pytorch-vgg19-bn.ipynb failed CI

Link to the notebook:
https://github.com/aws/amazon-sagemaker-examples/blob/master/sagemaker_neo_compilation_jobs/pytorch_vgg19_bn/pytorch-vgg19-bn.ipynb

Error:

---------------------------------------------------------------------------
Exception encountered at "In [11]":
---------------------------------------------------------------------------
ModelError Traceback (most recent call last)
in
2 start = time.time()
3 for _ in range(1000):
----> 4 output = vgg_predictor.predict(payload)
5 inference_time = (time.time()-start)
6 print('Inference time is ' + str(inference_time) + 'millisecond')

/opt/conda/lib/python3.6/site-packages/sagemaker/predictor.py in predict(self, data, initial_args, target_model, target_variant, inference_id)
134 data, initial_args, target_model, target_variant, inference_id
135 )
--> 136

[...]

". See https://us-west-2.console.aws.amazon.com/cloudwatch/home?region=us-west-2#logEventViewer:group=/aws/sagemaker/Endpoints/sagemaker-inference-pytorch-2021-05-11-00-03-12-980 in account 521695447989 for more information.

Start with sagemaker_neo_compilation_jobs/pytorch_vgg19_bn/pytorch-vgg19-bn.ipynb, focusing on In [11] where vgg_predictor.predict(payload) fails. Review the linked CloudWatch endpoint logs to identify the ModelError, then rerun the notebook to verify that inference completes successfully.

Written by the indexing model from the issue text.