FilesLast commitLast update
15 days ago
27 days ago
1 month ago
1 month ago
5 months ago
1 month ago
14 days ago
README

IdentityN

English | 简体中文

Product Support Status

Product Supported
Ascend 950PR&950DT products √
Atlas A3 products √
Atlas A2 products √
Atlas 200I/500 A2 inference products √
Atlas inference products √
Atlas training products √

Function Description

  • Operator function: returns copies of a group of input tensors. The outputs have the same number, shape, data type, and content as the inputs.

Parameter Description

Parameter Name Input/Output/Attribute Description Data Type Data Format
x Input List of input tensors to be copied. Dynamic input. FLOAT, FLOAT16, INT8, INT16, UINT16, UINT8, INT32, INT64, UINT32, UINT64, BOOL, DOUBLE, STRING ND
y Output Copies of the input tensor list x. Dynamic output. The length, shape, data type, and content are consistent with x. Same as x ND

Constraint Description

  • The number, shape, data type, and element content of x and y remain consistent.
  • For supported data types, refer to the IR definitions in identity_n_proto.h.

Invocation Description

Invocation Method Invocation Sample Description
Graph-mode invocation test_geir_identity_n, test_geir_identity_n_v2 Invokes the IdentityN operator by building a graph through the operator IR.