astype( bool)Įxpect( node, inputs =, outputs =, name = "test_and_bcast4v3d") astype( bool)Įxpect( node, inputs =, outputs =, name = "test_and_bcast4v2d") astype( bool)Įxpect( node, inputs =, outputs =, name = "test_and_bcast3v2d") astype( bool)Įxpect( node, inputs =, outputs =, name = "test_and_bcast3v1d") T1 : tensor(bool) Constrain output to boolean tensor. Type Constraints T : tensor(bool) Constrain input to boolean tensor. Outputs C (non-differentiable) : T1 Result tensor. 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). uint8)Įxpect( node, inputs =, outputs =, name = "test_add_uint8") And 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 =, name = "test_acosh") Add arccosh( x) # expected output expect( node, inputs =, outputs =, name = "test_acosh_example") ![]() 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 absolute value, 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,
0 Comments
Leave a Reply. |