aws / aws/amazon-sagemaker-examples

blazingtext_word2vec_subwords_text8.ipynb failed CI

Open
#2,397 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
11k
Forks
7k
Avg merge
8h 29m
Merged PRs (30d)
8

Description

Link to the notebook:
https://github.com/aws/amazon-sagemaker-examples/blob/master/introduction_to_amazon_algorithms/blazingtext_word2vec_subwords_text8/blazingtext_word2vec_subwords_text8.ipynb

Error:

---------------------------------------------------------------------------
Exception encountered at "In [13]":
---------------------------------------------------------------------------
ModelError Traceback (most recent call last)
in
3 payload = {"instances" : words}
4
----> 5 response = bt_endpoint.predict(json.dumps(payload))
6
7 vecs = json.loads(response)

/opt/conda/lib/python3.7/site-packages/sagemaker/predictor.py in predict(self, data, initial_args, target_model, target_variant, inference_id)
134

[...]

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (415) from model with message "content-type application/octet-stream not supported". See https://us-west-2.console.aws.amazon.com/cloudwatch/home?region=us-west-2#logEventViewer:group=/aws/sagemaker/Endpoints/blazingtext-2021-05-11-00-14-09-104 in account 521695447989 for more information.

Contributor guide

Open the contributing guide

Research direction

Open introduction_to_amazon_algorithms/blazingtext_word2vec_subwords_text8/blazingtext_word2vec_subwords_text8.ipynb and inspect cell In[13], where the endpoint prediction fails. Run the notebook or its CI check and trace the SageMaker endpoint request; done means the prediction completes without the reported 415 content-type error and CI passes.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, jupyter-notebook, machine-learning
Domain
cloud, machine-learning, testing
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.