ONNX model deployment issues on Jetson TX2

Autonomous Machines Jetson & Embedded Systems Jetson TX2
1

I am importing a pertained resnet50 onnx model and running on Jetson TX2. I have Jetpack 4.2 installed on TX2. I am able to import the ONNX file create TRT model, deploy and run inference on TX2 if ONNX model is opset_3. But I get errors if Resnet50 ONNX model is Opset_6 or above. I tried to convert the Opset using the ONNX converter, no luck the conversion to lower Opset itself fails.

https://s3.amazonaws.com/download.onnx/models/opset_3/resnet50.tar.gz . (Works fine)

https://s3.amazonaws.com/download.onnx/models/opset_6/resnet50.tar.gz (does not work)

I tried to upgrade TensorRT and ONNX with no luck. I thought it is not a good idea to upgrade without using Jetpack.

2

Hi,

TensorRT 5.0 of JetPack4.2 supports opset-7.
Would you mind to upgrade the device into JetPack4.2 and try it with opset-7’s model?
[url]https://s3.amazonaws.com/download.onnx/models/opset_7/resnet50.tar.gz[/url]

Thanks.

3

I already have Jetpack4.2 on my Jetson. It does not work.

4

Thanks, now Opset7 works for me now with TensorRT on jetson. But pytorch exports Opset9 and I have difficulty converting the ONNX Opset9 to Opset7. Here is the error:

converted_model = version_converter.convert_version(inferred_model, 7)
File “/home/user/miniconda/envs/py36/lib/python3.7/site-packages/onnx/version_converter.py”, line 166, in convert_version
converted_model_str = C.convert_version(model_str, target_version)
RuntimeError: /tmp/pip-req-build-jcsc1lyi/onnx/version_converter/BaseConverter.h:60: adapter_lookup: Assertion false failed: No Adapter For Current Version $9 for BatchNormalization

5

Hi,

Opset-9 is supported from TensorRT-5.1 but not available for Jetson yet.
[url]https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html#api[/url]

Please wait for our update and release.
Thanks.

6

Any info on when this release would be available?

Thanks

7

Hi,

Sorry that we cannot release our further plan here.
Please pay attention to our announcement for the new release.

Thanks.

8

Can you provide any method to convert opset-9 to opset-7. Or controlling the opset version while converting from pytorch?