pytorch_torchvision_neo_on_Inf1.ipynb failed CI

Link to the notebook:
https://github.com/aws/amazon-sagemaker-examples/blob/master/sagemaker_neo_compilation_jobs/deploy_pytorch_model_on_Inf1_instance/pytorch_torchvision_neo_on_Inf1.ipynb

Error:

---------------------------------------------------------------------------
Exception encountered at "In [14]":
---------------------------------------------------------------------------
UnexpectedStatusException Traceback (most recent call last)
in
6 role=role,
7 job_name=compilation_job_name,
----> 8 compiler_options={"num-neuroncores": 2})

/opt/conda/lib/python3.6/site-packages/sagemaker/model.py in compile(self, target_instance_family, input_shape, output_path, role, tags, job_name, compile_max_run, framework, framework_version, targe

[...]

UnexpectedStatusException: Error for Compilation job TorchVision-ResNet18-Neo-Inf1-2021-05-11-00-11-05-495: Failed. Reason: ClientError: CompilationError: Unable to compile model for ml_inf1:', 'No operations were successfully partitioned and compiled to neuron for this model - aborting trace!')

Open sagemaker_neo_compilation_jobs/deploy_pytorch_model_on_Inf1_instance/pytorch_torchvision_neo_on_Inf1.ipynb and inspect the failing In [14] compilation call. Reproduce the CI failure and investigate the reported Inf1 compilation error. Done means the notebook completes its compilation job successfully in CI.

Written by the indexing model from the issue text.