Benchmark Job

class anomalib.pipelines.benchmark.job.BenchmarkJob(accelerator, model, datamodule, seed, flat_cfg)

Bases: Job

Benchmarking job.

Parameters:

• accelerator (str) – The accelerator to use.

• model (AnomalyModule) – The model to use.

• datamodule (AnomalibDataModule) – The data module to use.

• seed (int) – The seed to use.

• flat_cfg (dict) – The flat dictionary of configs with dotted keys.

static collect(results)

Gather the results returned from run.

Return type:

DataFrame

run(task_id=None)

Run the benchmark.

Return type:

dict[str, Any]

static save(result)

Save the result to a csv file.

Return type:

None