[SymbolicShapeInference] Support 10 Reduce* ops #22722

yf711 · 2024-11-05T01:20:19Z

Description

Extend existing Reduce_Sum func to all 10 Reduce-series ops
i.e ReduceMean def: https://onnx.ai/onnx/operators/onnx__ReduceMean.html

Op	Defintions (bold: diff)
ReduceL1	Computes the L1 norm of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.
ReduceL2	Computes the L2 norm of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.
ReduceLogSum	Computes the log sum of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields minus infinity (if supported by the datatype) or undefined otherwise.
ReduceLogSumExp	Computes the log sum exponent of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields minus infinity (if supported by the datatype) or undefined otherwise.
ReduceMax	Computes the max of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields minus infinity (if supported by the datatype) or the minimum value of the data type otherwise. If the input data type is Boolean, the comparison should consider False < True.
ReduceMean	Computes the mean of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields undefined.
ReduceMin	Computes the min of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields plus infinity (if supported by the datatype) or the maximum value of the data type otherwise. If the input data type is Boolean, the comparison should consider False < True.
ReduceProd	Computes the product of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 1.
ReduceSum	Computes the sum of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.
ReduceSumSquare	Computes the sum square of the input tensor’s elements along the provided axes. The resulting tensor has the same rank as the input if keepdims equals 1. If keepdims equals 0, then the resulting tensor has the reduced dimension pruned. Input tensors of rank zero are valid. Reduction over an empty set of values yields 0.