Hi! I’m trying to run Trt_pose on one of the DLA cores of the Xavier NX. However building the engine fails with: [TensorRT] ERROR: ../builder/cudnnBuilder2.cpp (1757) - Assertion Error in operator(): 0 (et.region->getType() == RegionType::kNVM) This is my code for building the engine (adapted fro…

Yes, the next release will be available late July, 2021.

Trt_pose on DLA

Autonomous Machines Jetson & Embedded Systems Jetson Xavier NX

AastaLLL March 16, 2021, 8:11am 9

Hi,

This is a known issue and first reported by Problem building TensorRT engines for DLA core.
We already fixed this in our internal branch and the fix will be available in the next major release.

Sorry for the inconvenience.
Thanks.

Topic		Replies	Views
DLA_STANDALONE error in forceToUseNvmIO Jetson AGX Xavier dla	15	1265	February 9, 2023
Convert model to TensorRT with DLA \| DLA Node compilation Failed TensorRT	3	908	October 12, 2021
Cannot create DLA engine using trtexec on Xavier Jetson AGX Xavier tensorrt , dla	8	997	July 1, 2022
Xavier NX does not support adaptative average pooling on DLA? Jetson Xavier NX tensorrt	27	1100	October 11, 2023
Cannot build a TensorRT engine for DLA from a large ONNX file Jetson Xavier NX tensorrt , nvbugs , dla	12	2613	July 21, 2021
Engine creation fails when using DLA with GPU fallback Jetson AGX Xavier tensorrt , dla	11	1923	March 22, 2022
Tensorrt Python API has a bug in DLA usage Jetson AGX Xavier tensorrt	11	626	August 17, 2022
API usage error of torch2trt on Jetson Orin nano Jetson Orin Nano pytorch	10	1427	September 12, 2023
Simple 2 layer U-Net breaks TensorRT conversion TensorRT	14	1245	October 12, 2021
[TRT] [E] 3: [builderConfig.cpp::canRunOnDLA::493] Error Code 3: API Usage Error on Jetson orin Nano Jetson Orin Nano tensorrt	25	1181	November 20, 2023

Trt_pose on DLA

Related topics