onnx/onnx

Spec: Clarify Transpose

Open

#4,611 opened on Oct 20, 2022

View on GitHub
 (5 comments) (0 reactions) (0 assignees)Python (3,585 forks)batch import
contributions welcomegood first issuequestiontopic: spec clarification

Repository metrics

Stars
 (16,592 stars)
PR merge metrics
 (Avg merge 1d 23h) (80 merged PRs in 30d)

Description

Ask a Question

Question

It is unclear what types of tensors Transpose accepts from the spec. For example, does it accept 1d or 0d tensors as inputs? If so can perm be an empty list? Is perm optional since it has words like "by default"? Does len(perm) need to be rank(input)?

Further information

  • Relevant Area: operators

  • Is this issue related to a specific model?

No

Notes

Contributor guide

Research direction
Examine the ONNX Transpose spec in the repository to clarify whether 0d/1d tensors are accepted, whether perm is optional, and the relationship between perm length and input rank.
Tech stack
python
Domain
machine learning
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
1
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
ONNX basicstensor operations
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80