package caisar

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

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 0x00000001, which was the version we published on Oct 10, 2017.

IR_VERSION 2 published on Oct 30, 2017

• Added type discriminator to AttributeProto to support proto3 users

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

IR VERSION 4 published on Jan 22, 2019

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

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.

IR VERSION 6 published on Sep 19, 2019

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

IR VERSION 7 published on May 8, 2020

• Add support to allow function body graph to rely on multiple external opreator sets.
• Add a list to promote inference graph's initializers to global and mutable variables. Global variables are visible in all graphs of the stored models.
• Add message TrainingInfoProto to store initialization method and training algorithm. The execution of TrainingInfoProto can modify the values of mutable variables.
• Implicitly add inference graph into each TrainingInfoProto's algorithm.

IR VERSION 8 published on <TBD> Introduce TypeProto.SparseTensor Introduce TypeProto.Optional Added a list of FunctionProtos local to the model Deprecated since_version and operator status from FunctionProto