Announcing ONNX Runtime Availability in the NVIDIA Jetson Zoo for High Performance Inferencing

Technical Blogs & Events Technical Blog
1

Originally published at: Announcing ONNX Runtime Availability in the NVIDIA Jetson Zoo for High Performance Inferencing | NVIDIA Technical Blog

Microsoft and NVIDIA have collaborated to build, validate and publish the ONNX Runtime Python package and Docker container for the NVIDIA Jetson platform, now available on the Jetson Zoo. Today’s release of ONNX Runtime for Jetson extends the performance and portability benefits of ONNX Runtime to Jetson edge AI systems, allowing models from many…

2

I believe that the sample you are providing is a CPU-based sample… right?

3

I got the following WARNINGS, is this the expected behavior

jflo@jflo-desktop:~$ python3 main.py
Preprocessed image shape: (1, 416, 416, 3)
2020-12-04 13:11:19.593957581 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_1/Conv2D
2020-12-04 13:11:19.594691089 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_8/Conv2D
2020-12-04 13:11:19.595566111 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_17/Conv2D
2020-12-04 13:11:19.597640591 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_38/Conv2D
2020-12-04 13:11:19.599664288 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_59/Conv2D
2020-12-04 13:11:19.601954034 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_94/Conv2D
2020-12-04 13:11:19.602434098 [W:onnxruntime:Default, cuda_execution_provider.cc:1498 GetCapability] CUDA kernel not supported. Fallback to CPU execution provider for Op type: Conv node name: StatefulPartitionedCall/model/conv2d_102/Conv2D
Output shape: (1, 52, 52, 3, 85)
jflo@jflo-desktop:~$
4

No update for 1.8.1 or 1.8.2?
I have problem with v 1.8.0 on Nano. With agx xavier runs well.

5

Hi @mapin.ai.project,

Can you please provide some details of your issue at Issues · microsoft/onnxruntime · GitHub?

Natalie