logo
  • Overview
  • Install
  • Blog
  • Forum
  • Training
  • GitHub
English Chinese

OpenVINO 2022.1 introduces a new version of OpenVINO API (API 2.0). For more information on the changes and transition steps, see the transition guide

  • GET STARTED
    • Installing OpenVINO
      • OpenVINO Runtime
        • Linux
          • From Archive
          • From PyPI
          • From APT
          • From YUM
          • Using Docker
        • Windows
          • From Archive
          • From PyPI
          • Using Docker
        • macOS
          • From Archive
          • From PyPI
        • Raspbian OS
      • OpenVINO Development Tools
      • Build from Source
      • Creating a Yocto Image
    • Additional Configurations
      • For GPU
      • For NCS2
      • For VPU
        • IEI Mustang-V100-MX8-R10 Card
      • For GNA
    • Uninstalling
    • Troubleshooting
      • Issues & Solutions
      • Troubleshooting Steps
  • LEARN OPENVINO
    • Interactive Tutorials (Python)
      • Installation of OpenVINO™ Notebooks
    • Sample Applications (Python & C++)
      • Get Started with C++ Samples
      • Image Classification Async C++ Sample
      • Image Classification Async Python* Sample
      • Hello Classification C++ Sample
      • Hello Classification C Sample
      • Hello Classification Python* Sample
      • Hello Reshape SSD C++ Sample
      • Hello Reshape SSD Python* Sample
      • Hello NV12 Input Classification C++ Sample
      • Hello NV12 Input Classification C Sample
      • Hello Query Device C++ Sample
      • Hello Query Device Python* Sample
      • Model Creation C++ Sample
      • Model Creation Python* Sample
      • Automatic Speech Recognition C++ Sample
      • Automatic Speech Recognition Python* Sample
      • Sync Benchmark C++ Sample
      • Sync Benchmark Python* Sample
      • Throughput Benchmark C++ Sample
      • Throughput Benchmark Python* Sample
      • Bert Benchmark Python* Sample
      • Benchmark C++ Tool
      • Benchmark Python Tool
    • OpenVINO API 2.0 Transition
      • Installation & Deployment
      • Inference Pipeline
      • Configuring Devices
      • Preprocessing
      • Model Creation in OpenVINO™ Runtime
  • OPENVINO WORKFLOW
    • Model Preparation
      • Supported Model Formats
        • Converting a TensorFlow Model
        • Converting an ONNX Model
        • Converting a PyTorch Model
        • Converting a PaddlePaddle Model
        • Converting an MXNet Model
        • Converting a Caffe Model
        • Converting a Kaldi Model
        • Model Conversion Tutorials
          • Converting a TensorFlow Attention OCR Model
          • Converting a TensorFlow BERT Model
          • Converting a TensorFlow CRNN Model
          • Converting a TensorFlow DeepSpeech Model
          • Converting TensorFlow EfficientDet Models
          • Converting TensorFlow FaceNet Models
          • Converting a TensorFlow GNMT Model
          • Converting a TensorFlow Language Model on One Billion Word Benchmark
          • Converting a TensorFlow Neural Collaborative Filtering Model
          • Converting TensorFlow Object Detection API Models
          • Converting a TensorFlow RetinaNet Model
          • Converting TensorFlow Slim Image Classification Model Library Models
          • Converting TensorFlow Wide and Deep Family Models
          • Converting a TensorFlow XLNet Model
          • Converting TensorFlow YOLO Models
          • Converting an ONNX Faster R-CNN Model
          • Converting an ONNX GPT-2 Model
          • Converting an ONNX Mask R-CNN Model
          • Converting a PyTorch BERT-NER Model
          • Converting a PyTorch Cascade RCNN R-101 Model
          • Converting a PyTorch F3Net Model
          • Converting a PyTorch QuartzNet Model
          • Converting a PyTorch RCAN Model
          • Converting a PyTorch RNN-T Model
          • Converting a PyTorch YOLACT Model
          • Converting MXNet GluonCV Models
          • Converting an MXNet Style Transfer Model
          • Converting a Kaldi ASpIRE Chain Time Delay Neural Network (TDNN) Model
      • Model Optimizer Usage
        • Model Inputs and Outputs, Shapes and Layouts
        • Setting Input Shapes
        • Model Optimization Techniques
        • Cutting Off Parts of a Model
        • Embedding Preprocessing Computation
        • Compressing a Model to FP16
        • Model Optimizer Frequently Asked Questions
    • Model Optimization and Compression
      • Quantizing Models Post-training
        • Post-training Quantization with POT
          • Quantizing Model
            • DefaultQuantization Method
          • Quantizing Model with Accuracy Control
            • AccuracyAwareQuantization Method
          • Quantization Best Practices
            • Saturation Issue
          • API Reference
          • Command-line Interface
            • Simplified Mode
            • Configuration File Description
          • Examples
            • API Examples
            • Command-line Example
          • Post-training Optimization Tool FAQ
        • Post-training Quantization with NNCF (new)
          • Basic Quantization Flow
          • Quantizing with accuracy control
      • Compressing Models During Training
        • Quantization-aware Training (QAT)
        • Filter Pruning of Convolutional Models
      • (Experimental) Protecting Model
    • Running and Deploying Inference
      • Run and Deploy Locally
        • Run Inference
          • Integrate OpenVINO™ with Your Application
            • Model Representation in OpenVINO™ Runtime
            • OpenVINO™ Inference Request
            • OpenVINO™ Python API Exclusives
            • OpenVINO TensorFlow Frontend Capabilities and Limitations
          • Inference Modes
            • Automatic Device Selection
            • Multi-device execution
            • Heterogeneous execution
            • Automatic Batching
          • Inference Device Support
            • Query Device Properties - Configuration
            • CPU Device
            • GPU Device
            • VPU Devices
            • GNA Device
            • Arm® CPU Device
          • Changing Input Shapes
            • Troubleshooting Reshape Errors
          • Dynamic Shapes
            • When Dynamic Shapes API is Not Applicable
          • Stateful models
            • The LowLatencу2 Transformation
            • [DEPRECATED] The LowLatency Transformation
        • Optimize Inference
          • General Optimizations
          • High-level Performance Hints
          • Optimizing for Latency
            • Model Caching Overview
          • Optimizing for Throughput
          • Using Advanced Throughput Options: Streams and Batching
          • Optimize Preprocessing
            • Preprocessing API - details
            • Layout API Overview
            • Use Case - Integrate and Save Preprocessing Steps Into IR
          • Further Low-Level Implementation Details
        • Deploy Application with Deployment Manager
        • Local Distribution Libraries
  • DOCUMENTATION
    • API Reference
      • OpenVINO Runtime C++ API
        • Basics
          • Element types
            • Type_t
            • Type
          • Layout
            • Layout
          • DiscreteTypeInfo
          • Dimension
          • Extension
          • Input
          • Model
          • Node
          • Output
          • PartialShape
          • PrePostProcessor
          • Shape
        • Inference
          • Device properties
            • Affinity
            • Level
            • PerformanceMode
            • Priority
            • Type
            • Num
            • Priorities
            • Properties
            • UUID
          • Intel CPU specific properties
          • Intel GNA specific properties
            • ExecutionMode
            • HWGeneration
            • PWLDesignAlgorithm
          • Intel GPU OpenCL interoperability
            • ContextType
            • SharedMemType
            • ClBufferTensor
            • ClContext
            • ClImage2DTensor
            • D3DBufferTensor
            • D3DContext
            • D3DSurface2DTensor
            • USMTensor
            • VAContext
            • VASurfaceTensor
          • Intel GPU OpenCL specific properties
          • Intel HDDL specific properties
          • Intel MYRIAD & HDDL specific properties
            • Protocol
          • Intel MYRIAD specific properties
            • DDRType
          • ProfilingInfo
            • Status
          • Allocator
          • Busy
          • Cancelled
          • CompiledModel
          • Core
          • InferRequest
          • RemoteContext
          • RemoteTensor
          • Tensor
          • VariableState
        • Operation sets
          • OpSet
        • Operations
          • AUGRUCell
          • AUGRUSequence
          • Abs
          • Acos
          • Acosh
          • AdaptiveAvgPool
          • AdaptiveMaxPool
          • Add
          • Asin
          • Assign
          • Assign
          • Atan
          • Atanh
          • BatchNormInference
          • BatchNormInference
          • BatchToSpace
          • BinaryConvolution
            • BinaryConvolutionMode
          • Broadcast
          • Broadcast
          • Bucketize
          • CTCGreedyDecoder
          • CTCGreedyDecoderSeqLen
          • CTCLoss
          • Ceiling
          • Clamp
          • Concat
          • Constant
          • Convert
          • ConvertLike
          • Convolution
          • ConvolutionBackpropData
          • Cos
          • Cosh
          • CumSum
          • DFT
          • DeformableConvolution
          • DeformableConvolution
          • DeformablePSROIPooling
          • DepthToSpace
            • DepthToSpaceMode
          • Divide
          • Einsum
          • Elu
          • EmbeddingBagOffsetsSum
          • EmbeddingBagPackedSum
          • EmbeddingSegmentsSum
          • Equal
          • Erf
          • Exp
          • ExperimentalDetectronDetectionOutput
            • Attributes
          • ExperimentalDetectronGenerateProposalsSingleImage
            • Attributes
          • ExperimentalDetectronPriorGridGenerator
            • Attributes
          • ExperimentalDetectronROIFeatureExtractor
            • Attributes
          • ExperimentalDetectronTopKROIs
          • ExtractImagePatches
          • Eye
          • FakeQuantize
          • Floor
          • FloorMod
          • GRUCell
          • GRUSequence
          • Gather
          • Gather
          • Gather
          • GatherElements
          • GatherND
          • GatherND
          • GatherTree
          • Gelu
          • Gelu
          • Greater
          • GreaterEqual
          • GridSample
            • InterpolationMode
            • PaddingMode
            • Attributes
          • HSigmoid
          • HSwish
          • HardSigmoid
          • I420toBGR
          • I420toRGB
          • IDFT
          • If
            • BodyIndexes
          • Interpolate
            • InterpolateMode
            • Attributes
          • Interpolate
            • CoordinateTransformMode
            • InterpolateMode
            • NearestMode
            • ShapeCalcMode
            • InterpolateAttrs
          • IsFinite
          • IsInf
            • Attributes
          • IsNaN
          • LRN
          • LSTMCell
          • LSTMCell
          • LSTMSequence
          • LSTMSequence
          • Less
          • LessEqual
          • Log
          • LogSoftmax
          • LogicalAnd
          • LogicalNot
          • LogicalOr
          • LogicalXor
          • Loop
            • SpecialBodyPorts
          • MVN
          • MVN
          • MatMul
          • MatrixNms
            • DecayFunction
            • SortResultType
            • Attributes
          • MaxPool
          • MaxPool
          • Maximum
          • Minimum
          • Mish
          • Mod
          • Multiply
          • NV12toBGR
          • NV12toRGB
          • Negative
          • NonMaxSuppression
          • NonMaxSuppression
            • BoxEncodingType
          • NonMaxSuppression
            • BoxEncodingType
          • NonMaxSuppression
            • BoxEncodingType
          • NonZero
          • NormalizeL2
          • NotEqual
          • OneHot
          • Op
          • PRelu
          • PSROIPooling
          • Pad
          • Parameter
          • Power
          • PriorBox
            • Attributes
          • PriorBox
            • Attributes
          • PriorBoxClustered
            • Attributes
          • Proposal
            • Attributes
          • Proposal
          • RNNCell
          • RNNSequence
          • ROIAlign
            • PoolingMode
          • ROIPooling
          • RandomUniform
          • Range
          • Range
          • ReadValue
          • ReadValue
          • ReduceL1
          • ReduceL2
          • ReduceLogicalAnd
          • ReduceLogicalOr
          • ReduceMax
          • ReduceMean
          • ReduceMin
          • ReduceProd
          • ReduceSum
          • RegionYolo
          • Relu
          • ReorgYolo
          • Reshape
          • Result
          • Reverse
            • Mode
          • ReverseSequence
          • Roll
          • Round
            • RoundMode
          • ScatterElementsUpdate
          • ScatterNDUpdate
          • ScatterUpdate
          • Select
          • Selu
          • ShapeOf
          • ShapeOf
          • ShuffleChannels
          • Sigmoid
          • Sign
          • Sin
          • Sinh
          • Sink
          • Slice
          • SoftPlus
          • Softmax
          • Softmax
          • SpaceToBatch
          • SpaceToDepth
            • SpaceToDepthMode
          • Split
          • Sqrt
          • SquaredDifference
          • Squeeze
          • StridedSlice
          • Subtract
          • Swish
          • Tan
          • Tanh
          • TensorIterator
          • Tile
          • TopK
          • TopK
          • Transpose
            • Ins
            • Outs
          • Unique
          • Unsqueeze
          • VariadicSplit
          • Xor
        • Transformation passes
          • ConstantFolding
          • ConvertFP32ToFP16
          • GraphRewrite
          • LowLatency2
          • MakeStateful
          • Manager
          • MatcherPass
          • ModelPass
          • PassBase
          • PassConfig
          • Serialize
            • Version
          • StreamSerialize
            • DataHeader
          • Validate
          • VisualizeTree
        • ov
          • batch_util
          • cmp
            • Bound
            • Between
            • Equal
          • descriptor
            • Input
            • Output
            • Tensor
          • detail
          • device
            • capability
          • element
          • frontend
            • ExtensionHolder
            • FrontEndPluginInfo
            • ConversionExtension
            • ConversionExtensionBase
            • DecoderTransformationExtension
            • FWVisitor
            • FrontEnd
            • FrontEndManager
            • GeneralFailure
            • InitializationFailure
            • InputModel
            • NodeContext
            • NotImplementedFailure
            • OpConversionFailure
            • OpConversionFunction
            • OpExtensionBase
            • OpValidationFailure
            • Place
            • ProgressReporterExtension
            • TelemetryExtension
          • helpers
            • NumOfLambdaArgs
          • hint
          • intel_auto
          • intel_cpu
          • intel_gna
          • intel_gpu
            • capability
            • hint
            • memory_type
            • ocl
          • intel_myriad
            • hddl
          • layout
          • log
          • op
            • ShapeInferLSTM
            • ShapeInferRange
            • internal
            • rnn
            • util
            • v0
            • v1
            • v10
            • v3
            • v4
            • v5
            • v6
            • v7
            • v8
            • v9
            • AutoBroadcastType
            • BroadcastType
            • EpsMode
            • GeluApproximationMode
            • LSTMWeightsFormat
            • MVNEpsMode
            • PadMode
            • PadType
            • RecurrentSequenceDirection
            • RoundingType
            • TopKMode
            • TopKSortType
            • AutoBroadcastSpec
            • BroadcastModeSpec
            • TemporaryReplaceOutputType
            • TypeRelaxed
            • TypeRelaxedBase
          • opset1
          • opset10
          • opset2
          • opset3
          • opset4
          • opset5
          • opset6
          • opset7
          • opset8
          • opset9
          • pass
            • pattern
            • PassProperty
            • AddAddFusion
            • AddMultiplyFusion
            • AlignEltwiseInputRanks
            • Attributes
            • BackwardGraphRewrite
            • BatchNormDecomposition
            • ChangePlaceholderTypes
            • CommonOptimizations
            • ConvertBroadcast3
            • ConvertBroadcastToTiles
            • ConvertConvertLike
            • ConvertDepthToSpace
            • ConvertDivide
            • ConvertDivideWithConstant
            • ConvertGELU
            • ConvertGP9ToGPIEInternal
            • ConvertMatrixNmsToMatrixNmsIE
            • ConvertMinimum
            • ConvertMod
            • ConvertMulticlassNms8ToMulticlassNms9
            • ConvertMulticlassNmsToMulticlassNmsIE
            • ConvertNMS1ToNMS5
            • ConvertNMS1ToNMS9
            • ConvertNMS3ToNMS5
            • ConvertNMS3ToNMS9
            • ConvertNMS4ToNMS5
            • ConvertNMS4ToNMS9
            • ConvertNMS5ToNMS9
            • ConvertNMS9ToNMSIEInternal
            • ConvertNMSToNMSIEInternal
            • ConvertNegative
            • ConvertOpSet2ToOpSet1
            • ConvertOpSet3ToOpSet2
            • ConvertPrecision
            • ConvertReduceLogicalAndToReshape
            • ConvertReduceLogicalOrToReshape
            • ConvertReduceMaxToPooling
            • ConvertReduceMaxToReshape
            • ConvertReduceMeanToPooling
            • ConvertReduceMeanToReshape
            • ConvertReduceMinToReshape
            • ConvertReduceSumToPooling
            • ConvertReduceSumToReshape
            • ConvertReduceToPooling
            • ConvertReduceToReshape
            • ConvertSequenceToTensorIterator
            • ConvertShapeOf3
            • ConvertShuffleChannels3
            • ConvertSpaceToDepth
            • ConvertSubtract
            • ConvertTensorIteratorToSequence
            • ConvertTopK3
            • ConvolutionBackpropDataMultiplyFusion
            • ConvolutionMultiplyFusion
            • DisableConstantFolding
            • DisableFoldSubgraphEmptyInputs
            • DisableRemoveConcatZeroDimInput
            • DisableShapeOfConstantFolding
            • EliminateDuplicateTIInputs
            • EliminateSplitConcat
            • FindBatch
            • FoldSubgraphEmptyInputs
            • FuseFilteringBoxesBySize
            • GroupConvolutionBackpropDataMultiplyFusion
            • GroupConvolutionMultiplyFusion
            • Hash
            • MOCLegacyTransformations
            • MOCTransformations
            • MatMulConstTransposesExtraction
            • MultiplyConvolutionBackpropDataFusion
            • MultiplyGroupConvolutionBackpropDataFusion
            • MultiplyGroupConvolutionFusion
            • MultiplyMultiplyFusion
            • NodeRegistry
            • NopElimination
            • PadFusion
            • Proposal4Scales
            • PullTransposeThroughFQUp
            • RemoveFilteringBoxesBySize
            • RemoveMultiSubGraphOpDanglingParams
            • ReshapeBMatMul
            • ReverseShapeAndTypeInfer
            • SmartReshape
            • TransposeMatMul
            • TransposeSinkingBinaryElementwiseBackward
            • TransposeSinkingBinaryElementwiseForward
            • TransposeSinkingConcatBackward
            • TransposeSinkingConcatForward
            • TransposeSinkingGeneral
            • TransposeSinkingGeneralBackward
            • TransposeSinkingGeneralForward
            • TransposeSinkingSplitBackward
            • TransposeSinkingSplitForward
            • TransposeSinkingUnaryBackward
            • TransposeSinkingUnaryForward
            • UniqueDecomposition
          • preprocess
            • ColorFormat
            • ResizeAlgorithm
            • InputInfo
            • InputModelInfo
            • InputTensorInfo
            • OutputInfo
            • OutputModelInfo
            • OutputTensorInfo
            • PostProcessSteps
            • PreProcessSteps
            • TensorInfoMemoryType
          • runtime
          • streams
          • util
            • LOG_TYPE
            • AsTypePtr
            • FileTraits
            • ConstString
            • LogHelper
            • Logger
          • Direction
          • PropertyMutability
          • CheckLocInfo
          • MemBandwidthPressure
          • Property
          • PropertyName
          • RawNodeOutput
          • SoPtr
          • Version
          • element_type_traits
          • AllocatorImpl
          • Any
            • EqualityComparable
            • HasBaseMemberType
            • Impl
            • TupleToTypeIndex
            • Base
          • AssertFailure
          • AttributeAdapter
          • AttributeVisitor
          • AxisSet
          • AxisVector
          • BaseOpExtension
          • Coordinate
          • CoordinateDiff
          • DirectValueAccessor
          • EnumAttributeAdapterBase
          • EnumMask
          • EnumNames
          • Exception
          • IndirectScalarValueAccessor
          • IndirectVectorValueAccessor
          • Input
          • Interval
          • LayoutAttribute
          • NmsSelectedIndices
          • NodeValidationFailure
          • NotImplemented
          • OpExtension
          • Output
          • PrecisionSensitive
          • PreprocessingAttribute
          • PrimitivesPriority
          • Property
            • Forward
          • RuntimeAttribute
          • SeqGen
          • Strides
          • StridesPropagation
          • ValueAccessor
          • VisitorAdapter
          • bfloat16
            • F32
          • float16
            • F32
      • OpenVINO Runtime C API
        • Basics
          • ov_element_type_e
          • ov_status_e
        • Compiled Model
          • ov_compiled_model_t
        • Core
          • ov_available_devices_t
          • ov_core_t
          • ov_core_version
          • ov_core_version_list
          • ov_version
        • Dimension
          • ov_dimension
        • Infer Request
          • ov_ProfilingInfo_t
          • ov_callback_t
          • ov_infer_request_t
          • ov_profiling_info_list_t
        • Layout
          • ov_layout_t
        • Model
          • ov_model_t
        • Node
          • ov_output_const_port_t
          • ov_output_port_t
        • Partial Shape
          • ov_partial_shape
        • Pre Post Process
          • ov_color_format_e
          • ov_preprocess_resize_algorithm_e
          • ov_preprocess_input_info_t
          • ov_preprocess_input_model_info_t
          • ov_preprocess_input_tensor_info_t
          • ov_preprocess_output_info_t
          • ov_preprocess_output_tensor_info_t
          • ov_preprocess_prepostprocessor_t
          • ov_preprocess_preprocess_steps_t
        • Property
        • Rank
          • ov_rank_t
        • Shape
          • ov_shape_t
        • Tensor
          • ov_tensor_t
      • OpenVINO Python API
        • OpenVINO Python API - Compatibility
    • Tool Ecosystem
      • OpenVINO™ integration with TensorFlow
      • OpenVINO™ Security Add-on
      • Compile Tool
      • Tuning Utilities
        • Cross Check Tool
      • OpenVINO™ Deep Learning Workbench Overview
    • OpenVINO Extensibility
      • Custom OpenVINO™ Operations
      • Frontend Extensions
      • How to Implement Custom GPU Operations
      • How to Implement Custom Layers for VPU (Intel® Neural Compute Stick 2)
      • Model Optimizer Extensibility
        • Extending Model Optimizer with Caffe Python Layers
      • Overview of Transformations API
        • OpenVINO Model Pass
        • OpenVINO Matcher Pass
        • OpenVINO Graph Rewrite Pass
      • OpenVINO Plugin Developer Guide
        • Implement Plugin Functionality
        • Implement Executable Network Functionality
        • Implement Synchronous Inference Request
        • Implement Asynchronous Inference Request
        • Build Plugin Using CMake
        • Plugin Testing
        • Advanced Topics
          • Quantized networks compute and restrictions
          • OpenVINO™ Low Precision Transformations
            • Attributes
            • Step 1. Prerequisites transformations
            • Step 2. Markup transformations
            • Step 3. Main transformations
            • Step 4. Cleanup transformations
        • Plugin API Reference
          • Inference Engine Plugin API
            • Asynchronous Inference Request base classes
            • Blob creation and memory utilities
            • Error handling and debug helpers
            • Executable Network base classes
            • Execution graph utilities
            • FP16 to FP32 precision utilities
            • File utilities
            • ITT profiling utilities
            • Inference Request base classes
            • Plugin base classes
            • Preprocessing API
            • System configuration utilities
            • Threading utilities
            • Variable state base classes
            • XML helper utilities
          • Inference Engine Transformation API
            • Common optimization passes
            • Conversion from opset2 to opset1
            • Conversion from opset3 to opset2
            • Runtime information
    • Media Processing and CV Libraries
      • Intel® Deep Learning Streamer
      • Introduction to OpenCV Graph API (G-API)
        • Graph API Kernel API
        • Implementing a Face Beautification Algorithm
        • Building a Face Analytics Pipeline
      • OpenCV Developer Guide
      • OpenCL™ Developer Guide
      • OneVPL Developer Guide
    • OpenVINO™ Security
      • Deep Learning Workbench Security
      • Using Encrypted Models with OpenVINO
  • MODEL ZOO
  • RESOURCES
    • Performance Benchmarks
      • Intel® Distribution of OpenVINO™ toolkit Benchmark Results
        • Performance Information F.A.Q.
        • Model Accuracy and Performance for INT8 and FP32
        • Performance Data Spreadsheet (download xlsx)
      • Getting Performance Numbers
    • OpenVINO IR format
      • Deep Learning Network Intermediate Representation and Operation Sets in OpenVINO™
      • Available Operations Sets
        • opset10
        • opset9
        • opset8
        • opset7
        • opset6
        • opset5
        • opset4
        • opset3
        • opset2
        • opset1
      • Broadcast Rules For Elementwise Operations
      • Operations Specifications
        • Abs-1
        • Acos-1
        • Acosh-3
        • AdaptiveAvgPool-8
        • AdaptiveMaxPool-8
        • 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-3
        • DeformableConvolution-1
        • DeformableConvolution-8
        • DeformablePSROIPooling-1
        • DepthToSpace-1
        • DetectionOutput-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
        • Eye-9
        • FakeQuantize-1
        • FloorMod-1
        • Floor-1
        • GridSample-9
        • GRN-1
        • GRUCell-3
        • GRUSequence-5
        • GatherTree-1
        • Gather-1
        • Gather-7
        • Gather-8
        • GatherElements-6
        • GatherND-5
        • GatherND-8
        • GELU-2
        • GELU-7
        • GenerateProposals-9
        • GreaterEqual-1
        • Greater-1
        • GroupConvolutionBackpropData-1
        • GroupConvolution-1
        • HardSigmoid-1
        • HSigmoid-5
        • HSwish-4
        • I420toBGR-8
        • I420toRGB-8
        • IDFT-7
        • IRDFT-9
        • If-8
        • Interpolate-1
        • Interpolate-4
        • IsFinite-10
        • IsInf-10
        • IsNaN-10
        • 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
        • MatrixNms-8
        • MaxPool-1
        • MaxPool-8
        • Maximum-1
        • Minimum-1
        • Mish-4
        • Mod-1
        • MulticlassNonMaxSuppression-8
        • MulticlassNonMaxSuppression-9
        • Multiply-1
        • Negative-1
        • NonMaxSuppression-1
        • NonMaxSuppression-3
        • NonMaxSuppression-4
        • NonMaxSuppression-5
        • NonMaxSuppression-9
        • NonZero-3
        • NormalizeL2-1
        • NotEqual-1
        • NV12toBGR-8
        • NV12toRGB-8
        • OneHot-1
        • PReLU-1
        • PSROIPooling-1
        • Pad-1
        • Parameter-1
        • Power-1
        • PriorBoxClustered-1
        • PriorBox-1
        • PriorBox-8
        • Proposal-1
        • Proposal-4
        • RandomUniform-8
        • Range-1
        • Range-4
        • RDFT-9
        • 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-1
        • ReverseSequence-1
        • RNNCell-3
        • RNNSequence-5
        • ROIAlign-3
        • ROIAlign-9
        • ROIPooling-1
        • Roll-7
        • Round-5
        • ScatterElementsUpdate-3
        • ScatterNDUpdate-3
        • ScatterUpdate-3
        • Select-1
        • Selu-1
        • ShapeOf-1
        • ShapeOf-3
        • ShuffleChannels-1
        • Sigmoid-1
        • Sign-1
        • Sin-1
        • Sinh-1
        • Slice-8
        • SoftMax-1
        • SoftMax-8
        • SoftPlus-4
        • SoftSign-9
        • 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
        • Unique-10
        • Unsqueeze-1
        • VariadicSplit-1
      • Intermediate Representation Suitable for INT8 Inference
    • Supported Devices
    • Supported Models
    • Supported Framework Layers
    • Glossary
    • Legal Information
    • OpenVINO™ Telemetry
    • Case Studies
  • RELEASE NOTES
On this page
.pdf .zip

Media Processing and CV Libraries¶

  • Intel® Deep Learning Streamer
  • Introduction to OpenCV Graph API (G-API)
  • OpenCV Developer Guide
  • OpenCL™ Developer Guide
  • OneVPL Developer Guide

©2022 Intel Corporation Terms of Use Cookies Privacy

Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.