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

Support semantic segmentation downstream evaluation tasks #517

Merged
merged 26 commits into from
Jun 25, 2024
Merged

Support semantic segmentation downstream evaluation tasks #517

merged 26 commits into from
Jun 25, 2024

Conversation

ioangatop
Copy link
Collaborator

Closes #402

@ioangatop
Add simple decoder networks for segmentation tasks (#404)
2b5a1ce
@ioangatop
Add timm encoder networks (#403)
a7e65e5
@ioangatop
Add SemanticSegmentation module (#410)
ad392e8
@ioangatop
Add TotalSegmentator2D segmentation downstream task (#413)
4ef3afb
@ioangatop
Add dice score in TotalSegmentator2D task (#423)
07fbd08
@ioangatop
Allow to use subclasses in TotalSegmentator2D (#435)
a6fd246
@ioangatop
Create a callback to visualise the segmentation results (#424)
db5a578
@ioangatop
Improve the mask loading in TotalSegmentator2D (#440)
7656ae6
@ioangatop
Add per class metrics dice score in TotalSegmentator2D (#447)
702f634
@ioangatop
Support int16 training on TotalSegementator2D (#443)
434cacb
@ioangatop
Normalisations and transforms for int16 image types (#457)
35bb532
@ioangatop
Fix default segmentation metrics (#503)
c43b8ad
@ioangatop
Add support for multi-level embeddings training in segmentation tasks (…
b009aec 
…#501)
@ioangatop
merge with main
19c92cd
@ioangatop
update with main
cf54cad
@ioangatop
Add dataset licence and env var for dataset download (#516)
cfa47c9
@ioangatop ioangatop added vision Changes regarding the vision part of the library radiology Radiology related features aggregated-feature labels Jun 10, 2024
@ioangatop ioangatop self-assigned this Jun 10, 2024
@ioangatop ioangatop marked this pull request as ready for review June 10, 2024 12:58
nkaenzig
nkaenzig reviewed Jun 12, 2024
View reviewed changes
Copy link
Collaborator

@nkaenzig nkaenzig left a comment

Choose a reason for hiding this comment

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

Amazing work! 🚀
I only left some minor comments. The main thing missing is probably the documentation (mkdocs). It'd be nice to also have an overview there over the different decoders that are supported, with a brief explanation of how they work.

pyproject.toml Show resolved Hide resolved
src/eva/core/metrics/defaults/segmentation/multiclass.py Show resolved Hide resolved
src/eva/vision/models/networks/from_timm.py Show resolved Hide resolved
@roman807 roman807 mentioned this pull request Jun 24, 2024
Closed
@ioangatop ioangatop merged commit 36c1b4e into main Jun 25, 2024
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@roman807 roman807 roman807 left review comments

@nkaenzig nkaenzig nkaenzig approved these changes

Assignees

@ioangatop ioangatop

Labels
aggregated-feature radiology Radiology related features vision Changes regarding the vision part of the library
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[Aggregated Feature] Segmentation downstream evaluation tasks
3 participants
@ioangatop @roman807 @nkaenzig