Add hyper-parameter tuning with optuna #65
Merged
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Outdated suggestions cannot be applied.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.
This PR addresses issues #53 and #62.
Changelog
diart.optim.Optimizer
to tune hyper-parameters given a basic configuration objectOptimizer
creates a basic optuna study, but it can also work with a study created by the userOptimizer
is also compatible with optuna's distributed optimizationHyperParameter
data class to represent a tuneable hyper-parameterTauActive
,RhoUpdate
andDeltaNew
instances ofHyperParameter
so they don't have to be created from scratchdiart.tune
script to quickly tune the default pipeline to a dataset (also compatible with distributed optimization)diart.stream
,diart.benchmark
anddiart.tune
can be run withoutpython -m
SpeakerEmbedding.from_pyannote
andSpeakerSegmentation.from_pyannote
verbose
parameter inBenchmark
intoshow_progress
andshow_report
batch_size
a constructor parameter inBenchmark