Attributes
A set of pre-defined constants to be used as values for the standard denotation field in TensorShapeProto.Dimension for semantic description of the tensor dimension.
A set of pre-defined constants to be used as values for the standard denotation field in TensorShapeProto.Dimension for semantic description of the tensor dimension.
Describe a batch number dimension.
Describe a channel dimension.
Describe a time dimension.
Describe a feature dimension. This is typically a feature dimension in RNN and/or spatial dimension in CNN.
Describe a filter in-channel dimension. This is the dimension that is identical (in size) to the channel dimension of the input image feature maps.
Describe a filter out channel dimension. This is the dimension that is identical (int size) to the channel dimension of the output image feature maps.
Describe a filter spatial dimension.
Graphs
Graphs
A graph defines the computational logic of a model and is comprised of a parameterized list of nodes that form a directed acyclic graph based on their inputs and outputs. This is the equivalent of the "network" or "graph" in many deep learning frameworks.
The nodes in the graph, sorted topologically.
The name of the graph. namespace Graph
A list of named tensor values, used to specify constant inputs of the graph. Each TensorProto entry must have a distinct name (within the list) that also appears in the input list.
A human-readable documentation for this graph. Markdown is allowed.
The inputs and outputs of the graph.
Information for the values in the graph. The ValueInfoProto.name's must be distinct. It is optional for a value to appear in value_info list.
Models
Models
ModelProto is a top-level file/container format for bundling a ML model and associating its computation graph with metadata.
The semantics of the model are described by the associated GraphProto.
The version of the IR this model targets. See Version enum above. This field MUST be present.
The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.
The name of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
The version of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
Domain name of the model.
We use reverse domain names as name space indicators. For example:
com.facebook.fair
or com.microsoft.cognitiveservices
Together with model_version
and GraphProto.name, this forms the unique identity of
the graph.
The version of the graph encoded. See Version enum below.
A human-readable documentation for this model. Markdown is allowed.
The parameterized graph that is evaluated to execute the model.
Named metadata values; keys should be distinct.
Nodes
Nodes
Computation graphs are made up of a DAG of nodes, which represent what is commonly called a "layer" or "pipeline stage" in machine learning frameworks.
For example, it can be a node of type "Conv" that takes in an image, a filter tensor and a bias tensor, and produces the convolved output.
namespace Value
namespace Value
An optional identifier for this node in a graph. This field MAY be absent in ths version of the IR. namespace Node
The symbolic identifier of the Operator to execute. namespace Operator
The domain of the OperatorSet that specifies the operator named by op_type. namespace Domain
Additional named attributes.
A human-readable documentation for this node. Markdown is allowed.
Operator Sets
Operator Sets
OperatorSets are uniquely identified by a (domain, opset_version) pair.
The domain of the operator set being identified. The empty string ("") or absence of this field implies the operator set that is defined as part of the ONNX specification. This field MUST be present in this version of the IR when referring to any other operator set.
The version of the operator set being identified. This field MUST be present in this version of the IR.
StringStringEntryProto follows the pattern for cross-proto-version maps.
StringStringEntryProto follows the pattern for cross-proto-version maps. See https://developers.google.com/protocol-buffers/docs/proto3#maps
Tensors
Tensors
A serialized tensor value.
The shape of the tensor.
The data type of the tensor.
For float and complex64 values Complex64 tensors are encoded as a single array of floats, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i] is encoded as [1.0, 2.0 ,3.0 ,4.0] When this field is present, the data_type field MUST be FLOAT or COMPLEX64.
For int32, uint8, int8, uint16, int16, bool, and float16 values float16 values must be bit-wise converted to an uint16_t prior to writing to the buffer. When this field is present, the data_type field MUST be INT32, INT16, INT8, UINT16, INT8, BOOL, or FLOAT32
For strings. Each element of string_data is a UTF-8 encoded Unicode string. No trailing null, no leading BOM. The protobuf "string" scalar type is not used to match ML community conventions. When this field is present, the data_type field MUST be STRING
For int64. When this field is present, the data_type field MUST be INT64
Optionally, a name for the tensor. namespace Value
A human-readable documentation for this tensor. Markdown is allowed.
Serializations can either use one of the fields above, or use this raw bytes field. The only exception is the string case, where one is required to store the content in the repeated bytes string_data field. When this raw_data field is used to store tensor value, elements MUST be stored in as fixed-width, little-endian order. Floating-point data types MUST be stored in IEEE 754 format. Complex64 elements must be written as two consecutive FLOAT values, real component first. Complex128 elements must be written as two consecutive DOUBLE values, real component first. Boolean type MUST be written one byte per tensor element (00000001 for true, 00000000 for false). Note: the advantage of specific field rather than the raw_data field is that in some cases (e.g. int data), protobuf does a better packing via variable length storage, and may lead to smaller binary footprint. When this field is present, the data_type field MUST NOT be STRING or UNDEFINED
For double Complex64 tensors are encoded as a single array of doubles, with the real components appearing in odd numbered positions, and the corresponding imaginary component apparing in the subsequent even numbered position. (e.g., [1.0 + 2.0i, 3.0 + 4.0i] is encoded as [1.0, 2.0 ,3.0 ,4.0] When this field is present, the data_type field MUST be DOUBLE or COMPLEX128
For uint64 and uint32 values When this field is present, the data_type field MUST be UINT32 or UINT64
Defines a tensor shape.
Defines a tensor shape. A dimension can be either an integer value or a symbolic variable. A symbolic variable represents an unknown dimension.
Types
Types
The standard ONNX data types.
Defines information on value, including the name, the type, and the shape of the value.
Defines information on value, including the name, the type, and the shape of the value.
This field MUST be present in this version of the IR. namespace Value
This field MUST be present in this version of the IR.
A human-readable documentation for this value. Markdown is allowed.
Attributes
A named attribute containing either singular float, integer, string, graph, and tensor values, or repeated float, integer, string, graph, and tensor values. An AttributeProto MUST contain the name field, and *only one* of the following content fields, effectively enforcing a C/C++ union equivalent.
The name field MUST be present for this version of the IR. namespace Attribute
if ref_attr_name is not empty, ref_attr_name is the attribute name in parent function. In this case, this AttributeProto does not contain data, and it's a reference of attribute in parent scope. NOTE: This should ONLY be used in function (sub-graph). It's invalid to be used in main graph.
A human-readable documentation for this attribute. Markdown is allowed.
The type field MUST be present for this version of the IR. For 0.0.1 versions of the IR, this field was not defined, and implementations needed to use has_field hueristics to determine which value field was in use. For IR_VERSION 0.0.2 or later, this field MUST be set and match the f|i|s|t|... field in use. This change was made to accomodate proto3 implementations. discriminator that indicates which field below is in use
Exactly ONE of the following fields must be present for this version of the IR float
int
UTF-8 string
tensor value
graph
list of floats
list of ints
list of UTF-8 strings
list of tensors
list of graph