Add automatic highlight rolloff in preprocessing #27
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Outdated suggestions cannot be applied.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.
Motivation
preprocess_onepreviously only converted uint8->float, divided by 255, and resized, with no highlight handling.Description
preprocess_oneusing only tensor ops on the input device with constantssat_threshold=0.98,sat_frac_threshold=0.001,knee_start=0.98, androlloff_strength=4.0.y = knee_start + (1 - knee_start) * (1 - exp(-k * (x - knee_start) / (1 - knee_start)))and is applied elementwise forx > knee_start, followed byclamp(0,1)."highlight_rolloff_applied","highlight_sat_frac", and"highlight_sat_frac_threshold"so callers can observe when the rolloff ran.predict_imagepath.Testing
Codex Task