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

add occlusion sensitivity to 2d and 3d classifications #47

Merged
merged 3 commits into from
Oct 27, 2020

Conversation

rijobro
Copy link
Contributor

@rijobro rijobro commented Oct 20, 2020

Example of 2D occlusion sensitivity. Requires Project-MONAI/MONAI#1099

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>
@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>
@rijobro rijobro changed the title add occlusion sensitivity to 2d classification add occlusion sensitivity to 2d and 3d classifications Oct 20, 2020
@rijobro
Copy link
Contributor Author

rijobro commented Oct 21, 2020

Now that Project-MONAI/MONAI#1099 has been merged, this can go in, too.

The only problem is that the occlusion code isn't part of a tagged release yet, so presumably won't be available if the notebook contains, e.g.,:

%pip install -q monai

which the 2D classification tutorial does...

@wyli
Copy link
Contributor

wyli commented Oct 21, 2020

Now that Project-MONAI/MONAI#1099 has been merged, this can go in, too.

The only problem is that the occlusion code isn't part of a tagged release yet, so presumably won't be available if the notebook contains, e.g.,:

%pip install -q monai

which the 2D classification tutorial does...

that's a good point, one option would be pip install the tested commit directly

%pip install git+git://github.com/project-monai/monai.git@8169061cab567ec660373baa17136b916b00ab04

but if the notebooks depend on different commits this repo becomes messy... @ericspod @Nic-Ma

@rijobro
Copy link
Contributor Author

rijobro commented Oct 21, 2020

I would be in favour of removing the pip install monai altogether, it gets in the way of my local copy (not pip installed)!

@wyli wyli requested review from Nic-Ma and ericspod October 22, 2020 08:42
@ericspod
Copy link
Member

We do want to include tutorials into the future based on experimental features or at least those not on a current version. If we leave the pip install monai line as is we can put a note stating the version must at least be at a given commit or later, eventually when 0.4.0 is out we can modify the notebook to remove that. The alternative thing to do is like what would work for rijobro is not have the pip install anywhere and rely on the user to install things, I feel this is more common in the example notebooks I've seen across github and elsewhere rather than hard-coding the install process.

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>
@rijobro
Copy link
Contributor Author

rijobro commented Oct 27, 2020

I've moved the discussion of pip installs to issue #50, and in the meantime removed them from the notebook in this PR.

As such, think this is good to be merged.

@wyli wyli merged commit 0f7ac44 into Project-MONAI:master Oct 27, 2020
@rijobro rijobro deleted the occ_sens branch November 11, 2020 14:24
boneseva pushed a commit to boneseva/MONAI-tutorials that referenced this pull request Apr 21, 2024
)

* add occlusion sensitivity to 2d classification

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>

* add 3D occlusion example

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>

* remove pip installs

Signed-off-by: Richard Brown <33289025+rijobro@users.noreply.github.com>
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

3 participants