Cumsum
Description
Computes the cumulative sum of the input tensor on the given axis.
Input
Two inputs:
x: tensor of type float16, float, or int32.
axis: scalar of int32 or int64. Defaults to 0. Must be in the range [-r, r - 1], where r is the number of dimensions of the input x.
Output
One output:
y: tensor of the identical data type as input x.
Attribute
exclusive: int. Whether to return the sum excluding the top-level elements. Defaults to 0. The value 0 indicates False, and the value 1 indicates True.
reverse: int. Whether to perform reverse sum. Defaults to 0. 0 indicates False, and 1 indicates True.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18
Parent topic: Operators Specifications of the AI Framework