsPj146Q3ezhX72HNcHMDwg62jO5?usp=sharing
Then execute the file Faster_RCNN_2.ipynb
To be able to run the YOLO model, you will need to add the following folder to your own "My Drive" in Google Drive to be able to download the database used by it:
https://drive.google.com/drive/folders/1vszRdlsdA6zcZhxkFUOKWignr3VJmqVf
Then execute the file YOLOmain.ipynb