Bounding Box issue

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

Description

As can been seen from image bounding boxes are distorted.

Environment

TensorRT Version: 7.3.1
GPU Type: AGX Xavier
Nvidia Driver Version: jetpack 4.5.1
CUDA Version: 10.2
CUDNN Version: 7.5.0
Operating System + Version:
Python Version (if applicable): 3.6
PyTorch Version (if applicable): 1.5.0
Baremetal or Container (if container which image + tag):

imager
imager1920×1080 384 KB

Relevant Files

Steps To Reproduce

2

Hi,

We recommend you please post your concern on Issues · Tianxiaomo/pytorch-YOLOv4 · GitHub to get better help.
Also please use the latest TensorRT version 8.4 EA for better results.

Thank you.