The cocoeval is a goto evaluation script for calculating mAP across various IoUs. However, it doesn't provide class-wise accuracies. I'd like to use another repository for performing evaluation. However, the code expects two flat files. One with ground truths and another with predictions. Each line of both files should be of this format
<class_name> <left> <top> <right> <bottom>
How can I get this by modifying the cocoeval function?
