Task modules¶
Benchmark Tasks definition¶
- class orion.benchmark.task.BenchmarkTask(max_trials, **kwargs)[source]¶
Base class describing what a task can do. A task will define the objective function and search space of it.
- Parameters
- max_trialsint
Max number of trials the experiment will run against this task.
- kwargsdict
Configurable parameters of the task, a particular task implementation can have its own parameters.
- Attributes
configuration
Return the configuration of the task.
max_trials
Return the max number of trials to run for the
Methods
__call__
(*args, **kwargs)All tasks will be callable by default, and method call() will be executed when a task is called directly.
call
(*args, **kwargs)Define the black box function to optimize, the function will expect hyper-parameters to search and return objective values of trial with the hyper-parameters.
Return the search space for the task objective function
- __call__(*args, **kwargs)[source]¶
All tasks will be callable by default, and method call() will be executed when a task is called directly.
- abstract call(*args, **kwargs)[source]¶
Define the black box function to optimize, the function will expect hyper-parameters to search and return objective values of trial with the hyper-parameters.
- property configuration¶
Return the configuration of the task.
- property max_trials¶
Return the max number of trials to run for the
- class orion.benchmark.task.Branin(max_trials=20)[source]¶
Branin function as benchmark task
Methods
call
(x)Evaluate a 2-D branin function.
Return the search space for the task objective function
- class orion.benchmark.task.CarromTable(max_trials=20)[source]¶
CarromTable function as benchmark task
Methods
call
(x)Evaluate a 2-D CarromTable function.
Return the search space for the task objective function
- class orion.benchmark.task.EggHolder(max_trials=20, dim=2)[source]¶
EggHolder function as benchmark task
Methods
call
(x)Evaluate a n-D eggholder function.
Return the search space for the task objective function
- class orion.benchmark.task.RosenBrock(max_trials=20, dim=2)[source]¶
RosenBrock function as benchmark task
Methods
call
(x)Evaluate a n-D rosenbrock function.
Return the search space for the task objective function