Op registered for Upsample is depracted in domain_version of 10 error from running yolov3_to_onnx.py

Hello,

I am attempting to follow the instructions in Object Detection With The ONNX TensorRT Backend In Python (https://docs.nvidia.com/deeplearning/sdk/tensorrt-sample-support-guide/index.html#yolov3_onnx) in a container from TensorRT docker image pulled using

docker pull nvcr.io/nvidia/tensorrt:19.06-py3

I got the below error when trying to run

python yolov3_to_onnx.py
Traceback (most recent call last):
  File "yolov3_to_onnx.py", line 812, in <module>
    main()
  File "yolov3_to_onnx.py", line 805, in main
    onnx.checker.check_model(yolov3_model_def)
  File "/usr/local/lib/python2.7/dist-packages/onnx/checker.py", line 86, in check_model
    C.check_model(model.SerializeToString())
onnx.onnx_cpp2py_export.checker.ValidationError: Op registered for Upsample is depracted in domain_version of 10

==> Context: Bad node spec: input: "085_convolutional_lrelu" input: "086_upsample_scale" output: "086_upsample" name: "086_upsample" op_type: "Upsample" attribute { name: "mode" s: "nearest" type: STRING }

Anyone have any clues?

Thank you in advance for the help

Solved the problem via using nvcr.io/nvidia/tensorrt:19.06-py2 and downgrading onnx to version 1.4.1