tensorflow / tensorflow/recommenders

How to add "Instance Key" to basic retrieval model for batch predictions?

Open
#224 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2k
Forks
300
PR merge metrics
No merged PRs in 30d

Description

I'm using AI Platform Predictions to get batch predictions from a simple model (similar to https://www.tensorflow.org/recommenders/examples/basic_retrieval). This prediction service is outputting predictions with with no way to link them back to a user. This can be solved with "instance keys" (https://cloud.google.com/ai-platform/prediction/docs/overview#instance_keys), however I'm struggling to implement this in the model. Any suggestions/tips?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the linked TensorFlow Recommenders basic_retrieval example and the AI Platform Predictions instance-keys documentation. Determine how batch prediction outputs can be linked to users, then document a supported implementation or clearly state the limitation; no repository files or tests are named in the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
google-cloud, python, tensorflow
Domain
cloud, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.