In this part of the homework, you will use Pytorch and Detectron2 to design a deep network to perform instance segmentation of planes in images. You are provided with a baseline config in your Github repository and you will work on improving the framework and fine-tuning the hyper-parameters to improve the IoU the network.

Goal: Get hands-on experience designing and training segmentation and detection networks using PyTorch and Detectron2.

Note that the number of submissions is limited to a few times per day, so try to tune your model before uploading CSV files. Also, you must make at least one submission for your final system. The best performance will be considered.