Skip to content

Anchor free models #1

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

Closed
bhack opened this issue May 27, 2020 · 8 comments
Closed

Anchor free models #1

bhack opened this issue May 27, 2020 · 8 comments

Comments

@bhack
Copy link
Contributor

bhack commented May 27, 2020

Please evaluate to extract common components/utils that could support Anchor free models:
tensorflow/hub#424

See also:
google-ai-edge/mediapipe#495 (comment)
google-coral/edgetpu#51

@MatthAmoros
Copy link

Very naive questions here:

  1. Why would you like to implement an anchor free model in an industrial context ?
    AFAIK anchor model are widely used for label inspection as they give a very quick and reliable result.
  2. Have you considered adressing vision inspection problems (detect defects on products) or labeling only (read and check label information) ?

I would be very happy to discuss further on this subject, and maybe try to participate on this project, as I m currently trying to implement a (very humble) anchor based "old school" vision control library.

@tanzhenyu
Copy link
Contributor

Anchor free models are probably not in our immediate roadmaps yet. @fchollet WDYT?

@bhack
Copy link
Contributor Author

bhack commented Jun 15, 2020

@tanzhenyu At least it would have a bit of a way to diversify keras-cv compared to the model garden since almost all official anchor free papers implementations are in pytorch.

EDIT:
I meant that by an historical point of view model garden was more related to Google own research papers that on third_party research.

@tanzhenyu
Copy link
Contributor

@tanzhenyu At least it would have a bit of a way to diversify keras-cv compared to the model garden since almost all official anchor free papers implementations are in pytorch.

EDIT:
I meant that by an historical point of view model garden was more related to Google own research papers that on third_party research.

True -- but we'll focus on things not TF2/Keras implemented yet, such as semantic segmentation, DeepLab, etc. If this is in the long run outperforming anchor-based models, (as well as DETR I guess), then we'd need to consider having re-useable layers for them.

So "long run" is the vague word here, would it make more sense to put in addons?

@bhack
Copy link
Contributor Author

bhack commented Jun 15, 2020

but we'll focus on things not TF2/Keras implemented yet, such as semantic segmentation, DeepLab, etc

If you are talking about official models is true. But there are many third_party very good impl related to your list on Github.

@tanzhenyu
Copy link
Contributor

but we'll focus on things not TF2/Keras implemented yet, such as semantic segmentation, DeepLab, etc

If you are talking about official models is true. But there are many third_party very good impl related to your list on Github.

Yes -- and I'd like to consolidate the efforts. If that's already very good impl we should ask the author to migrate directly to this repo (or Keras-applications if it's backbone)

@bhack
Copy link
Contributor Author

bhack commented Jul 10, 2020

@tanzhenyu nevermind anchor-free just appeared in the new model garden object detection API (Centernet) https://github.com/tensorflow/models/tree/master/research/object_detection#tensorflow-2-support

@bhack
Copy link
Contributor Author

bhack commented Jul 10, 2020

@bhack bhack closed this as completed Aug 16, 2020
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Apr 13, 2022
LukeWood added a commit that referenced this issue Apr 20, 2022
* add fmix init commit

* fix issues try #1

* fix issues try #2

* change random generator to normal from uniform to support negative values

* add support for variable channels attempt 1

* update fftfreq description

* add changes

* add support for variable label shapes

* add changes

* fix errors

* remove newline

* change name to FourierMix attempt 1

* fixed lint issue

* remove edge softening

* Final pass

Co-authored-by: Luke Wood <lukewoodcs@gmail.com>
ianstenbit referenced this issue in ianstenbit/keras-cv Aug 6, 2022
* add fmix init commit

* fix issues try #1

* fix issues try #2

* change random generator to normal from uniform to support negative values

* add support for variable channels attempt 1

* update fftfreq description

* add changes

* add support for variable label shapes

* add changes

* fix errors

* remove newline

* change name to FourierMix attempt 1

* fixed lint issue

* remove edge softening

* Final pass

Co-authored-by: Luke Wood <lukewoodcs@gmail.com>
adhadse pushed a commit to adhadse/keras-cv that referenced this issue Sep 17, 2022
* add fmix init commit

* fix issues try keras-team#1

* fix issues try keras-team#2

* change random generator to normal from uniform to support negative values

* add support for variable channels attempt 1

* update fftfreq description

* add changes

* add support for variable label shapes

* add changes

* fix errors

* remove newline

* change name to FourierMix attempt 1

* fixed lint issue

* remove edge softening

* Final pass

Co-authored-by: Luke Wood <lukewoodcs@gmail.com>
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Oct 30, 2022
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Nov 3, 2022
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Jan 20, 2023
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Jan 29, 2023
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Feb 8, 2023
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Mar 22, 2023
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Mar 22, 2023
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Mar 27, 2023
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Mar 29, 2023
LukeWood pushed a commit that referenced this issue Apr 11, 2023
…d update iou losses (#1296)

* first attempt at introducing YoloX

* formatted and fixed bugs

* cast fix #1

* cast fix #2

* cast fix #3

* cast fix #4

* adding ensure shape for support

* reverting and removing ensure_shape

* fixed another bug

* updated train.py

* updated docs, tests and added support for loss strings

* first attempt at introducing YoloX

* formatted and fixed bugs

* adding ensure shape for support

* reverting and removing ensure_shape

* reformatted by black

* fixed a  linting issue

* finally rebased atop the recent changes

* finally rebased atop the new changes

* fixed linting issues

* reverted rebasing issues with iou loss

* fixing rebased errors part 2

* fixed more linting issues

* TPU testing changes

* linting fixes

* updated with implementation details from paper

* updated based on review comments and api changes

* first attempt at introducing YoloX

* updated docs, tests and added support for loss strings

* fixed linting issues

* reverted rebasing issues with iou loss

* review comments

* removed examples

* linting fix

* fixed rebasing error

* updated no_reduction warning

* review comments

* revert version and linting fixes
quantumalaviya added a commit to quantumalaviya/keras-cv that referenced this issue Apr 24, 2023
freedomtan pushed a commit to freedomtan/keras-cv that referenced this issue Jul 20, 2023
* Add numpy ops (initial batch) and some config

* Add unit test

* fix call

* Revert "fix call"

This reverts commit 6748ad183029ff4b97317b77ceed8661916bb9a0.

* full unit test coverage

* fix setup.py
ghost pushed a commit to y-vectorfield/keras-cv that referenced this issue Nov 16, 2023
…d update iou losses (keras-team#1296)

* first attempt at introducing YoloX

* formatted and fixed bugs

* cast fix keras-team#1

* cast fix keras-team#2

* cast fix keras-team#3

* cast fix keras-team#4

* adding ensure shape for support

* reverting and removing ensure_shape

* fixed another bug

* updated train.py

* updated docs, tests and added support for loss strings

* first attempt at introducing YoloX

* formatted and fixed bugs

* adding ensure shape for support

* reverting and removing ensure_shape

* reformatted by black

* fixed a  linting issue

* finally rebased atop the recent changes

* finally rebased atop the new changes

* fixed linting issues

* reverted rebasing issues with iou loss

* fixing rebased errors part 2

* fixed more linting issues

* TPU testing changes

* linting fixes

* updated with implementation details from paper

* updated based on review comments and api changes

* first attempt at introducing YoloX

* updated docs, tests and added support for loss strings

* fixed linting issues

* reverted rebasing issues with iou loss

* review comments

* removed examples

* linting fix

* fixed rebasing error

* updated no_reduction warning

* review comments

* revert version and linting fixes
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

No branches or pull requests

3 participants