DeepStream-Yolo-Face icon indicating copy to clipboard operation
DeepStream-Yolo-Face copied to clipboard

Published 20 hours ago • verified publisher icon marcoslucianops

Unable to Run INT8 Engine for YOLOv8 Model

Open somindra-agrex opened this issue 8 months ago • 0 comments

Issue Description: I have tried to create an INT8 engine for my YOLOv8 model but have been unable to do so. I have followed all the steps provided in the deepstream-yolo GitHub repository. Despite this, I am still encountering issues.

Steps to Reproduce:

Follow the instructions in the deepstream-yolo repository to set up the environment. Attempt to create an INT8 engine for the YOLOv8 model. Expected Behavior: The INT8 engine should be successfully created and functional.

Actual Behavior: The process fails, and the INT8 engine is not created. WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1208 INT8 calibration file not specified. Trying FP16 mode.

Environment:

YOLOv8 Model DeepStream version 6.2 TensorRT version 8.5.1.7 CUDA version 11.8 GPU NVIDIA GeForce GTX 1080 OS Ubuntu 20.04.6 LTS

somindra-agrex avatar Jun 28 '24 07:06 somindra-agrex