Megvii-BaseDetection / YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Significant Increase in Initialization Time for YOLOX TensorRT Model on NVIDIA-Jetson Nano 4gb

fyzanahammad opened this issue · comments

After converting the YOLOX model to TensorRT, the initialization time on an NVIDIA Jetson Nano 4GB has unexpectedly increased from 1:30 minutes to approximately 5 minutes over a period of time. The pytorch model was converted into tensorRT using the trt module provided by yolox tools that outputs a model_trt.pth file. Is this issue related to caching of yolox?