.xshape.shape_type_compute

experimental_experiment.xshape.shape_type_compute.broadcast_shape(sh1: Tuple[int | torch.SymInt | torch.SymFloat | float | str, ...], sh2: Tuple[int | torch.SymInt | torch.SymFloat | float | str, ...], graph_builder: ShapeBuilder | None = None) → Tuple[int | torch.SymInt | torch.SymFloat | float | str, ...]

Computes the shape for many broadcasting operators. This function should be used while converting the graph into ONNX because it assumes the broadcast is possible and adds the necessary constraints on the dynamic in the GraphBuilder shapes to make it work.

Parameters:

• sh1 – first shape

• sh2 – second shape

• graph_builder – if not None, the function register any constraint which might appear while applying the broadcast

Returns:

resulting shape

experimental_experiment.xshape.shape_type_compute.set_shape_type_custom(self: ShapeBuilder, node: NodeProto, exc: bool = False)

Sets the shape and type if it can.

experimental_experiment.xshape.shape_type_compute.set_shape_type_op_any(self: ShapeBuilder, node: NodeProto, exc: bool = False)

Sets the shape and type if it can.

experimental_experiment.xshape.shape_type_compute.set_type_shape_binary_op(g: ShapeBuilder, name: str, *input_names: List[str], begin: int = 0, cmp_op: bool = False, itype: int | None = None) → bool

Sets the shape and type for a binary operator (add, mul, …).

experimental_experiment.xshape.shape_type_compute.set_type_shape_gemm(g: ShapeBuilder, name: str, x: str, y: str, transA: int, transB: int)

Sets the output shape for node type Gemm.

experimental_experiment.xshape.shape_type_compute.set_type_shape_matmul(g: ShapeBuilder, name: str, x: str, y: str) → bool

Sets the output shape for node type MatMul.

experimental_experiment.xshape.shape_type_compute.set_type_shape_reduce_op(g: ShapeBuilder, name: str, x: str, keepdim: int, axes: Tuple[int] | None = None)

Sets the output shape for any Reduce type.

experimental_experiment.xshape.shape_type_compute.set_type_shape_reshape(g: ShapeBuilder, name: str, input_name: str, new_shape: Sequence[int])

Sets the output shape for node type Reshape

experimental_experiment.xshape.shape_type_compute.set_type_shape_unary_op(g: ShapeBuilder, name: str, input_name: str, itype: int | None = None) → bool

Sets the shape and type for an unary operator (abs, exp, …).

experimental_experiment.xshape.shape_type_compute.set_type_shape_unary_op_abs(g: ShapeBuilder, name: str, input_name: str, itype: int | None = None) → bool

Sets the shape and type for an unary operator (abs, exp, …).