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

Exp

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 a new tensor in which each element is the exponential of the corresponding element in the input tensor.
  • Computation formula:

outi=eselfiout_{i} = e^{self_{i}}

Parameter Description

Parameter Name Input/Output/Attribute Description Data Type Data Format
x Input Input parameter for the exp computation, which is self_i in the formula. FLOAT, FLOAT16, BFLOAT16 ND
base Optional attribute
  • Specifies the base of the exponential operation.
  • The default value is -1.0.
FLOAT ND
scale Optional attribute
  • Specifies the scaling coefficient.
  • The default value is 1.0.
FLOAT ND
shift Optional attribute
  • Specifies the offset.
  • The default value is 0.0.
FLOAT ND
y Output Output parameter for the exp computation, which is out_i in the formula. FLOAT, FLOAT16, BFLOAT16 ND

Constraint Description

None

Invocation Description

Invocation Method Invocation Sample Description
aclnn invocation test_aclnn_exp Invokes the Exp operator through the aclnnExp&aclnnInplaceExp API.