Giters

hova88 / PointPillars_MultiHead_40FPS

A REAL-TIME 3D detection network [Pointpillars] compiled by CUDA/TensorRT/C++.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

GPUassert: an illegal memory access

serser opened this issue · comments

commented

compiled under cuda-11, tensorrt 8.2

$ ./test/test_model
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from PointPillars
[ RUN      ] PointPillars.__build_model__
../model/cbgs_pp_multihead_backbone.trt
 |￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣>
 | ../model/cbgs_pp_multihead_pfe.trt >
 |＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿>
             (\__/) ||
             (•ㅅ•) ||
             /   づ
WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.1 but loaded cuBLAS/cuBLAS LT 11.2.0
WARNING: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.3
 |￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣>
 | ../model/cbgs_pp_multihead_backbone.trt >
 |＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿>
             (\__/) ||
             (•ㅅ•) ||
             /   づ
WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.1 but loaded cuBLAS/cuBLAS LT 11.2.0
WARNING: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.3
WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.1 but loaded cuBLAS/cuBLAS LT 11.2.0
WARNING: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.3
WARNING: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.1 but loaded cuBLAS/cuBLAS LT 11.2.0
WARNING: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.3
ERROR: 1: [genericReformat.cu::executeMemcpy::1334] Error Code 1: Cuda Runtime (invalid argument)
GPUassert: an illegal memory access was encountered /home/work/pointpillars_multihead_40fps/pointpillars/pointpillars.cc 420
commented

No avail with all version warning removed. Turned out to be wrong trt engine used. 😂