onnx_diagnostic.reference.torch_ops.reduce_ops

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceMax_18(node: NodeProto, version: int | None = None, verbose: int = 0)

ReduceMax

run(x: OpRunTensor, axes: OpRunTensor | None = None) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceMean_18(node: NodeProto, version: int | None = None, verbose: int = 0)

ReduceMean

run(x: OpRunTensor, axes: OpRunTensor | None = None) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceMin_17(node: NodeProto, version: int | None = None, verbose: int = 0)

ReduceMin

run(x: OpRunTensor) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceMin_18(node: NodeProto, version: int | None = None, verbose: int = 0)

ReduceMin

run(x: OpRunTensor, axes: OpRunTensor | None = None) → OpRunTensor

Kernel implementation.

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceOp(node: NodeProto, version: int | None = None, verbose: int = 0)

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceOpAxes(node: NodeProto, version: int | None = None, verbose: int = 0)

class onnx_diagnostic.reference.torch_ops.reduce_ops.ReduceSum_13(node: NodeProto, version: int | None = None, verbose: int = 0)

ReduceSum

run(x: OpRunTensor, axes: OpRunTensor | None = None) → OpRunTensor

Kernel implementation.