Enum Version

Versioning

ONNX versioning is specified in docs/IR.md and elaborated on in docs/Versioning.md

To be compatible with both proto2 and proto3, we will use a version number that is not defined by the default value but an explicit enum number.

Namespace: Onnx
Syntax
public enum Version

Fields

Name Description
IrVersion

IR VERSION 6 published on <TBD>

  • Add support for sparse tensor constants stored in model.
  • Add message SparseTensorProto
  • Add sparse initializers
IrVersion20171010

The version field is always serialized and we will use it to store the version that the graph is generated from. This helps us set up version control. For the IR, we are using simple numbers starting with with 0x00000001, which was the version we published on Oct 10, 2017.
IrVersion20171030

IR_VERSION 2 published on Oct 30, 2017

  • Added type discriminator to AttributeProto to support proto3 users
IrVersion2017113

IR VERSION 3 published on Nov 3, 2017

  • For operator versioning:
  • Added new message OperatorSetIdProto
  • Added opset_import in ModelProto
  • For vendor extensions, added domain in NodeProto
IrVersion2019122

IR VERSION 4 published on Jan 22, 2019

  • Relax constraint that initializers should be a subset of graph inputs
  • Add type BFLOAT16
IrVersion2019318

IR VERSION 5 published on March 18, 2019

  • Add message TensorAnnotation.
  • Add quantization annotation in GraphProto to map tensor with its scale and zero point quantization parameters.
StartVersion

proto3 requires the first enum value to be zero. We add this just to appease the compiler.