TensorRT doesn't work with NVIDIA VIDEO CODEC SDK

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

I want to use NVIDIA VIDEO CODEC to decode video file.
Then, real-time detection was implemented with tensorrt.
but , if I do it , The tensorrt will report an error:

c:\p4sw\sw\gpgpu\MachineLearning\DIT\release.0\engine\cuda\caskConvolutionLayer.cpp (256) - Cuda Error in nvinfer1::rt::task::caskConvolutionLayer::execute: 33

This phenomenon is very strange.
I can use one of them alone without any problems, and use them together and you will get this error.

I hope to get the help of officials.

my environment:
gtx1050ti
win10
cuda10
cudnn7.3
tensorRT 5.0.4
NVIDIA VIDEO CODEC SDK 8.2

2

Hello,

cuda error 33 is a resource handle error. Indicates that a resource handle passed to the API call was not valid. Can you double check if you are appropriately managing cuda resources when decoding video and inferencing together?

3

Hello,

I have confirmed that the correct data has been obtained through NV decoding,
but, when I use it :

test_context->execute(BATCH_SIZE, test_buffers);

will get this error.
Before execution, I have finished:

test_context = test_engine->createExecutionContext();
test_context->setProfiler(&gProfiler);

I really don’t understand have anything about resource handle error.

Could you tell about more detail?

very thanks.

4

Hello,

this is certainly unexpected. To help us debug, an you share a small repro that demonstrates when using video SDK and TRT together you get the Cuda 33 error, and separately you don’t get the error?

5

Hello,

I want to share it.but it should be In what form to report to you?
The forums can’t upload the vs project.
Could you tell me in detail?

6

Hello,

you can either upload the files to a github, dropbox, or google drive and share the project with me, or attach files to devtalk (reference this post https://devtalk.nvidia.com/default/topic/1043356/tensorrt/attaching-files-to-forum-topics-posts/).

regards,
NVIDIA Enterprise Support

7

Hello,

I have upload on github.a Fastercnn sample based on tensorrt, contains nvidia decoder code(add by me).the decoder code also come from nvidia decode demo.https://github.com/hset911/tensorrt_decode_bug_Report.git,you can git clone it.
In sampleFasterRCNN.cpp, line 352-394 code is add by me.you can run it ,if you changge line 352:#if 0 ->#if 1,it is sampleFasterRCNN Original code.
by the way,if run I add code ,tensorrt’s doInference will be crash and report the bug:“ERROR: c:\p4sw\sw\gpgpu\MachineLearning\DIT\release\5.0\engine\cuda\cudaPoolingLayer.cpp (133) - Cudnn Error in nvinfer1::rt::cuda::PoolingLayer::execute: 8”,like I report bug.

I hope you can solve the problem as soon as possible.
thank you.

8

Hello,

  Did you follow up on this issue？
9

ERROR: cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 33

CUcontext cuContext = nullptr;
ck(cuCtxCreate(&cuContext, 0, cuDevice));

context = engine->createExecutionContext();
context->setProfiler(&gProfiler);

two context conflicts?

10

guys,
any update?
I have the same issue…ERROR: cuda/caskConvolutionLayer.cpp (256) - Cuda Error in execute: 33

thx

11

@NVES come on！