FeedDataFlowGraph (Feeding Inputs by Index)

Applicability

Product	Supported
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	x
Atlas inference product	x
Atlas training product	x

Function Description

Inputs data to a graph by index.

Prototype

Status FeedDataFlowGraph(uint32_t graph_id, const std::vector<uint32_t> &indexes, const std::vector<Tensor> &inputs, const DataFlowInfo &info, int32_t timeout)

Parameters

Parameter	Input/Output	Description
graph_id	Input	ID of the graph to be executed.
indexes	Input	Indexes of inputs. Values must be in the range [0, N – 1], where N is the number of inputs. The number must be the same as the value of inputs. Example: {0,2}, indicating that the first and third inputs are fed.
inputs	Input	Input tensors of the computational graph, which are memory allocated on the host.
info	Input	Input data flow flag. For details, see DataFlowInfo Data Types.
timeout	Input	Data input timeout, in milliseconds. The value -1 means no timeout limit.

Returns

Parameter	Type	Description
-	Status	SUCCESS: successful data input. FAILED: failed data input. For details about error codes of ACL APIs, see Runtime APIs > Data Types and Operation APIs > aclError. For details about other error codes, see UDF Error Codes.

Constraints

None

Parent topic: Graph Running APIs