Cummin
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: computes the cumulative minimum of self and returns the minimum values and the corresponding indices.
-
Computation formula:
valuesOut:
valuesOuti=min(self1,self2,self3,......,selfi)valuesOut_{i} = min(self_{1}, self_{2}, self_{3}, ...... , self_{i})
indicesOut:
indicesOuti=argmin(self1,self2,self3,......,selfi)indicesOut_{i} = argmin(self_{1}, self_{2}, self_{3}, ...... , self_{i})
Parameter Description
| Parameter Name | Input/Output/Attribute | Description | Data Type | Data Format |
|---|---|---|---|---|
| x | Input | self in the formula, which is the input Tensor. | FLOAT16, FLOAT, DOUBLE, UINT8, INT8, INT16, INT32, INT64, BOOL, BFLOAT16 | ND |
| y | Output | valuesOut in the formula, which is the cumulative minimum of x. | FLOAT16, FLOAT, DOUBLE, UINT8, INT8, INT16, INT32, INT64, BOOL, BFLOAT16 | ND |
| argmin | Output | indicesOut in the formula, which is the index corresponding to y. | INT32, INT64 | ND |
| axis | Attribute | Dimension to process | int64_t | - |
Constraint Description
None
Invocation Description
| Invocation Method | Sample Code | Description |
|---|---|---|
| aclnn invocation | test_aclnn_cummin | Invokes the Cummin operator through the aclnnCummin API. |