-
Notifications
You must be signed in to change notification settings - Fork 102
NEW: Add SCCNN Cell Detection Architecture #434
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
Conversation
shaneahmed
commented
Jul 27, 2022
- Add SCCNN architecture.
- Add SCCNN architecture.
- Add docs to SCCNN architecture.
Codecov Report
@@ Coverage Diff @@
## develop #434 +/- ##
===========================================
+ Coverage 98.59% 98.62% +0.02%
===========================================
Files 58 59 +1
Lines 5784 5872 +88
Branches 1047 1049 +2
===========================================
+ Hits 5703 5791 +88
Misses 69 69
Partials 12 12
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
- Add preproc function to sccnn.py.
- Add infer_batch function to sccnn.py.
- Add postproc function to sccnn.py.
- Add tests for sccnn.py.
- Code refactoring
for more information, see https://pre-commit.ci
- Fix docstring and typo.
…ature-sccnn-detection
- Remove redundant function.
- Update documentation.
- Update model.
…ature-sccnn-detection
- Fix docstring.
John-P
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for adding this model! Looks good but I think some of the function names, especially for the layers and a bit inconsistent and vague. More verbose but helpful names would improve the readability and maintainability of the code.
- Refactor functions to meaningful names.
- Refactor variables to meaningful names.
John-P
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good, just some type hint, docstring, and formatting suggestions.
- Adds information for tests in docstring.
- Fixing type hint, docstring, and formatting.
- Fix G200 Logging statement uses exception.
- Fix Unsupported operand |.
- Update sccnn-conic
- Fix docstring.
- Fix sccnn docstring.
Update tiatoolbox/models/architecture/sccnn.py
John-P
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good. I like Dang's suggestion of moving the spatially constrained layer into its own class (easier to re-use), but otherwise good. Happy either way.
I had discussed this with Dang earlier. This meant retraining the model separately. So we decided not to do this. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks Shan for revising this code. All look good now.
I just add a comment about moving the preprocessing into Forward method (I made the same suggestion for MapDe as well). I'm happy for you to merge the branch after that change :-)
- Use self._transform for converting image to float.