DeepRegNet / DeepReg

Medical image registration using deep learning

Apache License 2.0

567 stars 77 forks source link

708 log more metrics in tensorboard #713

Closed mathpluscode closed 3 years ago

mathpluscode commented 3 years ago

Description

Fixes #708

Added

support for update_freq
TRE metric when data are labeled
stats (min/max/mean) on fixed/moving images/labels and DDF

Type of change

What types of changes does your code introduce to DeepReg?

Please check the boxes that apply after submitting the pull request.

[ ] Bugfix (non-breaking change which fixes an issue)
[ ] Code style update (formatting, renaming)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation Update (fix or improvement on the documentation)
[x] New feature (non-breaking change which adds functionality)
[ ] Other (if none of the other choices apply)

Checklist

Please check the boxes that apply after submitting the pull request.

If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your code.

[x] I have installed pre-commit using pre-commit install and formatted all changed files. If you are not certain, run pre-commit run --all-files.
[ ] My commits' message styles matches our requested structure, e.g. Issue #<issue number>: detailed message.
[x] I have updated the change log file regarding my changes.
[ ] I have added tests that prove my fix is effective or that my feature works
[ ] I have added necessary documentation (if appropriate)

mathpluscode commented 3 years ago

@YipengHu Adding images in tensorboard is a bit more complicated, thus I will leave that for another issue.

Otherwise, are these any other scalar metrics we may track?

codecov[bot] commented 3 years ago

Codecov Report

Merging #713 (45bddf1) into main (3b5a472) will not change coverage. The diff coverage is 100.00%.

@@            Coverage Diff            @@
##              main      #713   +/-   ##
=========================================
  Coverage   100.00%   100.00%           
=========================================
  Files           38        38           
  Lines         2426      2445   +19     
=========================================
+ Hits          2426      2445   +19

Impacted Files	Coverage Δ
deepreg/train.py	`100.00% <ø> (ø)`
deepreg/util.py	`100.00% <ø> (ø)`
deepreg/loss/label.py	`100.00% <100.00%> (ø)`
deepreg/model/layer.py	`100.00% <100.00%> (ø)`
deepreg/model/network.py	`100.00% <100.00%> (ø)`

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 3b5a472...45bddf1. Read the comment docs.

mathpluscode commented 3 years ago

@YipengHu @NMontanaBrown would you have time for this :)

YipengHu commented 3 years ago

@YipengHu @NMontanaBrown would you have time for this :)

will get to this today. Nina is away.

YipengHu commented 3 years ago

I think we need to add Dice(binary=True) as a metric for all labelled data, regardless if it is used for loss - you can still report Dice(Binary=False) as a metric if it is used as a loss. Does it makes sense? @mathpluscode