AI Stress Testing

To run RIME on image data, execute the RIME CLI using the rime-engine run-images command and specify the runtime parameters using the --config-path argument. Below is an overview of the supported configuration arguments for the runtime config.

Template

{
  "run_name": "Run Name",                       (REQUIRED)
  "data_info": {...},                           (REQUIRED)
  "model_task": "Task Name",                    (REQUIRED)
  "model_info": {...},
  "data_profiling_info": {...},
  "tests_config_path": "path/to/tests/config",
  "prediction_info": {...},
  "random_seed": null,
}

Arguments

run_name: string, required

The name under which your run will appear in the UI.
data_info: DataInfo, required

Configuration for the datasources to use. For a reference on how to configure a datasource, see Data Configuration.
model_info: ModelInfo, required

Configuration for the model to use. For a reference on how to configure a model, see Model Configuration. If you are not providing a model, this should be null.
model_task: string, required

Specification of the model task. Currently, the supported values are "Image Classification", "Object Detection".
data_profiling_info: DataProfilingInfo, default = DataProfilingInfo()

Specification of how to profile and interpret the data. For a guide on how to specify this info, see Data Profiling Configuration.

NOTE: this argument can also not be provided, in which all the defaults will be used.
tests_config_path: string or null, default = null

Path to a TestSuiteConfig JSON file. If path is null RIME will use the default TestSuiteConfig for the specified model task.
prediction_info: PredictionInfo or null, default = null

Specification of how to handle model predictions for this run. For a guide on how to specify this info, see CV Prediction Configuration. NOTE: this argument can also not be provided, in which case the default configuration is used.
random_seed: int or null, default = null

The random seed to use for the run.