OpenVINO Toolkit
  • Converting and Preparing Models
    • Model Optimizer Developer Guide
      • Model Optimizer Developer Guide
      • Preparing and Optimizing Your Trained Model
        • Preparing and Optimizing Your Trained Model
        • Configuring the Model Optimizer
        • Converting a Model to Intermediate Representation (IR)
          • Converting a Model to Intermediate Representation (IR)
          • Converting a Model Using General Conversion Parameters
          • Converting a Caffe* Model
          • Converting a TensorFlow* Model
            • Converting a TensorFlow* Model
            • Converting YOLO* Models from DarkNet to the Intermediate Representation
            • Converting FaceNet Models from TensorFlow
            • Converting Neural Collaborative Filtering Model from TensorFlow
            • Converting DeepSpeech Model from TensorFlow
            • Converting Language Model on One Billion Word Benchmark from TensorFlow
            • Converting TensorFlow* Object Detection API Models
            • Converting TensorFlow*-Slim Image Classification Model Library Models
            • Converting CRNN Model from TensorFlow
            • Converting GNMT from TensorFlow
            • Converting BERT from TensorFlow
            • Convert TensorFlow* XLNet Model to the Intermediate Representation
            • Converting TensorFlow* Wide and Deep Models from TensorFlow
            • Converting EfficientDet Models from TensorFlow
          • Converting a MXNet* Model
            • Converting a MXNet* Model
            • Converting a Style Transfer Model from MXNet
            • Converting GluonCV* Models
          • Converting Your Kaldi* Model
            • Converting Your Kaldi* Model
            • Convert Kaldi* ASpIRE Chain Time Delay Neural Network (TDNN) Model to the Intermediate Representation
          • Converting Your ONNX* Model
            • Converting Your ONNX* Model
            • Convert ONNX* Faster R-CNN Model to the Intermediate Representation
            • Convert ONNX* Mask R-CNN Model to the Intermediate Representation
            • Convert ONNX* GPT-2 Model to the Intermediate Representation
            • Convert DLRM ONNX* Model to the Intermediate Representation
            • Converting Your PyTorch* Model
              • Converting Your PyTorch* Model
              • Convert PyTorch* QuartzNet Model
              • Convert PyTorch* YOLACT Model
              • Convert PyTorch* F3Net Model
          • Model Optimizations Techniques
          • Cutting off Parts of a Model
          • Sub-graph Replacement in Model Optimizer
          • Supported Framework Layers
          • [DEPRECATED] IR Notation Reference
          • IR suitable for INT8 inference
        • Model Optimizer Extensibility
          • Model Optimizer Extensibility
          • Extending Model Optimizer with New Primitives
          • Extending Model Optimizer with Caffe* Python Layers
          • Extending Model Optimizer for Custom MXNet* Operations
          • Legacy Mode for Caffe* Custom Layers
          • [DEPRECATED] Offloading Sub-Graph Inference
      • Model Optimizer Frequently Asked Questions
      • Known Issues
    • Model Downloader
    • Custom Operations Guide
      • Custom Operations Guide
  • Intermediate Representation and Operations Sets
    • Intermediate Representation and Operations Sets
    • Available Operations Sets
      • Available Operations Sets
      • opset7 Specification
      • opset6 Specification
      • opset5 Specification
      • opset4 Specification
      • opset3 Specification
      • opset2 Specification
      • opset1 Specification
    • Operations Specifications
      • Abs-1
      • Acos-1
      • Acosh-3
      • Add-1
      • Asin-1
      • Asinh-3
      • Assign-3
      • Atan-1
      • Atanh-3
      • AvgPool-1
      • BatchNormInference-1
      • BatchNormInference-5
      • BatchToSpace-2
      • BinaryConvolution-1
      • Broadcast-1
      • Broadcast-3
      • Bucketize-3
      • CTCGreedyDecoder-1
      • CTCGreedyDecoderSeqLen-6
      • Ceiling-1
      • Clamp-1
      • Concat-1
      • Constant-1
      • ConvertLike-1
      • Convert-1
      • ConvolutionBackpropData-1
      • Convolution-1
      • Cos-1
      • Cosh-1
      • CTCLoss-4
      • CumSum
      • DeformableConvolution-1
      • DeformablePSROIPooling-1
      • DepthToSpace-1
      • DetectionOutput-1
      • DFT-7
      • Divide-1
      • Einsum-7
      • Elu-1
      • EmbeddingBagOffsetsSum-3
      • EmbeddingBagPackedSum-3
      • EmbeddingSegmentsSum-3
      • Equal-1
      • Erf-1
      • Exp-1
      • ExperimentalDetectronDetectionOutput-6
      • ExperimentalDetectronGenerateProposalsSingleImage-6
      • ExperimentalDetectronPriorGridGenerator-6
      • ExperimentalDetectronROIFeatureExtractor-6
      • ExperimentalDetectronTopKROIs-6
      • ExtractImagePatches-3
      • FakeQuantize-1
      • FloorMod-1
      • Floor_1
      • GRN-1
      • GRUCell-3
      • GRUSequence-5
      • GatherTree-1
      • Gather-1
      • Gather-7
      • GatherElements-6
      • GatherND-5
      • Gelu-2
      • Gelu-7
      • GreaterEqual-1
      • Greater-1
      • GroupConvolutionBackpropData-1
      • GroupConvolution-1
      • HardSigmoid-1
      • HSigmoid-5
      • HSwish-4
      • IDFT-7
      • Interpolate-1
      • Interpolate-4
      • LRN-1
      • LSTMCell-1
      • LSTMSequence-1
      • LessEqual-1
      • Less-1
      • Log-1
      • LogicalAnd-1
      • LogicalNot-1
      • LogicalOr-1
      • LogicalXor-1
      • LogSoftmax-5
      • Loop-5
      • MVN-1
      • MVN-6
      • MatMul-1
      • MaxPool-1
      • Maximum-1
      • Minimum-1
      • Mish-4
      • Mod-1
      • Multiply-1
      • Negative-1
      • NonMaxSuppression-1
      • NonMaxSuppression-3
      • NonMaxSuppression-4
      • NonMaxSuppression-5
      • NonZero-3
      • NormalizeL2-1
      • NotEqual-1
      • OneHot-1
      • PReLU-1
      • PSROIPooling-1
      • Pad-1
      • Parameter-1
      • Power-1
      • PriorBoxClustered-1
      • PriorBox-1
      • Proposal-1
      • Proposal-4
      • Range-1
      • Range-4
      • ReadValue-3
      • ReLU-1
      • ReduceL1-4
      • ReduceL2-4
      • ReduceLogicalAnd-1
      • ReduceLogicalOr-1
      • ReduceMax-1
      • ReduceMean-1
      • ReduceMin-1
      • ReduceProd-1
      • ReduceSum-1
      • RegionYolo-1
      • ReorgYolo-1
      • Reshape-1
      • Result-1
      • Reverse
      • ReverseSequence-1
      • RNNCell-3
      • RNNSequence-5
      • ROIAlign-3
      • ROIPooling-1
      • Roll-7
      • Round-5
      • ScatterElementsUpdate-3
      • ScatterNDUpdate
      • ScatterUpdate-3
      • Select-1
      • Selu-1
      • ShapeOf-1
      • ShapeOf-3
      • ShuffleChannels-1
      • Sigmoid-1
      • Sign-1
      • Sin-1
      • Sinh-1
      • SoftMax-1
      • SoftPlus-4
      • SpaceToBatch-2
      • SpaceToDepth-1
      • Split-1
      • Sqrt-1
      • SquaredDifference-1
      • Squeeze-1
      • StridedSlice-1
      • Subtract-1
      • Swish-4
      • Tan-1
      • Tanh-1
      • TensorIterator-1
      • Tile-1
      • TopK-1
      • TopK-3
      • Transpose-1
      • Unsqueeze-1
      • VariadicSplit-1
  • Deploying Inference
    • Deploying Inference
    • Inference Engine Developer Guide
      • Inference Engine Developer Guide
      • Inference Engine API Changes History
      • Inference Engine Memory primitives
      • Inference Engine Device Query API
      • Inference Engine Extensibility Mechanism
        • Inference Engine Extensibility Mechanism
        • Extension Library
        • Custom Operations
        • CPU Kernels Extensibility
        • GPU Kernels Extensibility
        • VPU Kernels Extensibility
        • Build Extension Library Using CMake
        • Custom ONNX operators
      • Integrate the Inference Engine with Your Application
      • [DEPRECATED] Migration from Inference Engine Plugin API to Core API
      • Introduction to Performance Topics
      • Inference Engine Python* API Overview
      • Read an ONNX model
      • [DEPRECATED] Import an ONNX model
      • Using Dynamic Batching Feature
      • Using Static Shape Infer Feature
      • Using GPU kernels tuning
      • Using Bfloat16 Inference
        • Using Bfloat16 Inference
      • Using Low-Precision 8-bit Integer Inference
        • Using Low-Precision 8-bit Integer Inference
      • Utilities to Validate Your Converted Model
        • Utilities to Validate Your Converted Model
        • Using Cross Check Tool for Per-Layer Comparison Between Plugins
      • Introduction to OpenVINO state API
      • Supported Devices
        • Supported Devices
        • GPU Plugin
          • GPU Plugin
          • RemoteBlob API of GPU Plugin
        • CPU Plugin
        • [DEPRECATED] FPGA Plugin
        • VPU Plugins
          • VPU Plugins
          • MYRIAD Plugin
          • HDDL Plugin
        • Heterogeneous Plugin
        • Multi-Device Plugin
        • GNA Plugin
      • Known Issues
      • Glossary
    • nGraph Developer Guide
      • nGraph Developer Guide
        • nGraph Developer Guide
          • Table of Contents
      • Introduction
      • Basic Concepts
      • Operation sets
      • Graph building
      • Transfomations
      • Debug capabilities
      • Python API
    • Deployment Manager Guide
    • Compile Tool
    • API References
      • Inference Engine C API Reference
      • Inference Engine Python API Reference
      • nGraph C++ API Reference
      • nGraph Python API Reference
    • Inference Engine Plugin Development Guide
 
OpenVINO Toolkit
  • Docs »
  • nGraph Developer Guide »
  • Deploying Inference »
  • nGraph Developer Guide

nGraph Developer Guide

Table of Contents

  • Introduction to the nGraph
  • Basic Concepts
  • Operation Sets
  • Graph Constructing
  • Transformations
  • Debug Capabilities
  • Python API
Next Previous

Built with MkDocs using a theme provided by Read the Docs.