saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add onnx protobuf format that supports large model (#313)

Browse source 
* Add onnx protobuf format that supports large model

* Add optional for DataLocation
This commit is contained in:
Yufeng Li 2019-01-11 10:23:18 -08:00 committed by GitHub
parent 05b9440fce
commit 4735bb1ccb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 53 additions and 38 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

91
onnxruntime/core/protobuf/onnx-ml.proto
View file

@ -2,7 +2,6 @@
// WARNING: This file is automatically generated! Please edit onnx.in.proto.
//
// Copyright (c) Facebook Inc. and Microsoft Corporation.
// Licensed under the MIT license.
@ -20,11 +19,11 @@ package onnx;
//
// This document describes the syntax of models and their computation graphs,
// as well as the standard data types. Together, they are referred to as the ONNX
// Intermediate Representation, or 'IR' for short.
// Intermediate Representation, or 'IR' for short.
//
// The normative semantic specification of the ONNX IR is found in docs/IR.md.
// Definitions of the built-in neural network operators may be found in docs/Operators.md.
// Definitions of the built-in classical machine learning operators may be found in
// Definitions of the built-in classical machine learning operators may be found in
// docs/Operators-ml.md.
// Notes
@ -37,8 +36,8 @@ package onnx;
// by sharing our working version of ONNX.
//
// Protobuf compatibility
//
// To simplify framework compatibility, ONNX is defined using the subset of protobuf
//
// To simplify framework compatibility, ONNX is defined using the subset of protobuf
// that is compatible with both protobuf v2 and v3. This means that we do not use any
// protobuf features that are only available in one of the two versions.
//
@ -49,7 +48,6 @@ package onnx;
// of key-value pairs, where order does not matter and duplicates
// are not allowed.
// Versioning
//
// ONNX versioning is specified in docs/IR.md and elaborated on in docs/Versioning.md
@ -62,8 +60,8 @@ enum Version {
_START_VERSION = 0;
// 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,
// control.
// For the IR, we are using simple numbers starting with with 0x00000001,
// which was the version we published on Oct 10, 2017.
IR_VERSION_2017_10_10 = 0x0000000000000001;
@ -86,7 +84,6 @@ enum Version {
// An AttributeProto MUST contain the name field, and *only one* of the
// following content fields, effectively enforcing a C/C++ union equivalent.
message AttributeProto {
// Note: this enum is structurally identical to the OpSchema::AttrType
// enum defined in schema.h. If you rev one, you likely need to rev the other.
enum AttributeType {
@ -105,8 +102,8 @@ message AttributeProto {
}
// The name field MUST be present for this version of the IR.
optional string name = 1; // namespace Attribute
optional string name = 1; // 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.
@ -122,14 +119,14 @@ message AttributeProto {
// 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.
optional AttributeType type = 20; // discriminator that indicates which field below is in use
optional AttributeType type = 20; // discriminator that indicates which field below is in use
// Exactly ONE of the following fields must be present for this version of the IR
optional float f = 2; // float
optional int64 i = 3; // int
optional bytes s = 4; // UTF-8 string
optional TensorProto t = 5; // tensor value
optional GraphProto g = 6; // graph
optional float f = 2; // float
optional int64 i = 3; // int
optional bytes s = 4; // UTF-8 string
optional TensorProto t = 5; // tensor value
optional GraphProto g = 6; // graph
// Do not use field below, it's deprecated.
// optional ValueProto v = 12; // value - subsumes everything but graph
@ -144,7 +141,7 @@ message AttributeProto {
// the shape of the value.
message ValueInfoProto {
// This field MUST be present in this version of the IR.
optional string name = 1; // namespace Value
optional string name = 1; // namespace Value
// This field MUST be present in this version of the IR.
optional TypeProto type = 2;
// A human-readable documentation for this value. Markdown is allowed.
@ -156,20 +153,20 @@ message ValueInfoProto {
// 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
// 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.
message NodeProto {
repeated string input = 1; // namespace Value
repeated string output = 2; // namespace Value
repeated string input = 1; // namespace Value
repeated string output = 2; // namespace Value
// An optional identifier for this node in a graph.
// This field MAY be absent in ths version of the IR.
optional string name = 3; // namespace Node
optional string name = 3; // namespace Node
// The symbolic identifier of the Operator to execute.
optional string op_type = 4; // namespace Operator
// The domain of the OperatorSet that specifies the operator named by op_type.
optional string domain = 7; // namespace Domain
optional string domain = 7; // namespace Domain
// Additional named attributes.
repeated AttributeProto attribute = 5;
@ -236,7 +233,7 @@ message ModelProto {
// See https://developers.google.com/protocol-buffers/docs/proto3#maps
message StringStringEntryProto {
optional string key = 1;
optional string value= 2;
optional string value = 2;
};
message QuantInfo {
@ -249,7 +246,7 @@ message QuantInfo {
// Graphs
//
// A graph defines the computational logic of a model and is comprised of a parameterized
// 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.
@ -258,7 +255,7 @@ message GraphProto {
repeated NodeProto node = 1;
// The name of the graph.
optional string name = 2; // namespace Graph
optional string name = 2; // 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
@ -275,7 +272,7 @@ message GraphProto {
// 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.
repeated ValueInfoProto value_info = 13;
// This field carries information to indicate the mapping among a tensor and its
// quantization parameter tensors. For example:
// A tensor “a” and its quantization parameter tensor are “scale_a” and
@ -315,8 +312,8 @@ message TensorProto {
DOUBLE = 11;
UINT32 = 12;
UINT64 = 13;
COMPLEX64 = 14; // complex with float32 real and imaginary components
COMPLEX128 = 15; // complex with float64 real and imaginary components
COMPLEX64 = 14; // complex with float32 real and imaginary components
COMPLEX128 = 15; // complex with float64 real and imaginary components
// Non-IEEE floating-point format based on IEEE754 single-precision
// floating-point number truncated to 16 bits.
@ -374,7 +371,7 @@ message TensorProto {
repeated int64 int64_data = 7 [packed = true];
// Optionally, a name for the tensor.
optional string name = 8; // namespace Value
optional string name = 8; // namespace Value
// A human-readable documentation for this tensor. Markdown is allowed.
optional string doc_string = 12;
@ -396,6 +393,29 @@ message TensorProto {
// When this field is present, the data_type field MUST NOT be STRING or UNDEFINED
optional bytes raw_data = 9;
// Data can be stored inside the protobuf file using type-specific fields or raw_data.
// Alternatively, raw bytes data can be stored in an external file, using the external_data field.
// external_data stores key-value pairs describing data location. Recognized keys are:
// - "location" (required) - file path relative to the filesystem directory where the ONNX
// protobuf model was stored
// - "offset" (optional) - position of byte at which stored data begins. Integer stored as string.
// Offset values SHOULD be multiples 4096 (page size) to enable mmap support.
// - "length" (optional) - number of bytes containing data. Integer stored as string.
// - "checksum" (optional) - SHA1 digest of file specified in under 'location' key.
repeated StringStringEntryProto external_data = 13;
// Location of the data for this tensor. MUST be one of:
// - DEFAULT - data stored inside the protobuf message. Data is stored in raw_data (if set) otherwise in type-specified field.
// - EXTERNAL - data stored in an external location as described by external_data field.
enum DataLocation {
DEFAULT = 0;
EXTERNAL = 1;
}
// If value not set, data is stored in raw_data (if set) otherwise in type-specified field.
optional DataLocation data_location = 14;
// For double
// Complex128 tensors are encoded as a single array of doubles,
// with the real components appearing in odd numbered positions,
@ -418,7 +438,7 @@ message TensorShapeProto {
message Dimension {
oneof value {
int64 dim_value = 1;
string dim_param = 2; // namespace Shape
string dim_param = 2; // namespace Shape
};
// Standard denotation can optionally be used to denote tensor
// dimensions with standard semantic descriptions to ensure
@ -434,7 +454,6 @@ message TensorShapeProto {
//
// The standard ONNX data types.
message TypeProto {
message Tensor {
// This field MUST NOT have the value of UNDEFINED
// This field MUST be present for this version of the IR.
@ -442,7 +461,6 @@ message TypeProto {
optional TensorShapeProto shape = 2;
}
// repeated T
message Sequence {
// The type and optional shape of each element of the sequence.
@ -476,12 +494,10 @@ message TypeProto {
optional TensorShapeProto shape = 2;
}
oneof value {
// The type of a tensor.
Tensor tensor_type = 1;
// NOTE: DNN-only implementations of ONNX MAY elect to not support non-tensor values
// as input and output to graphs and nodes. These types are needed to naturally
// support classical ML operators. DNN operators SHOULD restrict their input
@ -496,11 +512,10 @@ message TypeProto {
Opaque opaque_type = 7;
SparseTensor sparse_tensor_type = 8;
}
// An optional denotation can be used to denote the whole
// type with a standard semantic description as to what is
// An optional denotation can be used to denote the whole
// type with a standard semantic description as to what is
// stored inside. Refer to https://github.com/onnx/onnx/blob/master/docs/TypeDenotation.md#type-denotation-definition
// for pre-defined type denotations.
optional string denotation = 6;