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.

Sign up for GitHub

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

Jump to bottom

Posterize preprocessing layer #84

Closed
LukeWood opened this issue Feb 2, 2022 · 2 comments
Closed

Posterize preprocessing layer #84

LukeWood opened this issue Feb 2, 2022 · 2 comments
Assignees
@sebastian-sz
Labels
preprocessing
Projects
Keras CV 0.1 release

Comments

@LukeWood
Copy link
Contributor

LukeWood commented Feb 2, 2022

https://github.com/tensorflow/similarity/blob/906d141b75acf00d0e1d37dd0d88c432bbb30f57/tensorflow_similarity/augmenters/img_augments.py#L494
@sebastian-sz
Copy link
Contributor

I think PIL implementation assumes uint8 dtype, and TF's bitwise ops only support integers.

Is it safe to assume that this layer's input will only accept integer values in range 0-255? Or should it accept any dtype, cast internally to uint8, posterize and cast back to original dtype?

@sebastian-sz sebastian-sz mentioned this issue Feb 15, 2022
Merged
@qlzh727 qlzh727 added this to To Do in Keras CV 0.1 release Mar 22, 2022
@qlzh727 qlzh727 moved this from To Do to In progress in Keras CV 0.1 release Mar 22, 2022
@LukeWood
Copy link
Contributor Author

Thanks so much @sebastian-sz

@qlzh727 qlzh727 moved this from In progress to Done in Keras CV 0.1 release Mar 23, 2022
@bhack bhack mentioned this issue May 4, 2022
Open
freedomtan pushed a commit to freedomtan/keras-cv that referenced this issue Jul 20, 2023
@AakashKumarNain
Add Dot layer (keras-team#84)
18e5267 
* add base merge layer

* format docstrings

* add  layer

* add test cases for  layer

* Add import for  layer

* fix build function

* add dynamic and static tests

* fix pytest import

* fix pytest decorator

* remove batch size from dynamic shape test

* fix keras reference

* refactor test class

* fix tf tests, and linting issues

* add subtract layer

* add tests for subtract layer

* fix linting issues

* add average layer

* add maximum layer

* dd minimum layer

* add multiply layer

* add tests for average, minimum, maximum, and multiply layers

* add concatenate layer

* add dot layer

* add tests for dot layer

* format files

* fix tests

* fix bug in concatenate layer

* fix build method

* add missing tests for concatenate layer and dot layer
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@sebastian-sz sebastian-sz

Labels
preprocessing
Projects
No open projects
Keras CV 0.1 release
Done
Milestone
No milestone
Development

No branches or pull requests
2 participants
@LukeWood @sebastian-sz