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

[Keras-Sprint] Modification of the UNet example #1404

Merged
merged 6 commits into from
Aug 2, 2023

Conversation

ariG23498
Copy link
Contributor

This PR is an effort to modify the Unet example with KerasCV.

Colab Notebook

CC: https://github.com/martin-gorner, https://github.com/margaretmz

@martin-gorner
Copy link
Contributor

Changes look good. Can you also post the latest Colab for review ? The one linked above does not seem to correspond to the PR (for ex. it has the Cosine decay LR still in it but commented out, which i do not see in the commit. Also the Colab uses PiecewiseConstantDecay which i do not see in the commit either.).

Copy link
Contributor

@ianstenbit ianstenbit left a comment

Choose a reason for hiding this comment

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

Thanks for the PR! This example is awesome -- thanks for your contributions to KerasCV to make this UX so nice 😄

"""
## What does one input image and corresponding segmentation mask look like?

key_rename_fn = lambda inputs: {
Copy link
Contributor

Choose a reason for hiding this comment

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

Is this the right name? It seems more like a rescaling / bias term operation

Copy link
Contributor Author

Choose a reason for hiding this comment

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

What would you suggest?

Copy link
Contributor

Choose a reason for hiding this comment

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

Maybe rescale_images_and_correct_masks?

@ianstenbit ianstenbit requested a review from fchollet June 27, 2023 17:46
@ariG23498
Copy link
Contributor Author

@fchollet over to you for the final review!

@martin-gorner
Copy link
Contributor

I worked with Aritra on this example. This is the final version.
LGTM

Copy link
Contributor

@martin-gorner martin-gorner left a comment

Choose a reason for hiding this comment

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

I worked with Aritra on this example. This is the final version.
LGTM

@ariG23498
Copy link
Contributor Author

@martin-gorner I have also added the generated files!

Copy link
Contributor

@ianstenbit ianstenbit left a comment

Choose a reason for hiding this comment

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

Nice -- I love to see the KerasCV augmentations and visualizations 👍

Copy link
Member

@fchollet fchollet left a comment

Choose a reason for hiding this comment

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

LGTM, thank you!

@fchollet fchollet merged commit 57e17ec into keras-team:master Aug 2, 2023
3 checks passed
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.

4 participants