ArgMin
Description
Returns the index corresponding to the minimum value on the specified axis of the input tensor.
Input
data: input tensor of type float16 or float. The data format can be ND.
Attribute
- axis: int. Must be in the range [–r, r – 1], where r indicates the rank of the input x.
- keepdims: The default value is 1. The value can be 1 or 0 (optional).
- select_last_index: whether to select the first or last position if the minimum value appears in multiple positions. The value range is [0, 1]. The default value is 0. Currently, only value 0 is supported.
Output
reduced: output tensor of type int32. The data format can be ND.
Constraints
The input data does not support the scenario where the reduced axis is 0.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18
Parent topic: Supported ONNX Operators