Imaging benchmarks #984
Closed
Imaging benchmarks #984
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Andrewwango
requested changes
Dec 11, 2025
Collaborator
Andrewwango
left a comment
Andrewwango
left a comment
There was a problem hiding this comment.
Super cool idea @jscanvic !
Hello pandas, old friend...
|
|
||
|
|
||
| benchmark = Benchmark() | ||
| models = [dinv.models.DRUNet(), dinv.models.Restormer()] |
Collaborator
There was a problem hiding this comment.
super cool!
however, is the benchmark conflating multiple things - arch, how-well-weights-are-pretrained, model size?
Collaborator
Author
There was a problem hiding this comment.
For now it's a somewhat crude benchmark of the models featured out of the box in deepinv
| dinv.physics.GaussianNoise(sigma=25 / 255, rng=rng) | ||
| ).to(device) | ||
|
|
||
| psnr_fn = dinv.metric.PSNR(min_pixel=0.0, max_pixel=1.0).to(device) |
Collaborator
There was a problem hiding this comment.
would be nice to use modality-specific metrics e.g. our ERGAS etc. for spectral imaging benchmarks
| x = x.mul(255.0).round().div(255.0).clamp(0.0, 1.0) | ||
|
|
||
| psnr = psnr_fn(x_hat, x).item() | ||
| psnrs.append(psnr) |
Collaborator
There was a problem hiding this comment.
could use the AverageMeter we use in the trainer (utils/logger.py)
Collaborator
Author
|
Thanks Andrew, I'll make the changes over there deepinv/benchmarks#1 (closing this) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The library has all of the building blocks necessary to compute benchmarks on different imaging modalities. Yet, there is no standardized way to do that at the moment and we do not showcase it in the docs. The goal of this PR is to remedy that.
Plan
deepinv.benchmarkfor the benchmark-related codeInspirations
TODO