I want to change the prediction pipeline by modifying the non-max-suppression step in order to perform some tests. My final output should be a set of bounding boxes and a set of scoring vectors with a size of 1*C (C is the total number of classes of my dataset). However, I don't know how to do this since I cannot access to the pipeline of this trained model.
Is there any way to do this? Maybe by building a new model with my new pipeline and loading the trained weights somehow?
System information
Hello! I am loading (without any problem) a Faster RCNN model trained on the EPIC-KITCHENS dataset.
I want to change the prediction pipeline by modifying the non-max-suppression step in order to perform some tests. My final output should be a set of bounding boxes and a set of scoring vectors with a size of 1*C (C is the total number of classes of my dataset). However, I don't know how to do this since I cannot access to the pipeline of this trained model.
Is there any way to do this? Maybe by building a new model with my new pipeline and loading the trained weights somehow?
Thanks in advance!