Factorization Machines Inference Sparse Matrix

[ChandraLingam]

Please fill out the form below.

System Information

• Framework (e.g. TensorFlow) / Algorithm (e.g. KMeans): SageMaker/Factorization Machines
• Framework Version:
• Python Version:
• CPU or GPU:
• Python SDK Version:
• Are you using a custom image:

Describe the problem

I was able to train the model with sparse matrix recordIO file created with sagemaker python sdk. For inference, looks like JSON and RecordIO are supported.

If I want to use to JSON, how should I pass in the sparse matrix information? Ideally, it is preferable to send only the columns for which values exist.

For example: 623:1 3399:1

Thank you for the prompt help so far

Minimal repro / logs

Please provide any logs and a bare minimum reproducible test case, as this will be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.

• Exact command to reproduce:

[ChandraLingam]

I did find a reference to sparse matrix inference format.
https://docs.aws.amazon.com/sagemaker/latest/dg/cdf-inference.html

Closing this issue