The ONNX runtime provides a C# .Net binding for running inference on ONNX models in any of the .Net standard platforms. The API is .Net standard 1.1 compliant for maximum portability. This document describes the API.
The Microsoft.ML.OnnxRuntime Nuget package includes the precompiled binaries for ONNX runtime, and includes libraries for Windows and Linux platforms with X64 CPUs. The APIs conform to .Net Standard 1.1.
The unit tests contain several examples of loading models, inspecting input/output node shapes and types, as well as constructing tensors for scoring.
Here is simple tutorial for getting started with running inference on an existing ONNX model for a given input data. The model is typically trained using any of the well-known training frameworks and exported into the ONNX format. To start scoring using the model, open a session using the InferenceSession class, passing in the file path to the model as a parameter.
var session = new InferenceSession("model.onnx");
Once a session is created, you can execute queries using the Run method of the InferenceSession object. Currently, only Tensor type of input and outputs are supported. The results of the Run method are represented as a collection of .Net Tensor objects (as defined in System.Numerics.Tensor).
Tensor<float> t1, t2; // let's say data is fed into the Tensor objects
var inputs = new List<NamedOnnxValue>()
{
NamedOnnxValue.CreateFromTensor<float>("name1", t1),
NamedOnnxValue.CreateFromTensor<float>("name2", t2)
};
using (var results = session.Run(inputs))
{
// manipulate the results
}
You can load your input data into Tensor objects in several ways. A simple example is to create the Tensor from arrays.
float[] sourceData; // assume your data is loaded into a flat float array
int[] dimensions; // and the dimensions of the input is stored here
Tensor<float> t1 = new DenseTensor<float>(sourceData, dimensions);
Here is a complete sample code that runs inference on a pretrained model.
If using the GPU package, simply use the appropriate SessionOptions when creating an InferenceSession.
int gpuDeviceId = 0; // The GPU device ID to execute on var session = new InferenceSession("model.onnx", SessionOptions.MakeSessionOptionWithCudaProvider(gpuDeviceId));
class InferenceSession: IDisposable
The runtime representation of an ONNX model
InferenceSession(string modelPath);
InferenceSession(string modelPath, SesionOptions options);
IReadOnlyDictionary<NodeMetadata> InputMetadata;
Data types and shapes of the input nodes of the model.
IReadOnlyDictionary OutputMetadata;
Data types and shapes of the output nodes of the model.
IDisposableReadOnlyCollection<DisposableNamedOnnxValue> Run(IReadOnlyCollection<NamedOnnxValue> inputs);
Runs the model with the given input data to compute all the output nodes and returns the output node values. Both input and output are collection of NamedOnnxValue, which in turn is a name-value pair of string names and Tensor values. The outputs are IDisposable variant of NamedOnnxValue, since they wrap some unmanaged objects.
IDisposableReadOnlyCollection<DisposableNamedOnnxValue> Run(IReadOnlyCollection<NamedOnnxValue> inputs, IReadOnlyCollection<string> desiredOutputNodes);
Runs the model on given inputs for the given output nodes only.
The primary .Net object that is used for holding input-output of the model inference. Details on this newly introduced data type can be found in its open-source implementation. The binaries are available as a .Net NuGet package.
class NamedOnnxValue;
Represents a name-value pair of string names and any type of value that ONNX runtime supports as input-output data. Currently, only Tensor objects are supported as input-output values.
No public constructor available.
string Name; // read only
static NamedOnnxValue CreateFromTensor<T>(string name, Tensor<T>);
Creates a NamedOnnxValue from a name and a Tensor object.
Tensor<T> AsTensor<T>();
Accesses the value as a Tensor. Returns null if the value is not a Tensor.
class DisposableNamedOnnxValue: NamedOnnxValue, IDisposable;
This is a disposable variant of NamedOnnxValue, used for holding output values which contains objects allocated in unmanaged memory.
interface IDisposableReadOnlyCollection: IReadOnlyCollection, IDisposable
Collection interface to hold disposable values. Used for output of Run method.
class SessionOptions: IDisposable;
A collection of properties to be set for configuring the OnnxRuntime session
SessionOptions();
Constructs a SessionOptions will all options at default/unset values.
static SessionOptions Default; //read-only
Accessor to the default static option object
SetSessionGraphOptimizationLevel(GraphOptimizationLevel graph_transformer_level);
See [ONNX_Runtime_Graph_Optimizations.md] for more details.
SetSessionExecutionMode(ExecutionMode execution_mode);
- ORT_SEQUENTIAL - execute operators in the graph sequentially.
- ORT_PARALLEL - execute operators in the graph in parallel.
See [ONNX_Runtime_Perf_Tuning.md] for more details.
Container of metadata for a model graph node, used for communicating the shape and type of the input and output nodes.
int[] Dimensions;
Read-only shape of the node, when the node is a Tensor. Undefined if the node is not a Tensor.
System.Type ElementType;
Type of the elements of the node, when node is a Tensor. Undefined for non-Tensor nodes.
bool IsTensor;
Whether the node is a Tensor
class OnnxRuntimeException: Exception;
The type of Exception that is thrown in most of the error conditions related to Onnx Runtime.