Failed to build tensorrt engine with DLA enabled on Jetson Xavier NX

[harishkool]

Description

TensorRT engine build failed with error Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[/cnn/cnn.0/Conv]}.

Environment

TensorRT Version: 8.5.2

NVIDIA GPU: Volta GPU

CUDA Version: 11.4

CUDNN Version: 8.6

Operating System: Ubuntu 20

Platform : Jetson Xavier NX

Relevant Files

Model link: https://drive.google.com/file/d/1K5kQxR0IR-SGF6Ry1V44R-bmfwF4NPPx/view?usp=sharing

Steps To Reproduce

1. Took the example model from https://github.com/NVIDIA-AI-IOT/jetson_dla_tutorial
2. Exported the model to onnx format.
3. Tried building the engine with the command /usr/src/tensorrt/bin/trtexec --onnx=model_gn.onnx --shapes=input:32x3x32x32 --saveEngine=model_gn.engine --exportProfile=model_gn.json --int8 --useDLACore=0 --allowGPUFallback --useSpinWait --separateProfileRun
4. Build failed with the error Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[/cnn/cnn.0/Conv]}
5. You can check the complete log here https://drive.google.com/file/d/1Ude0Pb3VOb_rzJhbzu_AXtlk8HUUNbzT/view?usp=drive_link

Have you tried the latest release?: N/A

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt): Yes

[lix19937]

try to

/usr/src/tensorrt/bin/trtexec --onnx=model_gn.onnx --shapes=input:32x3x32x32 --saveEngine=model_gn.engine --exportProfile=model_gn.json --best --useDLACore=0 --allowGPUFallback --useSpinWait --separateProfileRun

[harishkool]

Same

[05/10/2024-12:14:41] [E] Error[10]: [optimizer.cpp::computeCosts::3728] Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[/cnn/cnn.0/Conv]}.)
[05/10/2024-12:14:41] [E] Error[2]: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
[05/10/2024-12:14:41] [E] Engine could not be created from network
[05/10/2024-12:14:41] [E] Building engine failed
[05/10/2024-12:14:41] [E] Failed to create engine from model or file.
[05/10/2024-12:14:41] [E] Engine set up failed

You can find the verbose log here https://drive.google.com/file/d/17o5k7_1ZPEd_iNScTUOKKRsa167VWjWs/view?usp=drive_link.

[lix19937]

Check your conv layer match condition or not ? The layer support and restrictions to the specified layers while running on DLA, see https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#dla-lay-supp-rest

On the other way, you can update the latest version of trt.

[harishkool]

I took the example model from Jetson DLA tutorial https://github.com/NVIDIA-AI-IOT/jetson_dla_tutorial, it supports.

[harishkool]

Any updates on this issue ?