Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Specify axis parameter for DequantizeLinear when input rank is 1 #6095

Merged
merged 1 commit into from May 6, 2024

Conversation

isdanni
Copy link
Contributor

@isdanni isdanni commented Apr 21, 2024

Description

Close #6067

@isdanni isdanni requested a review from a team as a code owner April 21, 2024 23:47
Copy link

codecov bot commented Apr 21, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 57.04%. Comparing base (83194ed) to head (7a1783b).
Report is 31 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #6095      +/-   ##
==========================================
+ Coverage   56.95%   57.04%   +0.08%     
==========================================
  Files         506      506              
  Lines       30467    30935     +468     
  Branches     4592     4592              
==========================================
+ Hits        17353    17646     +293     
- Misses      12285    12463     +178     
+ Partials      829      826       -3     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@isdanni isdanni force-pushed the specify-axis-dequantizelinear branch 4 times, most recently from f446e84 to 94f611f Compare April 22, 2024 12:13
@justinchuby
Copy link
Contributor

Could you update

and
"(Optional) The axis of the dequantizing dimension of the input tensor. Ignored for per-tensor quantization. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(input).",
? The md files will be auto updated.

@isdanni isdanni force-pushed the specify-axis-dequantizelinear branch 3 times, most recently from 139a24a to de2f0fb Compare April 23, 2024 13:18
@justinchuby justinchuby added documentation Issues related to ONNX documentation spec clarification Clarification of the ONNX spec needed labels Apr 23, 2024
@justinchuby justinchuby added this to the 1.17 milestone Apr 23, 2024
@justinchuby justinchuby added the auto update doc Generate md/proto files automatically using the CI pipeline label Apr 23, 2024
@justinchuby justinchuby reopened this Apr 23, 2024
@justinchuby justinchuby added review needed: operators approvers Require reviews from members of operators-approvers and removed auto update doc Generate md/proto files automatically using the CI pipeline labels Apr 23, 2024
@justinchuby justinchuby reopened this Apr 23, 2024
@justinchuby justinchuby enabled auto-merge May 4, 2024 01:57
@justinchuby justinchuby disabled auto-merge May 4, 2024 01:57
@isdanni isdanni force-pushed the specify-axis-dequantizelinear branch from 77c4cf9 to ce11acd Compare May 6, 2024 01:04
@isdanni isdanni requested a review from a team as a code owner May 6, 2024 01:04
@isdanni isdanni force-pushed the specify-axis-dequantizelinear branch 3 times, most recently from 8c66c0e to 6e1e224 Compare May 6, 2024 02:09
Signed-off-by: isdanni <leedanni@gmail.com>
@isdanni isdanni force-pushed the specify-axis-dequantizelinear branch from cba8f22 to 7a1783b Compare May 6, 2024 02:19
@justinchuby justinchuby added this pull request to the merge queue May 6, 2024
Merged via the queue into onnx:main with commit 09dc4ab May 6, 2024
39 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Issues related to ONNX documentation review needed: operators approvers Require reviews from members of operators-approvers spec clarification Clarification of the ONNX spec needed
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

Clarify default value of axis for DequantizeLinear when input rank is 1
4 participants