Running yolox with relu activation on dla gives me incorrect result

Autonomous Machines Jetson & Embedded Systems Jetson Xavier NX
1

I try to run yolox inference on agx 32g device. if I use gpu with fp16, the engine can works perfectly. but if I run the engine on dla, the result is not correct.

I have tried with yolov5 wih leaky relu to run on the dla, the result is ok.

I use onnx to generate the tensorrt engine file

My Env:
jetpack 4.4
tensorrt 7.1.3
cuda 10.2
input shape: 1x832x480x3

P.S. I add transpose and div255 operation in the graph.

3

Hi,

Would you mind upgrade your software to the latest and try it again?
Thanks.

4

Sorry for the late replay. I have tried the jetpack 4.6.1

this time I failed to generate engine that run on dla core. the following error showed up during engine file generating process

DEBUG: --------------- Timing Runner: {ForeignNode[Concat_195...Conv_279]} (DLA)
Module_id 33 Severity 2 : NVMEDIA_DLA 684
Module_id 33 Severity 2 : Failed to bind input tensor. err : 0x00000b
Module_id 33 Severity 2 : NVMEDIA_DLA 2866
Module_id 33 Severity 2 : Failed to bind input tensor args. status:  0x000007
DEBUG: Deleting timing cache: 164 entries, 10 hits
INFO: [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +0, now: CPU 1055, GPU 6417 (MiB)
ERROR: 1: [nvdlaUtils.cpp::submit::198] Error Code 1: DLA (Failure to submit program to DLA engine.)
5

Hi,

Based on the error, it seems that some issue in the implementation.
Could you try the model with trtexec to see if it works?

$ /usr/src/tensorrt/bin/trtexec --onnx=[/path/to/the/model] --useDLACore=0

Thanks.

6

trtexec has worked. Maybe there are some misconfig in my builder. I will check.

7

Hi,

Just for your reference.
You can find the source of trtexec below:

Thanks.

9

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.