ucb-bar/onnxruntime-riscv

Refactoring: Use the recently added Relu int8 type

Open

#25 opened on Jan 27, 2021

View on GitHub
 (1 comment) (0 reactions) (0 assignees)C++ (37 forks)auto 404
enhancementgood first issue

Repository metrics

Stars
 (93 stars)
PR merge metrics
 (PR metrics pending)

Description

Currently we emit our own QLinearRelu type in the quantizer and do fusing based off of this. This was done to work around a previous deficiency in ONNX operators that Relu did not support int8. I recently submitted a PR to add Relu support which was recently merged in: https://github.com/onnx/onnx/pull/3141

We can now emit and use this type.

Contributor guide

Research direction
Study the upstream PR (onnx/onnx#3141) to understand the new Relu int8 type. Then, in the local quantizer code, replace the QLinearRelu type emission with the standard Relu op that now supports int8. Remove any fusing logic that was specific to the custom type. Also, update relevant tests.
Tech stack
cpp
Domain
backend
Issue type
Refactor
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
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.
Clear
Prerequisites
GitC++
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70