FedMedian#
- class FedMedian(*, fraction_fit: float = 1.0, fraction_evaluate: float = 1.0, min_fit_clients: int = 2, min_evaluate_clients: int = 2, min_available_clients: int = 2, evaluate_fn: Callable[[int, List[ndarray[Any, dtype[Any]]], Dict[str, bool | bytes | float | int | str]], Tuple[float, Dict[str, bool | bytes | float | int | str]] | None] | None = None, on_fit_config_fn: Callable[[int], Dict[str, bool | bytes | float | int | str]] | None = None, on_evaluate_config_fn: Callable[[int], Dict[str, bool | bytes | float | int | str]] | None = None, accept_failures: bool = True, initial_parameters: Parameters | None = None, fit_metrics_aggregation_fn: Callable[[List[Tuple[int, Dict[str, bool | bytes | float | int | str]]]], Dict[str, bool | bytes | float | int | str]] | None = None, evaluate_metrics_aggregation_fn: Callable[[List[Tuple[int, Dict[str, bool | bytes | float | int | str]]]], Dict[str, bool | bytes | float | int | str]] | None = None, inplace: bool = True)[源代码]#
基类:
FedAvg
Configurable FedMedian strategy implementation.
Methods
aggregate_evaluate
(server_round, results, ...)采用加权平均法计算评估损失总额。
aggregate_fit
(server_round, results, failures)使用中位数汇总拟合结果。
configure_evaluate
(server_round, parameters, ...)配置下一轮评估。
configure_fit
(server_round, parameters, ...)配置下一轮训练。
evaluate
(server_round, parameters)使用评估函数评估模型参数。
initialize_parameters
(client_manager)初始化全局模型参数。
num_evaluation_clients
(num_available_clients)使用部分可用客户进行评估。
num_fit_clients
(num_available_clients)返回样本大小和所需的可用客户数量。
- aggregate_evaluate(server_round: int, results: List[Tuple[ClientProxy, EvaluateRes]], failures: List[Tuple[ClientProxy, EvaluateRes] | BaseException]) Tuple[float | None, Dict[str, bool | bytes | float | int | str]] #
采用加权平均法计算评估损失总额。
- aggregate_fit(server_round: int, results: List[Tuple[ClientProxy, FitRes]], failures: List[Tuple[ClientProxy, FitRes] | BaseException]) Tuple[Parameters | None, Dict[str, bool | bytes | float | int | str]] [源代码]#
使用中位数汇总拟合结果。
- configure_evaluate(server_round: int, parameters: Parameters, client_manager: ClientManager) List[Tuple[ClientProxy, EvaluateIns]] #
配置下一轮评估。
- configure_fit(server_round: int, parameters: Parameters, client_manager: ClientManager) List[Tuple[ClientProxy, FitIns]] #
配置下一轮训练。
- evaluate(server_round: int, parameters: Parameters) Tuple[float, Dict[str, bool | bytes | float | int | str]] | None #
使用评估函数评估模型参数。
- initialize_parameters(client_manager: ClientManager) Parameters | None #
初始化全局模型参数。
- num_evaluation_clients(num_available_clients: int) Tuple[int, int] #
使用部分可用客户进行评估。
- num_fit_clients(num_available_clients: int) Tuple[int, int] #
返回样本大小和所需的可用客户数量。