I want to do Instance Segmentation using the images in my dataset which are already annotated and I don't want to train the model but use the pre-trained model. I was following this colab notebook. Here I can upload my image and do the instance segmentation. But the pre-trained model actually outputs the image with predicted bounding boxes and masks which is fine.
However, my questions are,
How do I use the pre-trained model for instance segmentation of an image with pre-defined bounding boxes, i.e. an array of coordinates (top left, bottom right, and class). How can I tell the model to segment objects which are inside that particular bounding box?
How can I save the mask coordinates and class in an output text/JSON file? I want that for further use.
