tensorflow / tensorflow/model-analysis

`GenericChangeThreshold` relative validation inconsistency

Open
#520 2 comments 0 reactions 1 assignee View on GitHub

@jeelania10 is already working on this.

Since Sep 2, 2026.

stat:awaiting response
Dominant language
Python
Stars
1.3k
Forks
280
PR merge metrics
No merged PRs in 30d

Description

The implementation of relative threshold validation doesn't align with the documented/expected behaviour.

From the docs:

Aboslute change is calculated as the value diference between the metrics of the candidate and baseline model, namely, v_c - v_b where v_c denotes the candidate metric value and v_b denotes the baseline value. Relative value is the relative difference between the metric of the candidate and the baseline, namely, v_c/v_b.

However, the implementation instead calculates (v_c - v_b) / v_b, NOT v_c/v_b as the docs very clearly state.
https://github.com/tensorflow/model-analysis/blob/422dbd37b31e286bda3311028b5d9ff7b76df7ac/tensorflow_model_analysis/evaluators/metrics_validator.py#L88

The easiest fix would be to update the docs to correctly describe the implementation, but I'm not sure what the desired behaviour actually is.

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.