# gizai:onnx/model the ONNX graph types and protobuf fields. ```gizlang import * as Model from "gizai:onnx/model"; ``` ## Types ### `Attr` ```gizlang type Attr = { name: string; kind: i64; f: f64; i: i64; s: string; floats: Vec; ints: Vec; strings: Vec; wide: bool; proto: bytes; } ``` wide: the floats came from a tensor of f64. - `name`: `string` - `kind`: `i64` - `f`: `f64` - `i`: `i64` - `s`: `string` - `floats`: `Vec` - `ints`: `Vec` - `strings`: `Vec` - `wide`: `bool` - `proto`: `bytes` — A tensor attribute's TensorProto, as stored. ### `Node` ```gizlang type Node = { op: string; domain: string; inputs: Vec; outputs: Vec; attrs: Vec; } ``` A graph node: its operator in its domain, its input and output names and its attributes. - `op`: `string` - `domain`: `string` - `inputs`: `Vec` - `outputs`: `Vec` - `attrs`: `Vec` ### `Tensor` ```gizlang type Tensor = { name: string; dims: Vec; values: Vec; } ``` An initializer: its name, dimensions and values. - `name`: `string` - `dims`: `Vec` - `values`: `Vec` ### `Port` ```gizlang type Port = { name: string; elem: i64; dims: Vec; } ``` A graph input or output: its element type and dimensions (-1: the row count N). - `name`: `string` - `elem`: `i64` - `dims`: `Vec` ### `Graph` ```gizlang type Graph = { nodes: Vec; initializers: Vec; inputs: Vec; outputs: Vec; } ``` An ONNX graph: its nodes, initializers, inputs and outputs. - `nodes`: `Vec` - `initializers`: `Vec` - `inputs`: `Vec` - `outputs`: `Vec` ## Functions ### `attr` ```gizlang function attr(name: string, kind: i64): Attr ``` An empty attribute `name` of AttributeType `kind`. ### `intAttr` ```gizlang function intAttr(name: string, v: i64): Attr ``` The integer attribute `name`. ### `textAttr` ```gizlang function textAttr(name: string, v: string): Attr ``` The string attribute `name`. ### `floatsAttr` ```gizlang function floatsAttr(name: string, v: Vec): Attr ``` The float list attribute `name`. ### `intsAttr` ```gizlang function intsAttr(name: string, v: Vec): Attr ``` The integer list attribute `name`. ### `textsAttr` ```gizlang function textsAttr(name: string, v: Vec): Attr ``` The string list attribute `name`. ### `node` ```gizlang function node(op: string, domain: string, inputs: Vec, outputs: Vec, attrs: Vec): Node ``` The node of operator `op` in `domain`. ### `key` ```gizlang function key(out: mut bytes, field: i64, wire: i64): void ``` Writes the protobuf key of `field` with wire type `wire`. Effects: fail. ### `putInt` ```gizlang function putInt(out: mut bytes, field: i64, v: i64): void ``` Writes `v` as varint field `field`. Effects: fail. ### `putBytes` ```gizlang function putBytes(out: mut bytes, field: i64, b: bytes): void ``` Writes `b` as length-delimited field `field`. Effects: fail. ### `putText` ```gizlang function putText(out: mut bytes, field: i64, s: string): void ``` Writes `s` as a UTF-8 field `field`. Effects: fail. ### `putFloats` ```gizlang function putFloats(out: mut bytes, field: i64, v: Vec): void ``` Writes `v` as a packed f32 field `field`. Effects: fail. ### `putInts` ```gizlang function putInts(out: mut bytes, field: i64, v: Vec): void ``` Writes `v` as a packed varint field `field`. Effects: fail. ### `textOf` ```gizlang function textOf(w: Wire, f: Span): string ``` The text of the length-delimited field `f`. Effects: fail. ### `readFloats` ```gizlang function readFloats(w: Wire, f: Span, out: mut Vec): void ``` A repeated float (f32) field, one value or packed. Effects: fail. ### `readDoubles` ```gizlang function readDoubles(w: Wire, f: Span, out: mut Vec): void ``` A repeated double (f64) field, one value or packed. Effects: fail. ### `readInts` ```gizlang function readInts(w: Wire, f: Span, out: mut Vec): bool throws string ``` A repeated int64 field, one value or packed. Effects: fail. ## Methods ### `Node.find` ```gizlang function Node.find(self: Node, name: string): Option ``` The attribute `name` (or `name`_as_tensor), if present. Effects: fail. ### `Node.floats` ```gizlang function Node.floats(self: Node, name: string): Vec ``` The floats of attribute `name`, else none. Effects: fail. ### `Node.ints` ```gizlang function Node.ints(self: Node, name: string): Vec ``` The integers of attribute `name`, else none. Effects: fail. ### `Node.texts` ```gizlang function Node.texts(self: Node, name: string): Vec ``` The strings of attribute `name`, else none. Effects: fail. ### `Node.text` ```gizlang function Node.text(self: Node, name: string, otherwise: string): string ``` The string of attribute `name`, else `otherwise`. Effects: fail. ### `Node.int` ```gizlang function Node.int(self: Node, name: string, otherwise: i64): i64 ``` The integer of attribute `name`, else `otherwise`. Effects: fail. ### `Node.wide` ```gizlang function Node.wide(self: Node, name: string): bool ``` Whether the floats of attribute `name` came from an f64 tensor. Effects: fail. ## Constants ### `IR_VERSION` ```gizlang const IR_VERSION = 8 ``` The ONNX version that encode writes (IR version 8: ONNX 1.10 and later). ### `OPSET` ```gizlang const OPSET = 17 ``` The ONNX operator set version that encode writes. ### `ML_OPSET` ```gizlang const ML_OPSET = 3 ``` The ONNX-ML (ai.onnx.ml) operator set version that encode writes. ### `ML` ```gizlang const ML = "ai.onnx.ml" ``` The ONNX-ML operator domain. ### `A_FLOAT` ```gizlang const A_FLOAT = 1 ``` The AttributeType of a float. ### `A_INT` ```gizlang const A_INT = 2 ``` The AttributeType of an integer. ### `A_STRING` ```gizlang const A_STRING = 3 ``` The AttributeType of a string. ### `A_FLOATS` ```gizlang const A_FLOATS = 6 ``` The AttributeType of a list of floats. ### `A_INTS` ```gizlang const A_INTS = 7 ``` The AttributeType of a list of integers. ### `A_STRINGS` ```gizlang const A_STRINGS = 8 ``` The AttributeType of a list of strings. ### `T_FLOAT` ```gizlang const T_FLOAT = 1 ``` The TensorProto data type of a 32-bit float. ### `T_INT64` ```gizlang const T_INT64 = 7 ``` The TensorProto data type of a 64-bit integer. ### `T_INT32` ```gizlang const T_INT32 = 6 ``` The TensorProto data type of a 32-bit integer. ### `T_DOUBLE` ```gizlang const T_DOUBLE = 11 ``` The TensorProto data type of a 64-bit float.