aws / aws/amazon-sagemaker-examples
[Bug Report] I cannot send paramters to get predicted result from tensorflow_script_mode_training_and_serving.ipynb
- Dominant language
- Jupyter Notebook
- Stars
- 11k
- Forks
- 7k
- Avg merge
- 8h 29m
- Merged PRs (30d)
- 8
Description
https://github.com/aws/amazon-sagemaker-examples/blob/main/sagemaker-python-sdk/tensorflow_script_mode_training_and_serving/tensorflow_script_mode_training_and_serving.ipynb
I try to run that notebook. Then, I'm facing with getting predicted result from the notebook example.
I didn't change the code following the orignal notebook but why it still shows error as below.

The line of problem is
`predictions = predictor.predict(train_data[:50])`
Contributor guide
Research direction
Start with sagemaker-python-sdk/tensorflow_script_mode_training_and_serving/tensorflow_script_mode_training_and_serving.ipynb and run the notebook through the failing predictor.predict(train_data[:50]) call. Inspect the linked screenshot and the notebook's training and serving setup to identify why the input parameters are rejected. Done means the unchanged example produces a predicted result from that call.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, tensorflow
- Domain
- cloud, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100