Abhishek AgrawalCan we take product level decisions based on mAP accuracy?To evaluate object detection models like YOLOv5, YOLOV8 and DETR, the mean average precision (mAP) is used. The mAP compares the…Aug 15, 2023Aug 15, 2023
Abhishek AgrawalWhy Torch Inference in slower than ONNX and TensorRT ?Have you ever wondered 1. Why you don’t need model class to run ONNX or TensorRT inference but you need one to run PyTorch inference ?Aug 8, 20231Aug 8, 20231
Abhishek AgrawalYolact++ Pytorch to ONNX & TensorRTYolact++, which is a very efficient model for object detection and Instance segmentation but the model has to go to production as well in…Aug 7, 2022Aug 7, 2022
Abhishek AgrawalIf this holds true then what are the reasons of our inability to get very high accuracies even with…Apr 30, 20212Apr 30, 20212