Added blending probability maps with original WSI

[sarthakpati]

Fixes #464

Proposed Changes

• blending option added with default alpha of 0.5 with option to specify in config with the option blending_alpha
• added a new colormap agni that is pure red and black for easier visualization
• includes Update data type for stride size #458

Checklist

• I have read the CONTRIBUTING guide
• My PR is based from the current GaNDLF master
• Non-breaking change (does not break existing functionality): provide as many details as possible for any breaking change
• Function/class source code documentation added/updated
• Code has been blacked for style consistency
• If applicable, version information has been updated in GANDLF/version.py
• If adding a git submodule, add to list of exceptions for black styling in pyproject.toml file
• Usage documentation has been updated, if appropriate
• History has been updated, if appropriate
• Tests added or modified to cover the changes; if coverage is reduced, please give explanation
• If customized dependency installation is required (i.e., a separate pip install step is needed for PR to be functional), please ensure it is reflected in all the files that control the CI, namely: python-test.yml, and all docker files [1,2,3,4]

[codecov]

Codecov Report

Merging #465 (b101eff) into master (e8d21ac) will decrease coverage by 0.03%.
The diff coverage is 94.28%.

❗ Current head b101eff differs from pull request most recent head 84eda98. Consider uploading reports for the commit 84eda98 to get more accurate results

@@            Coverage Diff             @@
##           master     #465      +/-   ##
==========================================
- Coverage   92.46%   92.42%   -0.04%     
==========================================
  Files         105      105              
  Lines        6276     6287      +11     
==========================================
+ Hits         5803     5811       +8     
- Misses        473      476       +3     

Flag	Coverage Δ
unittests	92.42% <94.28%> (-0.04%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
GANDLF/data/inference_dataloader_histopath.py	95.08% <ø> (ø)
GANDLF/compute/inference_loop.py	84.21% <94.28%> (-0.19%)	⬇️
...NDLF/data/preprocessing/template_matching/utils.py	95.34% <0.00%> (-2.33%)	⬇️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[Geeks-Sid]

Hi @sarthakpati, have you tested this with svs or tiffs that are of the size 1GB+ in their original format?

[sarthakpati]

@Geeks-Sid unfortunately I have not, and I do not have access to such data right now. If you or @ujjwalbaid0408 could test it, it would be great!

[Geeks-Sid]

Yes, I believe this would require such testing because saving png images with the blended heat map and figuring out a way to read them in a multi-tiff manner is not that trivial from my experience. I will test this by end of the week. Also, great work!

[sarthakpati]

Yes, I believe this would require such testing because saving png images with the blended heat map and figuring out a way to read them in a multi-tiff manner is not that trivial from my experience. I will test this by end of the week. Also, great work!

Any update? @Geeks-Sid @ujjwalbaid0408

[Geeks-Sid]

This works for tiff as I tested a slide for the given condition. LGTM!

[sarthakpati]

Cool, I fixed a codacy issue, so this should be ready to merge, unless @ujjwalbaid0408 has objections?

[sarthakpati]

@ujjwalbaid0408 and I have verified results from this using testing data for the TIL prediction project. This is good to merge.