Skip to content

Conversation

neginraoof
Copy link
Contributor

batched_nms needs to be scripted to capture the code flow and support export of model for images with no detection.

Copy link
Member

@fmassa fmassa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks Negin!

Let's wait until the PyTorch PR gets merged and CI is green before merging this.

I believe once support for numel() is added, we will be able to simplify a few things we did in the past that used numel().

@codecov-io
Copy link

codecov-io commented May 5, 2020

Codecov Report

Merging #2126 into master will not change coverage.
The diff coverage is n/a.

Impacted file tree graph

@@          Coverage Diff           @@
##           master   #2126   +/-   ##
======================================
  Coverage    0.48%   0.48%           
======================================
  Files          92      92           
  Lines        7433    7433           
  Branches     1133    1133           
======================================
  Hits           36      36           
  Misses       7384    7384           
  Partials       13      13           

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update c5ddf2b...c5ddf2b. Read the comment docs.

Copy link
Member

@fmassa fmassa left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks a lot!

@fmassa fmassa merged commit 3ac864d into pytorch:master May 7, 2020
fmassa pushed a commit to fmassa/vision-1 that referenced this pull request Jun 9, 2020
* Fixing nms on boxes when no detection

* test

* Fix for scale_factor computation

* remove newline

* Fix for mask_rcnn dynanmic axes

* Clean up

* Update transform.py

* Fix for torchscript

* Fix scripting errors

* Fix annotation

* Fix lint

* Fix annotation

* Fix for interpolate scripting

* Fix for scripting

* refactoring

* refactor the code

* Fix annotation

* Fixed annotations

* Added test for resize

* lint

* format

* bump ORT

* ort-nightly version

* Going to ort 1.1.0

* remove version

* install typing-extension

* Export model for images with no detection

* Upgrade ort nightly

* update ORT

* Update test_onnx.py

* updated tests

* Updated tests

* merge

* Update transforms.py

* Update cityscapes.py

* Update celeba.py

* Update caltech.py

* Update pkg_helpers.bash

* Clean up

* Clean up for dynamic split

* Remove extra casts

* flake8
@neginraoof neginraoof changed the title [ONNX] Fix model export for images w/ no detection [ONNX] Fix model export for images w/o detection Sep 18, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants