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

Unet #95

Open
wants to merge 4 commits into
base: dev
Choose a base branch
from
Open

Unet #95

wants to merge 4 commits into from

Conversation

jacob-rosenthal
Copy link
Collaborator

Add U-net, plus tests.
This is the model that they used in the PESO paper

Copy link
Contributor

@ryanccarelli ryanccarelli left a comment

Choose a reason for hiding this comment

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

Let's add to our contributing that models must reproduce baselines from paper before merge

* - :class:`~pathml.ml.unet.UNet`
- A standard general-purpose model designed for segmentation in biomedical images.
Architecture consists of an 4 encoder blocks followed by 4 decoder blocks.
Skip connections propagate information from each layer of the encoder to the corresponding layer in
Copy link
Contributor

Choose a reason for hiding this comment

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

layer of same dimension

- A model for simultaneous nucleus segmentation and classification in H&E images.
Architecture consists of a single encoder with three separate decoder branches: one to perform binary
classification of nuclear pixels (NP), one to compute horizontal and vertical nucleus maps (HV), and one which
is used in the classification setting to perform classification of nuclear pixels (NC).
Copy link
Contributor

Choose a reason for hiding this comment

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

verbose

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.

None yet

2 participants