A Hyperparameter Tuning Library for Keras
APACHE-2.0 License
Bot releases are visible (Hide)
Published by haifeng-jin over 2 years ago
Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.1.2...1.1.3rc0
Published by haifeng-jin over 2 years ago
Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.1.1...1.1.2
Published by haifeng-jin over 2 years ago
Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.1.1...1.1.2rc0
Published by haifeng-jin over 2 years ago
objective
argument.run_trial()
or HyperModel.fit()
are of wrong type.BayesianOptimization
tuner.Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.1.1rc0...1.1.1
Published by haifeng-jin over 2 years ago
objective
argument.run_trial()
or HyperModel.fit()
are of wrong type.Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.1.0...1.1.1rc0
Published by haifeng-jin almost 3 years ago
HyperModel.fit()
to tune the fit process.Tuner.run_trial()
to return a single float as the objective value to minimize.Tuner.run_trial()
to return a dictionary of {metric_name: value}
or Keras history.hypermodel
to Tuner
if override Tuner.run_trial()
.objective
to Tuner
if HyperModel.fit()
or Tuner.run_trial()
return a single float.MultiExecutionTuner
to Tuner
to replace all overridden methods.KerasHyperModel
an internal class to wrap the user provided HyperModel
.Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.0.4...1.1.0rc0
Published by haifeng-jin almost 3 years ago
HyperModel.fit()
to tune the fit process.Tuner.run_trial()
to return a single float as the objective value to minimize.Tuner.run_trial()
to return a dictionary of {metric_name: value}
or Keras history.hypermodel
to Tuner
if override Tuner.run_trial()
.objective
to Tuner
if HyperModel.fit()
or Tuner.run_trial()
return a single float.MultiExecutionTuner
to Tuner
to replace all overridden methods.KerasHyperModel
an internal class to wrap the user provided HyperModel
.Full Changelog: https://github.com/keras-team/keras-tuner/compare/1.0.4...1.1.0rc0
Published by haifeng-jin about 3 years ago
Tuner.search_space_summary()
to print all the hyperparameters based on conditional_scope
s.Published by haifeng-jin about 3 years ago
Tuner.search_space_summary()
to print all the hyperparameters based on conditional_scope
s.Published by haifeng-jin about 3 years ago
Tuner.search_space_summary()
to print all the hyperparameters based on conditional_scope
s.Published by haifeng-jin over 3 years ago
kerastuner
to keras_tuner
.Oracle
s to add the Oracle
as suffix, e.g., RandomSearch
oracle is renamed to RandomSearchOracle
. (The RandomSearch
tuner is still named RandomSearch
.)Tuner._populate_space
to Tuner.populate_space
.Tuner._score_trail
to Tuner.score_trial
.kt.tuners.Sklearn
tuner to kt.SklearnTuner
and put it at the root level of import.CloudLogger
feature, but the Logger
class still works.sklearn.pipeline.Pipeline
.Published by haifeng-jin almost 4 years ago
Published by omalleyt12 almost 5 years ago
The first major release of Keras Tuner. This release includes improved algorithms and the ability to distribute tuning.