Hacktoberfest 2026：维护者为十月标记出来的 issue，仍然开放、适合新手。 浏览 Hacktoberfest issue

Discrepancy in actual and expected output for subgraph test : batchNormalization options.axis=0 + gelu

未关闭
  • 哪里不对？
#950 3 条评论 1 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
15/100
Issue 类型
缺陷
描述清晰度
需要澄清
活跃度
活跃
技术栈
tensorflow
领域
machine-learning, testing

调研方向

Start from the subgraph conformance test that chains batchNormalization with options.axis=0 into gelu, using the inputs and expected values in the issue. Reproduce the ULP mismatch at index 4 on the CPU backend, then compare against the other backends the reporter tried. The thread asks the working group whether the tolerance or the expected values should change, so there is no code change to make until that decision is recorded. Done means a documented decision on the tolerance, plus either an updated threshold or a fix.

由索引模型根据 Issue 内容生成。

描述

Agenda+ web-platform-tests

Issue

I was running this conformance test for NVIDIA's TensorRT-RTX EP with ORT backend and encountered a failure.

Input:

bnInput     shape [3,1,2] float32 = [-1, 0, 1, 2, 3, 4]
bnMean      shape [3]     float32 = [0, 3, 6]
bnVariance  shape [3]     float32 = [1.0, 1.5, 2.0]

Graph:

batchNormalization(input=bnInput, mean=bnMean, variance=bnVariance, {axis: 0}) -> bnOutput
gelu(bnOutput) -> output

Expected output: shape [3,1,2] float32

[-0.15865567326545715, 0, -0.08366739749908447,
 -0.16910307109355927, -0.03595117852091789, -0.1112278625369072]

Error happens at index 4

actual -0.035951320081949234 should be close enough to expected -0.03595117852091789 by ULP distance: expected <= 24 but got 38

Observations

I tested this with other execution providers in ORT and other backends and encountered similar or same error.

Backend Actual ULP Difference
ORT CPU EP −0.035951320081949234 38
TFLite −0.035951387137174606 56
LiteRT (GPU) −0.035951387137174606 56

Question for the Working Group

  • What is the expected behavior for this test ?
  • Should the discrepancy between the actual and expected outputs be investigated, or is the current error tolerance too strict and in need of adjustment?
主要语言
Bikeshed
星标
566
派生
72
平均合并
6 天 5 小时
30 天内合并 PR
1

环境准备

  • 没有 Dockerfile 或 Docker Compose 文件
  • 没有 Pull Request 模板
  • 阅读贡献指南

从这里开始

  1. 先读完整个 Issue，再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库，在一个分支上完成修改。
  4. 提交 Pull Request，并在描述里引用这个 Issue 编号。

webmachinelearning/webnn 的其他 Issue

查看 webmachinelearning/webnn 的全部 Issue

相似的 Issue

更多 Machine Learning Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。