B (non-differentiable) : T Second input operand for the logical operator. Other versions of this operator: 1 Inputs A (non-differentiable) : T First input operand for the logical operator. This version of the operator has been available since version 7 of the default ONNX operator set. This operator supports multidirectional (i.e., Numpy-style) broadcasting for more details please check the doc. Returns the tensor resulted from performing the and logical operationĮlementwise on the input tensors A and B (with Numpy-style broadcasting support). Outputs C (differentiable) : T Result, has same element type as two inputs Type Constraints T : tensor(uint8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(int8), tensor(int16), tensor(int32), tensor(int64), tensor(float16), tensor(float), tensor(double), tensor(bfloat16) Constrain input and output types to all numeric tensors. Other versions of this operator: 1, 6, 7, 13 Inputs A (differentiable) : T First operand. This version of the operator has been available since version 14 of the default ONNX operator set. (Opset 14 change): Extend supported types to include uint8, int8, uint16, and int16. Performs element-wise binary addition (with Numpy-style broadcasting support). float32)Įxpect( node, inputs =, outputs =, arccosh( x) # expected output expect( node, inputs =, outputs =, Other versions of this operator: 1, 6 Inputs X (differentiable) : T Input tensor Outputs Y (differentiable) : T Output tensor Type Constraints T : tensor(uint8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(int8), tensor(int16), tensor(int32), tensor(int64), tensor(float16), tensor(float), tensor(double), tensor(bfloat16) Constrain input and output types to all numeric tensors. This version of the operator has been available since version 13 of the default ONNX operator set. (Tensor) where the absolute is, y = abs(x), is applied to ai.onnx (default) OperatorĪbsolute takes one input data (Tensor) and produces one output data Is not specified, that variable has undefined differentiability.
This file is automatically generated from theĭo not modify directly and instead edit operator definitions.įor an operator input/output's differentiability, it can be differentiable,