Description
When converting Mask-RCNN from onnx to trt trtexec
, the segfault (‘Segmentation fault (core dumped)’) happened. I check the size of tensor before resize is (1,1,30,30) and target is (1, 1, 275, 442). I used code base of torchvision when implementing Mask-RCNN. Any help would much appreciated!
Environment
TensorRT Version: 8.6.0.12-1+cuda11.8
GPU Type: 3060 Ti
Nvidia Driver Version: 530.30.02
CUDA Version: 12.1
CUDNN Version:
Operating System + Version: Ubuntu 20.04 LTS
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):
Relevant Files
ONNX file: LINK
Log of trtexec: LINK
Steps To Reproduce
./trtexec --onnx=maskrcnn.onnx --verbose