FilesLast commitLast update
19 days ago
2 months ago
3 months ago
1 month ago
7 months ago
5 days ago
7 months ago
2 months ago
2 months ago
5 days ago
1 month ago
11 days ago
README

Atan

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: performs the arctangent operation on each element of the input and outputs the result.

  • Computation formula:

    yi=tan−1(xi)y_{i}=tan^{-1}(x_{i})

Parameter Description

Parameter Name Input/Output/Attribute Description Data Type Data Format
x Input Input tensor x in the formula. INT8, INT16, INT32, INT64, UINT8, BOOL, FLOAT, FLOAT16, DOUBLE, BFLOAT16 ND
y Output Output tensor y in the formula. FLOAT, FLOAT16, DOUBLE, BFLOAT16 ND
  • Ascend 950PR&950DT products: Supports FLOAT, FLOAT16, and BFLOAT16.
  • Atlas inference products and Atlas training products: BFLOAT16 is not supported.

Constraint Description

  • When the input type is INT8, INT16, INT32, INT64, UINT8, or BOOL, the input is converted to FLOAT32 for computation, and the output is of the FLOAT32 type. Supports non-contiguous tensors, and the supported data format is ND. The dimensions of a non-contiguous tensor must not be greater than 8, and the shapes of the input and output must be the same.

Invocation Description

Invocation Method Invocation Sample Description
aclnn invocation test_aclnn_Atan Invokes the Atan operator through the aclnnAtan API.
Graph-mode invocation test_geir_Atan Invokes the Atan operator by building a graph through the operator IR.