cellflow.training.CallbackRunner.on_log_iteration

CallbackRunner.on_log_iteration(valid_source_data, valid_data, pred_data, solver)

Called at each validation/log iteration to run callbacks. First computes metrics with computation callbacks and then logs data with logging callbacks.

Parameters:

• valid_source_data (dict[str, dict[str, ndarray[tuple[Any, ...], dtype[float64]]]]) – Source data in nested dictionary format with same keys as valid_true_data

• valid_true_data – Validation data in nested dictionary format with same keys as valid_pred_data

• valid_pred_data – Predicted data in nested dictionary format with same keys as valid_true_data

• solver (OTFlowMatching | GENOT) – OTFlowMatching solver or GENOT solver with a conditional velocity field.

• valid_data (dict[str, dict[str, ndarray[tuple[Any, ...], dtype[float64]]]])

• pred_data (dict[str, dict[str, ndarray[tuple[Any, ...], dtype[float64]]]])

Return type:

dict[str, Any]

Returns:

: dict_to_log: Dictionary containing data to log