A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”
I trained the object detector and notice the mAP is extremely low. Maybe due to the number of bboxes being detected without nms or post-processing. Is there another way to calculate mAP for the detector model?
I trained the object detector and notice the mAP is extremely low. Maybe due to the number of bboxes being detected without nms or post-processing. Is there another way to calculate mAP for the detector model?