NVIDIA-AI-IOT / CUDA-PointPillars

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

When I run./demo, I get an OutOfMemory and Cudnn (CUDNN_STATUS_EXECUTION_FAILED) error

windlinsherlock opened this issue · comments

Building TRT engine.
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 2: [virtualMemoryBuffer.cpp::resizePhysical::144] Error Code 2: OutOfMemory (no further information)
trt_infer: 1: [convolutionRunner.cpp::executeConv::465] Error Code 1: Cudnn (CUDNN_STATUS_EXECUTION_FAILED)
: engine init null!