From a2ca1d44997d196bca1eb9695740361e33d73dc6 Mon Sep 17 00:00:00 2001 From: Ilya Churaev Date: Mon, 7 Feb 2022 06:57:35 +0300 Subject: [PATCH] Merge IE & nGraph DG (#10055) * Changed folder for documentation * Fixed links * Merged nGraph DG to OpenVINO Runtime UG * Fixed errors * Fixed some issues * Fixed tree * Fixed typo * Update docs/documentation.md Co-authored-by: Andrey Zaytsev * Update README.md Co-authored-by: Andrey Zaytsev * Update README.md Co-authored-by: Andrey Zaytsev * Fixed name * FIxed snippets * Small fixes * Update docs/HOWTO/Custom_Layers_Guide.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Fixed comments * Try to fix doc * Try to fix doc issue * Update docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev * Update docs/OV_Runtime_UG/model_representation.md Co-authored-by: Andrey Zaytsev Co-authored-by: Andrey Zaytsev --- README.md | 5 +- docs/HOWTO/Custom_Layers_Guide.md | 32 +-- .../Deep_Learning_Model_Optimizer_DevGuide.md | 3 +- .../prepare_model/Additional_Optimizations.md | 2 +- .../Getting_performance_numbers.md | 8 +- .../prepare_model/Model_Optimizer_FAQ.md | 4 +- .../convert_model/Convert_Model_From_Caffe.md | 4 +- .../convert_model/Convert_Model_From_Kaldi.md | 4 +- .../convert_model/Convert_Model_From_MxNet.md | 4 +- .../Convert_Model_From_Paddle.md | 4 +- .../Convert_Model_From_PyTorch.md | 4 +- .../Convert_Model_From_TensorFlow.md | 4 +- .../IR_suitable_for_INT8_inference.md | 2 +- .../pytorch_specific/Convert_RNNT.md | 2 +- .../Convert_BERT_From_Tensorflow.md | 2 +- .../Convert_DeepSpeech_From_Tensorflow.md | 2 +- .../Convert_Object_Detection_API_Models.md | 4 +- .../Customize_Model_Optimizer.md | 10 +- docs/{IE_DG => OV_Runtime_UG}/API_Changes.md | 0 .../Bfloat16Inference.md | 0 ...Deep_Learning_Inference_Engine_DevGuide.md | 6 +- .../DynamicBatching.md | 0 .../Extensibility_DG/AddingNGraphOps.md | 0 .../Extensibility_DG/Building.md | 0 .../Extensibility_DG/CPU_Kernel.md | 0 .../Extensibility_DG/Custom_ONNX_Ops.md | 0 .../Extensibility_DG/Extension.md | 0 .../Extensibility_DG/GPU_Kernel.md | 0 .../Extensibility_DG/Intro.md | 0 .../Extensibility_DG/VPU_Kernel.md | 0 docs/{IE_DG => OV_Runtime_UG}/Glossary.md | 0 .../InferenceEngine_QueryAPI.md | 0 .../{IE_DG => OV_Runtime_UG}/Int8Inference.md | 0 ...grate_with_customer_application_new_API.md | 12 +- .../Known_Issues_Limitations.md | 0 .../Memory_primitives.md | 0 .../Model_caching_overview.md | 0 docs/{IE_DG => OV_Runtime_UG}/ONNX_Support.md | 0 .../Operations_specifications.md | 0 .../Paddle_Support.md | 0 .../PythonPackage_Overview.md | 0 .../Samples_Overview.md | 0 .../ShapeInference.md | 8 +- .../img/BASIC_FLOW_IE_C.svg | 0 .../img/BASIC_FLOW_MO.svg | 0 .../img/BASIC_FLOW_MO_simplified.svg | 0 .../img/BASIC_IE_API_workflow_Cpp.svg | 0 .../img/BASIC_IE_API_workflow_Python.svg | 0 .../img/DEVELOPMENT_FLOW_V3_crunch.svg | 0 .../img/IMPLEMENT_PIPELINE_with_API_C.svg | 0 .../IMPLEMENT_PIPELINE_with_API_Python.svg | 0 .../img/LATENCY_VS_THROUGHPUT.svg | 0 .../img/Latency_Throughput.png | 0 .../img/NewAndOldCNNNetworkImpl.png | 0 .../img/TopLevelNGraphFlow.png | 0 .../img/WHAT_TO_USE.svg | 0 .../img/applying_low_latency.png | 0 .../img/applying_low_latency_2.png | 0 .../img/bf16_format.png | 0 .../img/conv_depth_01.png | 0 .../img/conv_simple_01.png | 0 .../img/conv_sum_relu_01.png | 0 .../img/cpu_int8_flow.png | 0 .../img/cpu_streams_explained.png | 0 .../img/deploy_encrypted_model.png | 0 .../img/deploy_encrypted_model.vsdx | 0 .../img/development_deployment.png | 0 .../img/diagram_workflow.svg | 0 .../img/example_sample_output.png | 0 .../img/fpga_full_workflow.png | 0 .../img/fpga_platform_hub.png | 0 .../img/fullyconnected_activation_01.png | 0 .../img/graph_rewrite_efficient_search.png | 0 .../img/graph_rewrite_execution.png | 0 .../img/group_convolutions_01.png | 0 .../img/hor_fusion_1.png | 0 .../img/hor_fusion_2.png | 0 .../img/hor_fusion_3.png | 0 .../img/hor_fusion_4.png | 0 .../img/ie_api_cpp.png | 0 .../img/ie_api_integration_cpp.png | 0 .../img/ie_api_integration_python.png | 0 .../img/ie_api_python.png | 0 .../img/ie_workflow_steps.png | 0 .../img/intel_logo.png | 0 .../img/ir_add_n_ref.png | 0 .../img/latency_throughput_1.png | 0 .../img/llt2_use_const_initializer.png | 0 .../img/low_latency_limitation_1.png | 0 .../img/low_latency_limitation_2.png | 0 .../img/mkldnn_conv_sum.png | 0 .../img/mkldnn_conv_sum_result.png | 0 .../img/mkldnn_group_conv.png | 0 .../img/ngraph_insert_node.png | 0 .../img/ngraph_replace_node.png | 0 .../img/opt-notice-en_080411.gif | 0 .../img/optimizations/groups.png | 0 .../img/optimizations/inception_v4.png | 0 .../img/optimizations/resnet_269.png | 0 .../img/optimizations/resnet_optimization.png | 0 .../img/output_trimmed.png | 0 .../img/pooling_fakequant_01.png | 0 .../img/register_new_node.png | 0 .../img/resnet_269.png | 0 .../img/state_network_example.png | 0 .../img/transformations_structure.png | 0 .../img/vtune_async.png | 0 .../img/vtune_option.png | 0 .../img/vtune_regular.png | 0 .../img/vtune_timeline.png | 0 .../img/vtune_topdown_view.jpg | 0 .../img/yolo_tiny_v1.png | 0 docs/OV_Runtime_UG/model_representation.md | 91 +++++++ .../nGraphTransformation.md | 6 +- .../network_state_intro.md | 6 +- .../protecting_model_guide.md | 0 .../supported_plugins/AUTO.md | 0 .../supported_plugins/CPU.md | 0 .../supported_plugins/Device_Plugins.md | 0 .../supported_plugins/GNA.md | 0 .../supported_plugins/GPU.md | 0 .../supported_plugins/GPU_RemoteBlob_API.md | 0 .../supported_plugins/HDDL.md | 0 .../supported_plugins/HETERO.md | 0 .../supported_plugins/MULTI.md | 0 .../supported_plugins/MYRIAD.md | 0 .../supported_plugins/Supported_Devices.md | 0 .../supported_plugins/VPU.md | 0 docs/api/api_reference.rst | 2 - docs/benchmarks/performance_benchmarks_faq.md | 2 +- docs/documentation.md | 5 +- docs/get_started/get_started_demos.md | 4 +- .../install_guides/installing-openvino-apt.md | 10 +- .../installing-openvino-conda.md | 6 +- .../installing-openvino-linux.md | 6 +- .../installing-openvino-macos.md | 8 +- .../install_guides/installing-openvino-pip.md | 4 +- .../installing-openvino-raspbian.md | 4 +- .../installing-openvino-windows.md | 6 +- .../install_guides/installing-openvino-yum.md | 6 +- docs/model_server/README.md | 4 +- docs/nGraph_DG/build_function.md | 36 --- docs/nGraph_DG/intro.md | 46 ---- docs/nGraph_DG/nGraph_Python_API.md | 222 ------------------ docs/nGraph_DG/nGraph_basic_concepts.md | 39 --- docs/nGraph_DG/nGraph_debug_capabilities.md | 18 -- docs/nGraph_DG/nGraph_dg.md | 16 -- docs/ops/opset8.md | 2 +- .../dldt_deployment_optimization_guide.md | 36 +-- ...eployment_optimization_guide_additional.md | 6 +- docs/resources.md | 4 +- docs/snippets/example_ngraph_utils.cpp | 187 ++++++++------- samples/c/hello_classification/README.md | 10 +- .../hello_nv12_input_classification/README.md | 8 +- samples/cpp/benchmark_app/README.md | 4 +- .../cpp/classification_sample_async/README.md | 10 +- samples/cpp/hello_classification/README.md | 10 +- .../hello_nv12_input_classification/README.md | 12 +- samples/cpp/hello_query_device/README.md | 10 +- samples/cpp/hello_reshape_ssd/README.md | 12 +- .../ngraph_function_creation_sample/README.md | 14 +- samples/cpp/speech_sample/README.md | 10 +- .../classification_sample_async/README.md | 8 +- samples/python/hello_classification/README.md | 8 +- samples/python/hello_query_device/README.md | 6 +- samples/python/hello_reshape_ssd/README.md | 10 +- .../ngraph_function_creation_sample/README.md | 12 +- samples/python/speech_sample/README.md | 8 +- tools/benchmark_tool/README.md | 2 +- .../openvino/tools/benchmark/README.md | 4 +- 170 files changed, 395 insertions(+), 671 deletions(-) rename docs/{IE_DG => OV_Runtime_UG}/API_Changes.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Bfloat16Inference.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Deep_Learning_Inference_Engine_DevGuide.md (86%) rename docs/{IE_DG => OV_Runtime_UG}/DynamicBatching.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/AddingNGraphOps.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/Building.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/CPU_Kernel.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/Custom_ONNX_Ops.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/Extension.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/GPU_Kernel.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/Intro.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Extensibility_DG/VPU_Kernel.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Glossary.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/InferenceEngine_QueryAPI.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Int8Inference.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Integrate_with_customer_application_new_API.md (97%) rename docs/{IE_DG => OV_Runtime_UG}/Known_Issues_Limitations.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Memory_primitives.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Model_caching_overview.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/ONNX_Support.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Operations_specifications.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Paddle_Support.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/PythonPackage_Overview.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/Samples_Overview.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/ShapeInference.md (97%) rename docs/{IE_DG => OV_Runtime_UG}/img/BASIC_FLOW_IE_C.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/BASIC_FLOW_MO.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/BASIC_FLOW_MO_simplified.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/BASIC_IE_API_workflow_Cpp.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/BASIC_IE_API_workflow_Python.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/DEVELOPMENT_FLOW_V3_crunch.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/IMPLEMENT_PIPELINE_with_API_C.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/IMPLEMENT_PIPELINE_with_API_Python.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/LATENCY_VS_THROUGHPUT.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/Latency_Throughput.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/NewAndOldCNNNetworkImpl.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/TopLevelNGraphFlow.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/WHAT_TO_USE.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/applying_low_latency.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/applying_low_latency_2.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/bf16_format.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/conv_depth_01.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/conv_simple_01.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/conv_sum_relu_01.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/cpu_int8_flow.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/cpu_streams_explained.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/deploy_encrypted_model.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/deploy_encrypted_model.vsdx (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/development_deployment.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/diagram_workflow.svg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/example_sample_output.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/fpga_full_workflow.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/fpga_platform_hub.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/fullyconnected_activation_01.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/graph_rewrite_efficient_search.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/graph_rewrite_execution.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/group_convolutions_01.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/hor_fusion_1.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/hor_fusion_2.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/hor_fusion_3.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/hor_fusion_4.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/ie_api_cpp.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/ie_api_integration_cpp.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/ie_api_integration_python.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/ie_api_python.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/ie_workflow_steps.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/intel_logo.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/ir_add_n_ref.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/latency_throughput_1.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/llt2_use_const_initializer.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/low_latency_limitation_1.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/low_latency_limitation_2.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/mkldnn_conv_sum.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/mkldnn_conv_sum_result.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/mkldnn_group_conv.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/ngraph_insert_node.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/ngraph_replace_node.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/opt-notice-en_080411.gif (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/optimizations/groups.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/optimizations/inception_v4.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/optimizations/resnet_269.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/optimizations/resnet_optimization.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/output_trimmed.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/pooling_fakequant_01.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/register_new_node.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/resnet_269.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/state_network_example.png (100%) rename docs/{nGraph_DG => OV_Runtime_UG}/img/transformations_structure.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/vtune_async.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/vtune_option.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/vtune_regular.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/vtune_timeline.png (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/vtune_topdown_view.jpg (100%) rename docs/{IE_DG => OV_Runtime_UG}/img/yolo_tiny_v1.png (100%) create mode 100644 docs/OV_Runtime_UG/model_representation.md rename docs/{nGraph_DG => OV_Runtime_UG}/nGraphTransformation.md (99%) rename docs/{IE_DG => OV_Runtime_UG}/network_state_intro.md (98%) rename docs/{IE_DG => OV_Runtime_UG}/protecting_model_guide.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/AUTO.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/CPU.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/Device_Plugins.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/GNA.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/GPU.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/GPU_RemoteBlob_API.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/HDDL.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/HETERO.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/MULTI.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/MYRIAD.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/Supported_Devices.md (100%) rename docs/{IE_DG => OV_Runtime_UG}/supported_plugins/VPU.md (100%) delete mode 100644 docs/nGraph_DG/build_function.md delete mode 100644 docs/nGraph_DG/intro.md delete mode 100644 docs/nGraph_DG/nGraph_Python_API.md delete mode 100644 docs/nGraph_DG/nGraph_basic_concepts.md delete mode 100644 docs/nGraph_DG/nGraph_debug_capabilities.md delete mode 100644 docs/nGraph_DG/nGraph_dg.md diff --git a/README.md b/README.md index 62c68a83a9a..71ffc42adcf 100644 --- a/README.md +++ b/README.md @@ -44,8 +44,7 @@ Please report questions, issues and suggestions using: \* Other names and brands may be claimed as the property of others. [Open Model Zoo]:https://github.com/openvinotoolkit/open_model_zoo -[Inference Engine]:https://software.intel.com/en-us/articles/OpenVINO-InferEngine -[Model Optimizer]:https://software.intel.com/en-us/articles/OpenVINO-ModelOptimizer -[nGraph]:https://docs.openvino.ai/latest/openvino_docs_nGraph_DG_DevGuide.html +[OpenVINO Runtime™]:https://docs.openvino.ai/latest/openvino_docs_IE_DG_Deep_Learning_Inference_Engine_DevGuide.html +[Model Optimizer]:https://docs.openvino.ai/latest/openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide.html [tag on StackOverflow]:https://stackoverflow.com/search?q=%23openvino diff --git a/docs/HOWTO/Custom_Layers_Guide.md b/docs/HOWTO/Custom_Layers_Guide.md index 84a193c1a1f..0069acb737d 100644 --- a/docs/HOWTO/Custom_Layers_Guide.md +++ b/docs/HOWTO/Custom_Layers_Guide.md @@ -31,15 +31,15 @@ There are three steps to support inference of a model with custom operation(s): 1. Add support for a custom operation in the [Model Optimizer](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) so the Model Optimizer can generate the IR with the operation. 2. Create an operation set and implement a custom nGraph operation in it as described in the -[Custom nGraph Operation](../IE_DG/Extensibility_DG/AddingNGraphOps.md). -3. Implement a customer operation in one of the [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) +[Custom nGraph Operation](../OV_Runtime_UG/Extensibility_DG/AddingNGraphOps.md). +3. Implement a customer operation in one of the [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) plugins to support inference of this operation using a particular target hardware (CPU, GPU or VPU). To see the operations that are supported by each device plugin for the Inference Engine, refer to the -[Supported Devices](../IE_DG/supported_plugins/Supported_Devices.md). +[Supported Devices](../OV_Runtime_UG/supported_plugins/Supported_Devices.md). > **NOTE**: If a device doesn't support a particular operation, an alternative to creating a new operation is to target -> an additional device using the HETERO plugin. The [Heterogeneous Plugin](../IE_DG/supported_plugins/HETERO.md) may be +> an additional device using the HETERO plugin. The [Heterogeneous Plugin](../OV_Runtime_UG/supported_plugins/HETERO.md) may be > used to run an inference model on multiple devices allowing the unsupported operations on one device to "fallback" to > run on another device (e.g., CPU) that does support those operations. @@ -61,20 +61,20 @@ operation. Refer to the "Operation Extractor" section of ## Custom Operations Extensions for the Inference Engine -Inference Engine provides an extension mechanism to support new operations. This mechanism is described in [Inference Engine Extensibility Mechanism](../IE_DG/Extensibility_DG/Intro.md). +Inference Engine provides an extension mechanism to support new operations. This mechanism is described in [Inference Engine Extensibility Mechanism](../OV_Runtime_UG/Extensibility_DG/Intro.md). Each device plugin includes a library of optimized implementations to execute known operations which must be extended to execute a custom operation. The custom operation extension is implemented according to the target device: - Custom Operation CPU Extension - A compiled shared library (`.so` or `.dll`) needed by the CPU Plugin for executing the custom operation - on a CPU. Refer to the [How to Implement Custom CPU Operations](../IE_DG/Extensibility_DG/CPU_Kernel.md) for more + on a CPU. Refer to the [How to Implement Custom CPU Operations](../OV_Runtime_UG/Extensibility_DG/CPU_Kernel.md) for more details. - Custom Operation GPU Extension - - OpenCL source code (.cl) for the custom operation kernel that will be compiled to execute on the GPU along with an operation description file (.xml) needed by the GPU Plugin for the custom operation kernel. Refer to the [How to Implement Custom GPU Operations](../IE_DG/Extensibility_DG/GPU_Kernel.md) for more details. + - OpenCL source code (.cl) for the custom operation kernel that will be compiled to execute on the GPU along with an operation description file (.xml) needed by the GPU Plugin for the custom operation kernel. Refer to the [How to Implement Custom GPU Operations](../OV_Runtime_UG/Extensibility_DG/GPU_Kernel.md) for more details. - Custom Operation VPU Extension - - OpenCL source code (.cl) for the custom operation kernel that will be compiled to execute on the VPU along with an operation description file (.xml) needed by the VPU Plugin for the custom operation kernel. Refer to [How to Implement Custom Operations for VPU](../IE_DG/Extensibility_DG/VPU_Kernel.md) for more details. + - OpenCL source code (.cl) for the custom operation kernel that will be compiled to execute on the VPU along with an operation description file (.xml) needed by the VPU Plugin for the custom operation kernel. Refer to [How to Implement Custom Operations for VPU](../OV_Runtime_UG/Extensibility_DG/VPU_Kernel.md) for more details. -Also, it is necessary to implement nGraph custom operation according to [Custom nGraph Operation](../IE_DG/Extensibility_DG/AddingNGraphOps.md) so the Inference Engine can read an IR with this +Also, it is necessary to implement nGraph custom operation according to [Custom nGraph Operation](../OV_Runtime_UG/Extensibility_DG/AddingNGraphOps.md) so the Inference Engine can read an IR with this operation and correctly infer output tensor shape and type. ## Enabling Magnetic Resonance Image Reconstruction Model @@ -125,7 +125,7 @@ Firstly, open the model in TensorBoard or other TensorFlow* model visualization batch dimension because the value for the batch dimension is not hardcoded in the model. Model Optimizer need to set all dynamic dimensions to some specific value to create the IR, therefore specify the command line parameter `-b 1` to set the batch dimension equal to 1. The actual batch size dimension can be changed at runtime using the Inference Engine API -described in the [Using Shape Inference](../IE_DG/ShapeInference.md). Also refer to the General Conversion Parameters section in [Converting a Model to Intermediate Representation (IR)](../MO_DG/prepare_model/convert_model/Converting_Model.md) and [Convert Your TensorFlow* Model](../MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md) +described in the [Using Shape Inference](../OV_Runtime_UG/ShapeInference.md). Also refer to the General Conversion Parameters section in [Converting a Model to Intermediate Representation (IR)](../MO_DG/prepare_model/convert_model/Converting_Model.md) and [Convert Your TensorFlow* Model](../MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md) for more details and command line parameters used for the model conversion. ```sh @@ -263,7 +263,7 @@ The sub-graph corresponding to the originally non-supported one is depicted in t ### Inference Engine Extension Implementation Now it is necessary to implement the extension for the CPU plugin with operation "FFT" introduced previously. The code -below is based on the template extension described in [Inference Engine Extensibility Mechanism](../IE_DG/Extensibility_DG/Intro.md). +below is based on the template extension described in [Inference Engine Extensibility Mechanism](../OV_Runtime_UG/Extensibility_DG/Intro.md). #### CMake Build File The first step is to create a CMake configuration file which builds the extension. The content of the "CMakeLists.txt" @@ -284,7 +284,7 @@ in the `fft_op.cpp` file with the following content: @snippet template_extension/old/fft_op.cpp fft_op:implementation -Refer to the [Custom nGraph Operation](../IE_DG/Extensibility_DG/AddingNGraphOps.md) for more details. +Refer to the [Custom nGraph Operation](../OV_Runtime_UG/Extensibility_DG/AddingNGraphOps.md) for more details. #### CPU FFT Kernel Implementation The operation implementation for CPU plugin uses OpenCV to perform the FFT. The header file "fft_kernel.hpp" has the @@ -296,11 +296,11 @@ The "fft_kernel.cpp" with the implementation of the CPU has the following conten @snippet template_extension/old/fft_kernel.cpp fft_kernel:implementation -Refer to the [How to Implement Custom CPU Operations](../IE_DG/Extensibility_DG/CPU_Kernel.md) for more details. +Refer to the [How to Implement Custom CPU Operations](../OV_Runtime_UG/Extensibility_DG/CPU_Kernel.md) for more details. #### Extension Library Implementation The last step is to create an extension library "extension.cpp" and "extension.hpp" which will include the FFT -operation for the CPU plugin. The code of the library is described in the [Extension Library](../IE_DG/Extensibility_DG/Extension.md). +operation for the CPU plugin. The code of the library is described in the [Extension Library](../OV_Runtime_UG/Extensibility_DG/Extension.md). ### Building and Running the Custom Extension To build the extension, run the following:
@@ -335,8 +335,8 @@ python3 mri_reconstruction_demo.py \ - OpenVINO™ toolkit online documentation: [https://docs.openvino.ai](https://docs.openvino.ai) - [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) - [Model Optimizer Extensibility](../MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md) -- [Inference Engine Extensibility Mechanism](../IE_DG/Extensibility_DG/Intro.md) -- [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md) +- [Inference Engine Extensibility Mechanism](../OV_Runtime_UG/Extensibility_DG/Intro.md) +- [OpenVINO™ Toolkit Samples Overview](../OV_Runtime_UG/Samples_Overview.md) - [Overview of OpenVINO™ Toolkit Pre-Trained Models](@ref omz_models_group_intel) - For IoT Libraries and Code Samples see the [Intel® IoT Developer Kit](https://github.com/intel-iot-devkit). diff --git a/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md b/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md index 6e5136441ef..8778401c446 100644 --- a/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md +++ b/docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md @@ -6,6 +6,7 @@ :maxdepth: 1 :hidden: + openvino_docs_MO_DG_IR_and_opsets openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model openvino_docs_MO_DG_Additional_Optimization_Use_Cases openvino_docs_MO_DG_prepare_model_customize_model_optimizer_Customize_Model_Optimizer @@ -19,7 +20,7 @@ Model Optimizer is a cross-platform command-line tool that facilitates the transition between the training and deployment environment, performs static model analysis, and adjusts deep learning models for optimal execution on end-point target devices. -Model Optimizer process assumes you have a network model trained using supported deep learning frameworks: Caffe*, TensorFlow*, Kaldi*, MXNet* or converted to the ONNX* format. Model Optimizer produces an Intermediate Representation (IR) of the network, which can be inferred with the [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md). +Model Optimizer process assumes you have a network model trained using supported deep learning frameworks: Caffe*, TensorFlow*, Kaldi*, MXNet* or converted to the ONNX* format. Model Optimizer produces an Intermediate Representation (IR) of the network, which can be inferred with the [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md). > **NOTE**: Model Optimizer does not infer models. Model Optimizer is an offline tool that runs before the inference takes place. diff --git a/docs/MO_DG/prepare_model/Additional_Optimizations.md b/docs/MO_DG/prepare_model/Additional_Optimizations.md index 517b4bdf0a2..4a927563b6c 100644 --- a/docs/MO_DG/prepare_model/Additional_Optimizations.md +++ b/docs/MO_DG/prepare_model/Additional_Optimizations.md @@ -9,7 +9,7 @@ Model Optimizer performs preprocessing to a model. It is possible to optimize th If, for example, your network assumes the RGB inputs, the Model Optimizer can swap the channels in the first convolution using the `--reverse_input_channels` command line option, so you do not need to convert your inputs to RGB every time you get the BGR image, for example, from OpenCV*. - **Larger batch size**
- Notice that the devices like GPU are doing better with larger batch size. While it is possible to set the batch size in the runtime using the Inference Engine [ShapeInference feature](../../IE_DG/ShapeInference.md). + Notice that the devices like GPU are doing better with larger batch size. While it is possible to set the batch size in the runtime using the Inference Engine [ShapeInference feature](../../OV_Runtime_UG/ShapeInference.md). - **Resulting IR precision**
The resulting IR precision, for instance, `FP16` or `FP32`, directly affects performance. As CPU now supports `FP16` (while internally upscaling to `FP32` anyway) and because this is the best precision for a GPU target, you may want to always convert models to `FP16`. Notice that this is the only precision that Intel® Movidius™ Myriad™ 2 and Intel® Myriad™ X VPUs support. diff --git a/docs/MO_DG/prepare_model/Getting_performance_numbers.md b/docs/MO_DG/prepare_model/Getting_performance_numbers.md index 6fc7e9b5e81..1d11be89064 100644 --- a/docs/MO_DG/prepare_model/Getting_performance_numbers.md +++ b/docs/MO_DG/prepare_model/Getting_performance_numbers.md @@ -18,7 +18,7 @@ You need to build your performance conclusions on reproducible data. Do the perf - If the warm-up run does not help or execution time still varies, you can try running a large number of iterations and then average or find a mean of the results. - For time values that range too much, use geomean. -Refer to the [Inference Engine Samples](../../IE_DG/Samples_Overview.md) for code examples for the performance measurements. Almost every sample, except interactive demos, has a `-ni` option to specify the number of iterations. +Refer to the [Inference Engine Samples](../../OV_Runtime_UG/Samples_Overview.md) for code examples for the performance measurements. Almost every sample, except interactive demos, has a `-ni` option to specify the number of iterations. ## Getting performance numbers using OpenVINO tool @@ -39,7 +39,7 @@ to execute on the CPU instead. For example, for the CPU throughput mode from the previous section, you can play with number of streams (`-nstreams` command-line param). Try different values of the `-nstreams` argument from `1` to a number of CPU cores and find one that provides the best performance. For example, on a 8-core CPU, compare the `-nstreams 1` (which is a latency-oriented scenario) to the `2`, `4` and `8` streams. Notice that `benchmark_app` automatically queries/creates/runs number of requests required to saturate the given number of streams. -Finally, notice that when you don't specify number of streams with `-nstreams`, "AUTO" value for the streams is used, e.g. for the CPU this is [CPU_THROUGHPUT_AUTO](../../IE_DG/supported_plugins/CPU.md). You can spot the actual value behind "AUTO" for your machine in the application output. +Finally, notice that when you don't specify number of streams with `-nstreams`, "AUTO" value for the streams is used, e.g. for the CPU this is [CPU_THROUGHPUT_AUTO](../../OV_Runtime_UG/supported_plugins/CPU.md). You can spot the actual value behind "AUTO" for your machine in the application output. Notice that the "AUTO" number is not necessarily most optimal, so it is generally recommended to play either with the benchmark_app's "-nstreams" as described above, or via [new Workbench tool](@ref workbench_docs_Workbench_DG_Introduction).This allows you to simplify the app-logic, as you don't need to combine multiple inputs into a batch to achieve good CPU performance. Instead, it is possible to keep a separate infer request per camera or another source of input and process the requests in parallel using Async API. @@ -47,7 +47,7 @@ Instead, it is possible to keep a separate infer request per camera or another s When comparing the Inference Engine performance with the framework or another reference code, make sure that both versions are as similar as possible: -- Wrap exactly the inference execution (refer to the [Inference Engine Samples](../../IE_DG/Samples_Overview.md) for examples). +- Wrap exactly the inference execution (refer to the [Inference Engine Samples](../../OV_Runtime_UG/Samples_Overview.md) for examples). - Do not include model loading time. - Ensure the inputs are identical for the Inference Engine and the framework. For example, Caffe\* allows to auto-populate the input with random values. Notice that it might give different performance than on real images. - Similarly, for correct performance comparison, make sure the access pattern, for example, input layouts, is optimal for Inference Engine (currently, it is NCHW). @@ -64,7 +64,7 @@ Alternatively, you can gather the raw profiling data that samples report, the se ### Internal Inference Performance Counters -Almost every sample (inspect command-line options for a specific sample with `-h`) supports a `-pc` command that outputs internal execution breakdown. Refer to the [samples code](../../IE_DG/Samples_Overview.md) for the actual Inference Engine API behind that. +Almost every sample (inspect command-line options for a specific sample with `-h`) supports a `-pc` command that outputs internal execution breakdown. Refer to the [samples code](../../OV_Runtime_UG/Samples_Overview.md) for the actual Inference Engine API behind that. Below is example of CPU plugin output for a network (since the device is CPU, the layers wall clock `realTime` and the `cpu` time are the same): diff --git a/docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md b/docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md index 22ca4670f3d..91106d0ee86 100644 --- a/docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md +++ b/docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md @@ -214,7 +214,7 @@ One of the layers in the specified topology might not have inputs or values. Ple #### 24. What does the message "Part of the nodes was not translated to IE. Stopped" mean? -Some of the layers are not supported by the Inference Engine and cannot be translated to an Intermediate Representation. You can extend the Model Optimizer by allowing generation of new types of layers and implement these layers in the dedicated Inference Engine plugins. For more information, refer to the [Custom Layers Guide](../../HOWTO/Custom_Layers_Guide.md) and [Inference Engine Extensibility Mechanism](../../IE_DG/Extensibility_DG/Intro.md) +Some of the layers are not supported by the Inference Engine and cannot be translated to an Intermediate Representation. You can extend the Model Optimizer by allowing generation of new types of layers and implement these layers in the dedicated Inference Engine plugins. For more information, refer to the [Custom Layers Guide](../../HOWTO/Custom_Layers_Guide.md) and [Inference Engine Extensibility Mechanism](../../OV_Runtime_UG/Extensibility_DG/Intro.md) #### 25. What does the message "While creating an edge from .. to .. : node name is undefined in the graph. Check correctness of the input model" mean? @@ -638,4 +638,4 @@ Starting from the 2022.1 version, the default IR conversion path for ONNX models Certain features, such as `--extensions` and `--transformations_config`, are not yet fully supported on the new frontends. For `--extensions`, the new frontends support only paths to shared libraries (.dll and .so). For `--transformations_config`, they support JSON configurations with defined library fields. Inputs freezing (enabled by `--freeze_placeholder_with_value` or `--input` arguments) is not supported on the new frontends. -The IR conversion falls back to the old path if a user does not select any expected path of conversion explicitly (by `--use_new_frontend` or `--use_legacy_frontend` MO arguments) and unsupported pre-defined scenario is detected on the new frontend path. \ No newline at end of file +The IR conversion falls back to the old path if a user does not select any expected path of conversion explicitly (by `--use_new_frontend` or `--use_legacy_frontend` MO arguments) and unsupported pre-defined scenario is detected on the new frontend path. diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md index d1d123ba30a..26f815b5937 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Caffe.md @@ -4,8 +4,8 @@ A summary of the steps for optimizing and deploying a model that was trained wit 1. [Configure the Model Optimizer](../../Deep_Learning_Model_Optimizer_DevGuide.md) for Caffe\*. 2. [Convert a Caffe\* Model](#Convert_From_Caffe) to produce an optimized [Intermediate Representation (IR)](../../IR_and_opsets.md) of the model based on the trained network topology, weights, and biases values -3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../IE_DG/Samples_Overview.md) -4. [Integrate](../../../IE_DG/Samples_Overview.md) the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment +3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../OV_Runtime_UG/Samples_Overview.md) +4. [Integrate](../../../OV_Runtime_UG/Samples_Overview.md) the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment ## Supported Topologies diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md index 08d3be6f389..28101c02f96 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md @@ -14,8 +14,8 @@ A summary of the steps for optimizing and deploying a model that was trained wit 1. [Configure the Model Optimizer](../../Deep_Learning_Model_Optimizer_DevGuide.md) for Kaldi\*. 2. [Convert a Kaldi\* Model](#Convert_From_Kaldi) to produce an optimized [Intermediate Representation (IR)](../../IR_and_opsets.md) of the model based on the trained network topology, weights, and biases values. -3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../IE_DG/Samples_Overview.md). -4. [Integrate](../../../IE_DG/Samples_Overview.md) the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment. +3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../OV_Runtime_UG/Samples_Overview.md). +4. [Integrate](../../../OV_Runtime_UG/Samples_Overview.md) the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment. > **NOTE**: The Model Optimizer supports the [nnet1](http://kaldi-asr.org/doc/dnn1.html) and [nnet2](http://kaldi-asr.org/doc/dnn2.html) formats of Kaldi models. Support of the [nnet3](http://kaldi-asr.org/doc/dnn3.html) format is limited. diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md index 35453e67373..3af3c126a82 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_MxNet.md @@ -15,8 +15,8 @@ A summary of the steps for optimizing and deploying a model that was trained wit 1. [Configure the Model Optimizer](../../Deep_Learning_Model_Optimizer_DevGuide.md) for MXNet* (MXNet was used to train your model) 2. [Convert a MXNet model](#ConvertMxNet) to produce an optimized [Intermediate Representation (IR)](../../IR_and_opsets.md) of the model based on the trained network topology, weights, and biases values -3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../IE_DG/Samples_Overview.md) -4. [Integrate](../../../IE_DG/Samples_Overview.md) the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment +3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../OV_Runtime_UG/Samples_Overview.md) +4. [Integrate](../../../OV_Runtime_UG/Samples_Overview.md) the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment ## Supported Topologies diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md index 16378b32331..1ba7be84631 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Paddle.md @@ -4,8 +4,8 @@ A summary of the steps for optimizing and deploying a model trained with Paddle\ 1. [Configure the Model Optimizer](../../Deep_Learning_Model_Optimizer_DevGuide.md) for Paddle\*. 2. [Convert a Paddle\* Model](#Convert_From_Paddle) to produce an optimized [Intermediate Representation (IR)](../../IR_and_opsets.md) of the model based on the trained network topology, weights, and biases. -3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../IE_DG/Samples_Overview.md). -4. [Integrate](../../../IE_DG/Samples_Overview.md) the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment. +3. Test the model in the Intermediate Representation format using the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided Inference Engine [sample applications](../../../OV_Runtime_UG/Samples_Overview.md). +4. [Integrate](../../../OV_Runtime_UG/Samples_Overview.md) the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in your application to deploy the model in the target environment. ## Supported Topologies diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md index 19a03d7dca8..f6de3b1355f 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md @@ -48,8 +48,8 @@ PyTorch* framework is supported through export to ONNX\* format. A summary of th 1. [Configure the Model Optimizer](../../Deep_Learning_Model_Optimizer_DevGuide.md) for ONNX\*. 2. [Export PyTorch model to ONNX\*](#export-to-onnx). 3. [Convert an ONNX\* model](Convert_Model_From_ONNX.md) to produce an optimized [Intermediate Representation (IR)](../../IR_and_opsets.md) of the model based on the trained network topology, weights, and biases values. -4. Test the model in the Intermediate Representation format using the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided [sample applications](../../../IE_DG/Samples_Overview.md). -5. [Integrate](../../../IE_DG/Samples_Overview.md) the Inference Engine in your application to deploy the model in the target environment. +4. Test the model in the Intermediate Representation format using the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided [sample applications](../../../OV_Runtime_UG/Samples_Overview.md). +5. [Integrate](../../../OV_Runtime_UG/Samples_Overview.md) the Inference Engine in your application to deploy the model in the target environment. ## Export PyTorch\* Model to ONNX\* Format diff --git a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md index 0ecc0b8900f..c129f10d8ac 100644 --- a/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md +++ b/docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow.md @@ -29,8 +29,8 @@ A summary of the steps for optimizing and deploying a model that was trained wit 1. [Configure the Model Optimizer](../../Deep_Learning_Model_Optimizer_DevGuide.md) for TensorFlow\* (TensorFlow was used to train your model). 2. [Freeze the TensorFlow model](#freeze-the-tensorflow-model) if your model is not already frozen or skip this step and use the [instruction](#loading-nonfrozen-models) to a convert a non-frozen model. 3. [Convert a TensorFlow\* model](#Convert_From_TF) to produce an optimized [Intermediate Representation (IR)](../../IR_and_opsets.md) of the model based on the trained network topology, weights, and biases values. -4. Test the model in the Intermediate Representation format using the [Inference Engine](../../../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided [sample applications](../../../IE_DG/Samples_Overview.md). -5. [Integrate](../../../IE_DG/Samples_Overview.md) the Inference Engine in your application to deploy the model in the target environment. +4. Test the model in the Intermediate Representation format using the [Inference Engine](../../../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) in the target environment via provided [sample applications](../../../OV_Runtime_UG/Samples_Overview.md). +5. [Integrate](../../../OV_Runtime_UG/Samples_Overview.md) the Inference Engine in your application to deploy the model in the target environment. ## Supported Topologies diff --git a/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md b/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md index bf117d90d69..34df1408cdb 100644 --- a/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md +++ b/docs/MO_DG/prepare_model/convert_model/IR_suitable_for_INT8_inference.md @@ -3,7 +3,7 @@ ## Introduction Inference Engine CPU and GPU plugin can infer models in the low precision. -For details, refer to [Low Precision Inference on the CPU](../../../IE_DG/Int8Inference.md). +For details, refer to [Low Precision Inference on the CPU](../../../OV_Runtime_UG/Int8Inference.md). Intermediate Representation (IR) should be specifically formed to be suitable for low precision inference. Such an IR is called a Low Precision IR and you can generate it in two ways: diff --git a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md index b3eafbaea77..ecaf315295a 100644 --- a/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md +++ b/docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_RNNT.md @@ -104,5 +104,5 @@ mo --input_model rnnt_prediction.onnx --input "symbol[1 1],hidden_in_1[2 1 320], mo --input_model rnnt_joint.onnx --input "0[1 1 1024],1[1 1 320]" ``` Please note that hardcoded value for sequence length = 157 was taken from the MLCommons but conversion to IR preserves -network [reshapeability](../../../../IE_DG/ShapeInference.md), this means you can change input shapes manually to any value either during conversion or +network [reshapeability](../../../../OV_Runtime_UG/ShapeInference.md), this means you can change input shapes manually to any value either during conversion or inference. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md index ebef0028dc5..6af7bef609e 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_BERT_From_Tensorflow.md @@ -116,4 +116,4 @@ Run the Model Optimizer with the following command line parameters to generate r ``` For other applicable parameters, refer to [Convert Model from TensorFlow](../Convert_Model_From_TensorFlow.md). -For more information about reshape abilities, refer to [Using Shape Inference](../../../../IE_DG/ShapeInference.md). +For more information about reshape abilities, refer to [Using Shape Inference](../../../../OV_Runtime_UG/ShapeInference.md). diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md index 77bac6149ac..ad0ffbbb9fd 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_DeepSpeech_From_Tensorflow.md @@ -47,7 +47,7 @@ There are two specificities with the supported part of the model. The first is that the model contains an input with sequence length. So the model can be converted with a fixed input length shape, thus the model is not reshapeable. -Refer to the [Using Shape Inference](../../../../IE_DG/ShapeInference.md). +Refer to the [Using Shape Inference](../../../../OV_Runtime_UG/ShapeInference.md). The second is that the frozen model still has two variables: `previous_state_c` and `previous_state_h`, figure with the frozen *.pb model is below. It means that the model keeps training these variables at each inference. diff --git a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md index 458e884c612..56324c1facb 100644 --- a/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md +++ b/docs/MO_DG/prepare_model/convert_model/tf_specific/Convert_Object_Detection_API_Models.md @@ -2,7 +2,7 @@ > **NOTES**: > * Starting with the 2022.1 release, the Model Optimizer can convert the TensorFlow\* Object Detection API Faster and Mask RCNNs topologies differently. By default, the Model Optimizer adds operation "Proposal" to the generated IR. This operation needs an additional input to the model with name "image_info" which should be fed with several values describing the pre-processing applied to the input image (refer to the [Proposal](../../../../ops/detection/Proposal_4.md) operation specification for more information). However, this input is redundant for the models trained and inferred with equal size images. Model Optimizer can generate IR for such models and insert operation [DetectionOutput](../../../../ops/detection/DetectionOutput_1.md) instead of `Proposal`. The `DetectionOutput` operation does not require additional model input "image_info" and moreover, for some models the produced inference results are closer to the original TensorFlow\* model. In order to trigger new behaviour the attribute "operation_to_add" in the corresponding JSON transformation configuration file should be set to value "DetectionOutput" instead of default one "Proposal". -> * Starting with the 2021.1 release, the Model Optimizer converts the TensorFlow\* Object Detection API SSDs, Faster and Mask RCNNs topologies keeping shape-calculating sub-graphs by default, so topologies can be re-shaped in the Inference Engine using dedicated reshape API. Refer to [Using Shape Inference](../../../../IE_DG/ShapeInference.md) for more information on how to use this feature. It is possible to change the both spatial dimensions of the input image and batch size. +> * Starting with the 2021.1 release, the Model Optimizer converts the TensorFlow\* Object Detection API SSDs, Faster and Mask RCNNs topologies keeping shape-calculating sub-graphs by default, so topologies can be re-shaped in the Inference Engine using dedicated reshape API. Refer to [Using Shape Inference](../../../../OV_Runtime_UG/ShapeInference.md) for more information on how to use this feature. It is possible to change the both spatial dimensions of the input image and batch size. > * To generate IRs for TF 1 SSD topologies, the Model Optimizer creates a number of `PriorBoxClustered` operations instead of a constant node with prior boxes calculated for the particular input image size. This change allows you to reshape the topology in the Inference Engine using dedicated Inference Engine API. The reshaping is supported for all SSD topologies except FPNs which contain hardcoded shapes for some operations preventing from changing topology input shape. ## How to Convert a Model @@ -63,7 +63,7 @@ based on deep learning in various tasks, including Image Classifiacton, Visual O Speech Recognition, Natural Language Processing and others. Refer to the links below for more details. -* [Inference Engine Samples](../../../../IE_DG/Samples_Overview.md) +* [Inference Engine Samples](../../../../OV_Runtime_UG/Samples_Overview.md) * [Open Model Zoo Demos](@ref omz_demos) ## Important Notes About Feeding Input Images to the Samples diff --git a/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md b/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md index 98c6e6db24c..d3252704549 100644 --- a/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md +++ b/docs/MO_DG/prepare_model/customize_model_optimizer/Customize_Model_Optimizer.md @@ -157,7 +157,7 @@ the following (for the case when `axis` is not equal to 0 and 1): 4. Use the concatenated value as the second input to the `Reshape` operation. It is highly recommended that you write shape-agnostic transformations to avoid model reshape-ability issues. Refer to -[Using Shape Inference](../../../IE_DG/ShapeInference.md) for more information related to the reshaping of a model. +[Using Shape Inference](../../../OV_Runtime_UG/ShapeInference.md) for more information related to the reshaping of a model. More information on how to develop front phase transformations and dedicated API description is provided in the [Front Phase Transformations](#front-phase-transformations). @@ -171,7 +171,7 @@ defined as a mathematical expression using the [ShapeOf](../../../ops/shape/Shap > **NOTE**: Model Optimizer does not fold sub-graphs starting from the [ShapeOf](../../../ops/shape/ShapeOf_3.md) > operation by default because this leads to a model non-reshape-ability (the command line parameter `--static_shape` -> can override this behavior). Refer to [Using Shape Inference](../../../IE_DG/ShapeInference.md) for more information +> can override this behavior). Refer to [Using Shape Inference](../../../OV_Runtime_UG/ShapeInference.md) for more information > related to reshaping of a model. Model Optimizer calculates output shapes for all operations in a model to write them to Intermediate Representation @@ -507,7 +507,7 @@ There are a number of common attributes used in the operations. Here is the list Model Optimizer operations this attribute should be set to `None`. The model conversion fails if an operation with `type` equal to `None` comes to the IR emitting phase. **Mandatory**. * `version` — the operation set (opset) name the operation belongs to. If not specified, the Model Optimizer sets it -equal to `experimental`. Refer to [nGraph Basic Concepts](@ref openvino_docs_nGraph_DG_basic_concepts) for more +equal to `experimental`. Refer to [OpenVINO Model Representation](@ref openvino_docs_OV_Runtime_UG_Model_Representation) for more information about operation sets. **Mandatory**. * `op` — Model Optimizer type of the operation. In many cases, the value of `type` is equal to the value of `op`. But when the Model Optimizer cannot instantiate the opset operation during model loading, it creates an instance of an internal @@ -1259,6 +1259,6 @@ Refer to the `extensions/back/GatherNormalizer.py` for the example of a such typ ## See Also * [Deep Learning Network Intermediate Representation and Operation Sets in OpenVINO™](../../IR_and_opsets.md) * [Converting a Model to Intermediate Representation (IR)](../convert_model/Converting_Model.md) -* [nGraph Basic Concepts](../../../nGraph_DG/nGraph_basic_concepts.md) -* [Inference Engine Extensibility Mechanism](../../../IE_DG/Extensibility_DG/Intro.md) +* [OpenVINO Model Representation](../../../OV_Runtime_UG/model_representation.md) +* [Inference Engine Extensibility Mechanism](../../../OV_Runtime_UG/Extensibility_DG/Intro.md) * [Extending the Model Optimizer with Caffe* Python Layers](Extending_Model_Optimizer_with_Caffe_Python_Layers.md) diff --git a/docs/IE_DG/API_Changes.md b/docs/OV_Runtime_UG/API_Changes.md similarity index 100% rename from docs/IE_DG/API_Changes.md rename to docs/OV_Runtime_UG/API_Changes.md diff --git a/docs/IE_DG/Bfloat16Inference.md b/docs/OV_Runtime_UG/Bfloat16Inference.md similarity index 100% rename from docs/IE_DG/Bfloat16Inference.md rename to docs/OV_Runtime_UG/Bfloat16Inference.md diff --git a/docs/IE_DG/Deep_Learning_Inference_Engine_DevGuide.md b/docs/OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md similarity index 86% rename from docs/IE_DG/Deep_Learning_Inference_Engine_DevGuide.md rename to docs/OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md index 171ae0fe143..c955f83fef8 100644 --- a/docs/IE_DG/Deep_Learning_Inference_Engine_DevGuide.md +++ b/docs/OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md @@ -1,4 +1,4 @@ -# Inference Engine Developer Guide {#openvino_docs_IE_DG_Deep_Learning_Inference_Engine_DevGuide} +# OpenVINO™ Runtime User Guide {#openvino_docs_IE_DG_Deep_Learning_Inference_Engine_DevGuide} @sphinxdirective @@ -8,6 +8,8 @@ openvino_2_0_transition_guide openvino_docs_IE_DG_Integrate_with_customer_application_new_API + openvino_docs_OV_Runtime_UG_Model_Representation + ngraph_transformation openvino_docs_deployment_optimization_guide_dldt_optimization_guide openvino_docs_IE_DG_Device_Plugins Direct ONNX Format Support @@ -35,8 +37,6 @@ The scheme below illustrates the typical workflow for deploying a trained deep l ![](img/BASIC_FLOW_IE_C.svg) -\\* _nGraph_ is the internal graph representation in the OpenVINO™ toolkit. Use it to [build a model from source code](https://docs.openvino.ai/latest/openvino_docs_nGraph_DG_build_function.html). - ## Video diff --git a/docs/IE_DG/DynamicBatching.md b/docs/OV_Runtime_UG/DynamicBatching.md similarity index 100% rename from docs/IE_DG/DynamicBatching.md rename to docs/OV_Runtime_UG/DynamicBatching.md diff --git a/docs/IE_DG/Extensibility_DG/AddingNGraphOps.md b/docs/OV_Runtime_UG/Extensibility_DG/AddingNGraphOps.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/AddingNGraphOps.md rename to docs/OV_Runtime_UG/Extensibility_DG/AddingNGraphOps.md diff --git a/docs/IE_DG/Extensibility_DG/Building.md b/docs/OV_Runtime_UG/Extensibility_DG/Building.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/Building.md rename to docs/OV_Runtime_UG/Extensibility_DG/Building.md diff --git a/docs/IE_DG/Extensibility_DG/CPU_Kernel.md b/docs/OV_Runtime_UG/Extensibility_DG/CPU_Kernel.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/CPU_Kernel.md rename to docs/OV_Runtime_UG/Extensibility_DG/CPU_Kernel.md diff --git a/docs/IE_DG/Extensibility_DG/Custom_ONNX_Ops.md b/docs/OV_Runtime_UG/Extensibility_DG/Custom_ONNX_Ops.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/Custom_ONNX_Ops.md rename to docs/OV_Runtime_UG/Extensibility_DG/Custom_ONNX_Ops.md diff --git a/docs/IE_DG/Extensibility_DG/Extension.md b/docs/OV_Runtime_UG/Extensibility_DG/Extension.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/Extension.md rename to docs/OV_Runtime_UG/Extensibility_DG/Extension.md diff --git a/docs/IE_DG/Extensibility_DG/GPU_Kernel.md b/docs/OV_Runtime_UG/Extensibility_DG/GPU_Kernel.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/GPU_Kernel.md rename to docs/OV_Runtime_UG/Extensibility_DG/GPU_Kernel.md diff --git a/docs/IE_DG/Extensibility_DG/Intro.md b/docs/OV_Runtime_UG/Extensibility_DG/Intro.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/Intro.md rename to docs/OV_Runtime_UG/Extensibility_DG/Intro.md diff --git a/docs/IE_DG/Extensibility_DG/VPU_Kernel.md b/docs/OV_Runtime_UG/Extensibility_DG/VPU_Kernel.md similarity index 100% rename from docs/IE_DG/Extensibility_DG/VPU_Kernel.md rename to docs/OV_Runtime_UG/Extensibility_DG/VPU_Kernel.md diff --git a/docs/IE_DG/Glossary.md b/docs/OV_Runtime_UG/Glossary.md similarity index 100% rename from docs/IE_DG/Glossary.md rename to docs/OV_Runtime_UG/Glossary.md diff --git a/docs/IE_DG/InferenceEngine_QueryAPI.md b/docs/OV_Runtime_UG/InferenceEngine_QueryAPI.md similarity index 100% rename from docs/IE_DG/InferenceEngine_QueryAPI.md rename to docs/OV_Runtime_UG/InferenceEngine_QueryAPI.md diff --git a/docs/IE_DG/Int8Inference.md b/docs/OV_Runtime_UG/Int8Inference.md similarity index 100% rename from docs/IE_DG/Int8Inference.md rename to docs/OV_Runtime_UG/Int8Inference.md diff --git a/docs/IE_DG/Integrate_with_customer_application_new_API.md b/docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md similarity index 97% rename from docs/IE_DG/Integrate_with_customer_application_new_API.md rename to docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md index 6206e46fda7..62a47b8afdf 100644 --- a/docs/IE_DG/Integrate_with_customer_application_new_API.md +++ b/docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md @@ -34,15 +34,13 @@ Read the sections below to learn about each item. ``` 2. **Include Inference Engine, nGraph and OpenCV libraries** in `project/CMakeLists.txt` -[OpenCV](https://docs.opencv.org/master/db/df5/tutorial_linux_gcc_cmake.html) integration is needed mostly for pre-processing input data and nGraph for more complex applications using [nGraph API](../nGraph_DG/nGraph_dg.md). +[OpenCV](https://docs.opencv.org/master/db/df5/tutorial_linux_gcc_cmake.html) integration is needed mostly for pre-processing input data and model representation in OpenVINO™ Runtime for more complex applications using [OpenVINO Model API](../OV_Runtime_UG/model_representation.md). ``` cmake cmake_minimum_required(VERSION 3.0.0) project(project_name) - find_package(ngraph REQUIRED) - find_package(InferenceEngine REQUIRED) - find_package(OpenCV REQUIRED) + find_package(OpenVINO REQUIRED) add_executable(${PROJECT_NAME} src/main.cpp) - target_link_libraries(${PROJECT_NAME} PRIVATE ${InferenceEngine_LIBRARIES} ${OpenCV_LIBS} ${NGRAPH_LIBRARIES}) + target_link_libraries(${PROJECT_NAME} PRIVATE openvino::runtime) ``` ### Use Inference Engine API to Implement Inference Pipeline @@ -457,7 +455,7 @@ Load the model to the device using `load_network()`: @endsphinxdirective -This example is designed for CPU device, refer to the [Supported Devices](../IE_DG/supported_plugins/Supported_Devices.md) page to read about more devices. +This example is designed for CPU device, refer to the [Supported Devices](../OV_Runtime_UG/supported_plugins/Supported_Devices.md) page to read about more devices. #### Step 4. Prepare input ```py @@ -491,4 +489,4 @@ Congratulations, you have made your first Python application with OpenVINO™ to [ie_api_flow_cpp]: img/BASIC_IE_API_workflow_Cpp.svg [ie_api_use_cpp]: img/IMPLEMENT_PIPELINE_with_API_C.svg [ie_api_flow_python]: img/BASIC_IE_API_workflow_Python.svg -[ie_api_use_python]: img/IMPLEMENT_PIPELINE_with_API_Python.svg \ No newline at end of file +[ie_api_use_python]: img/IMPLEMENT_PIPELINE_with_API_Python.svg diff --git a/docs/IE_DG/Known_Issues_Limitations.md b/docs/OV_Runtime_UG/Known_Issues_Limitations.md similarity index 100% rename from docs/IE_DG/Known_Issues_Limitations.md rename to docs/OV_Runtime_UG/Known_Issues_Limitations.md diff --git a/docs/IE_DG/Memory_primitives.md b/docs/OV_Runtime_UG/Memory_primitives.md similarity index 100% rename from docs/IE_DG/Memory_primitives.md rename to docs/OV_Runtime_UG/Memory_primitives.md diff --git a/docs/IE_DG/Model_caching_overview.md b/docs/OV_Runtime_UG/Model_caching_overview.md similarity index 100% rename from docs/IE_DG/Model_caching_overview.md rename to docs/OV_Runtime_UG/Model_caching_overview.md diff --git a/docs/IE_DG/ONNX_Support.md b/docs/OV_Runtime_UG/ONNX_Support.md similarity index 100% rename from docs/IE_DG/ONNX_Support.md rename to docs/OV_Runtime_UG/ONNX_Support.md diff --git a/docs/IE_DG/Operations_specifications.md b/docs/OV_Runtime_UG/Operations_specifications.md similarity index 100% rename from docs/IE_DG/Operations_specifications.md rename to docs/OV_Runtime_UG/Operations_specifications.md diff --git a/docs/IE_DG/Paddle_Support.md b/docs/OV_Runtime_UG/Paddle_Support.md similarity index 100% rename from docs/IE_DG/Paddle_Support.md rename to docs/OV_Runtime_UG/Paddle_Support.md diff --git a/docs/IE_DG/PythonPackage_Overview.md b/docs/OV_Runtime_UG/PythonPackage_Overview.md similarity index 100% rename from docs/IE_DG/PythonPackage_Overview.md rename to docs/OV_Runtime_UG/PythonPackage_Overview.md diff --git a/docs/IE_DG/Samples_Overview.md b/docs/OV_Runtime_UG/Samples_Overview.md similarity index 100% rename from docs/IE_DG/Samples_Overview.md rename to docs/OV_Runtime_UG/Samples_Overview.md diff --git a/docs/IE_DG/ShapeInference.md b/docs/OV_Runtime_UG/ShapeInference.md similarity index 97% rename from docs/IE_DG/ShapeInference.md rename to docs/OV_Runtime_UG/ShapeInference.md index 827a1fb0bef..f766fa34b98 100644 --- a/docs/IE_DG/ShapeInference.md +++ b/docs/OV_Runtime_UG/ShapeInference.md @@ -43,8 +43,8 @@ If a model has a hard-coded batch dimension, use `InferenceEngine::CNNNetwork::s Inference Engine takes three kinds of a model description as an input, which are converted into an `InferenceEngine::CNNNetwork` object: 1. [Intermediate Representation (IR)](../MO_DG/IR_and_opsets.md) through `InferenceEngine::Core::ReadNetwork` -2. [ONNX model](../IE_DG/ONNX_Support.md) through `InferenceEngine::Core::ReadNetwork` -3. [nGraph function](../nGraph_DG/nGraph_dg.md) through the constructor of `InferenceEngine::CNNNetwork` +2. [ONNX model](../OV_Runtime_UG/ONNX_Support.md) through `InferenceEngine::Core::ReadNetwork` +3. [OpenVINO Model](../OV_Runtime_UG/model_representation.md) through the constructor of `InferenceEngine::CNNNetwork` `InferenceEngine::CNNNetwork` keeps an `ngraph::Function` object with the model description internally. The object should have fully-defined input shapes to be successfully loaded to Inference Engine plugins. @@ -66,7 +66,7 @@ To feed input data of a shape that is different from the model input shape, resh Once the input shape of `InferenceEngine::CNNNetwork` is set, call the `InferenceEngine::Core::LoadNetwork` method to get an `InferenceEngine::ExecutableNetwork` object for inference with updated shapes. -There are other approaches to reshape the model during the stage of IR generation or [nGraph::Function creation](../nGraph_DG/build_function.md). +There are other approaches to reshape the model during the stage of IR generation or [ov::Model creation](../OV_Runtime_UG/model_representation.md). Practically, some models are not ready to be reshaped. In this case, a new input shape cannot be set with the Model Optimizer or the `InferenceEngine::CNNNetwork::reshape` method. @@ -223,4 +223,4 @@ The Inference Engine provides a special mechanism that allows adding support of ### See Also: -[Hello Reshape Python Sample](../../inference_engine/ie_bridges/python/sample/hello_reshape_ssd/README.html) \ No newline at end of file +[Hello Reshape Python Sample](../../samples/python/hello_reshape_ssd/README.html) diff --git a/docs/IE_DG/img/BASIC_FLOW_IE_C.svg b/docs/OV_Runtime_UG/img/BASIC_FLOW_IE_C.svg similarity index 100% rename from docs/IE_DG/img/BASIC_FLOW_IE_C.svg rename to docs/OV_Runtime_UG/img/BASIC_FLOW_IE_C.svg diff --git a/docs/IE_DG/img/BASIC_FLOW_MO.svg b/docs/OV_Runtime_UG/img/BASIC_FLOW_MO.svg similarity index 100% rename from docs/IE_DG/img/BASIC_FLOW_MO.svg rename to docs/OV_Runtime_UG/img/BASIC_FLOW_MO.svg diff --git a/docs/IE_DG/img/BASIC_FLOW_MO_simplified.svg b/docs/OV_Runtime_UG/img/BASIC_FLOW_MO_simplified.svg similarity index 100% rename from docs/IE_DG/img/BASIC_FLOW_MO_simplified.svg rename to docs/OV_Runtime_UG/img/BASIC_FLOW_MO_simplified.svg diff --git a/docs/IE_DG/img/BASIC_IE_API_workflow_Cpp.svg b/docs/OV_Runtime_UG/img/BASIC_IE_API_workflow_Cpp.svg similarity index 100% rename from docs/IE_DG/img/BASIC_IE_API_workflow_Cpp.svg rename to docs/OV_Runtime_UG/img/BASIC_IE_API_workflow_Cpp.svg diff --git a/docs/IE_DG/img/BASIC_IE_API_workflow_Python.svg b/docs/OV_Runtime_UG/img/BASIC_IE_API_workflow_Python.svg similarity index 100% rename from docs/IE_DG/img/BASIC_IE_API_workflow_Python.svg rename to docs/OV_Runtime_UG/img/BASIC_IE_API_workflow_Python.svg diff --git a/docs/IE_DG/img/DEVELOPMENT_FLOW_V3_crunch.svg b/docs/OV_Runtime_UG/img/DEVELOPMENT_FLOW_V3_crunch.svg similarity index 100% rename from docs/IE_DG/img/DEVELOPMENT_FLOW_V3_crunch.svg rename to docs/OV_Runtime_UG/img/DEVELOPMENT_FLOW_V3_crunch.svg diff --git a/docs/IE_DG/img/IMPLEMENT_PIPELINE_with_API_C.svg b/docs/OV_Runtime_UG/img/IMPLEMENT_PIPELINE_with_API_C.svg similarity index 100% rename from docs/IE_DG/img/IMPLEMENT_PIPELINE_with_API_C.svg rename to docs/OV_Runtime_UG/img/IMPLEMENT_PIPELINE_with_API_C.svg diff --git a/docs/IE_DG/img/IMPLEMENT_PIPELINE_with_API_Python.svg b/docs/OV_Runtime_UG/img/IMPLEMENT_PIPELINE_with_API_Python.svg similarity index 100% rename from docs/IE_DG/img/IMPLEMENT_PIPELINE_with_API_Python.svg rename to docs/OV_Runtime_UG/img/IMPLEMENT_PIPELINE_with_API_Python.svg diff --git a/docs/IE_DG/img/LATENCY_VS_THROUGHPUT.svg b/docs/OV_Runtime_UG/img/LATENCY_VS_THROUGHPUT.svg similarity index 100% rename from docs/IE_DG/img/LATENCY_VS_THROUGHPUT.svg rename to docs/OV_Runtime_UG/img/LATENCY_VS_THROUGHPUT.svg diff --git a/docs/IE_DG/img/Latency_Throughput.png b/docs/OV_Runtime_UG/img/Latency_Throughput.png similarity index 100% rename from docs/IE_DG/img/Latency_Throughput.png rename to docs/OV_Runtime_UG/img/Latency_Throughput.png diff --git a/docs/IE_DG/img/NewAndOldCNNNetworkImpl.png b/docs/OV_Runtime_UG/img/NewAndOldCNNNetworkImpl.png similarity index 100% rename from docs/IE_DG/img/NewAndOldCNNNetworkImpl.png rename to docs/OV_Runtime_UG/img/NewAndOldCNNNetworkImpl.png diff --git a/docs/nGraph_DG/img/TopLevelNGraphFlow.png b/docs/OV_Runtime_UG/img/TopLevelNGraphFlow.png similarity index 100% rename from docs/nGraph_DG/img/TopLevelNGraphFlow.png rename to docs/OV_Runtime_UG/img/TopLevelNGraphFlow.png diff --git a/docs/IE_DG/img/WHAT_TO_USE.svg b/docs/OV_Runtime_UG/img/WHAT_TO_USE.svg similarity index 100% rename from docs/IE_DG/img/WHAT_TO_USE.svg rename to docs/OV_Runtime_UG/img/WHAT_TO_USE.svg diff --git a/docs/IE_DG/img/applying_low_latency.png b/docs/OV_Runtime_UG/img/applying_low_latency.png similarity index 100% rename from docs/IE_DG/img/applying_low_latency.png rename to docs/OV_Runtime_UG/img/applying_low_latency.png diff --git a/docs/IE_DG/img/applying_low_latency_2.png b/docs/OV_Runtime_UG/img/applying_low_latency_2.png similarity index 100% rename from docs/IE_DG/img/applying_low_latency_2.png rename to docs/OV_Runtime_UG/img/applying_low_latency_2.png diff --git a/docs/IE_DG/img/bf16_format.png b/docs/OV_Runtime_UG/img/bf16_format.png similarity index 100% rename from docs/IE_DG/img/bf16_format.png rename to docs/OV_Runtime_UG/img/bf16_format.png diff --git a/docs/IE_DG/img/conv_depth_01.png b/docs/OV_Runtime_UG/img/conv_depth_01.png similarity index 100% rename from docs/IE_DG/img/conv_depth_01.png rename to docs/OV_Runtime_UG/img/conv_depth_01.png diff --git a/docs/IE_DG/img/conv_simple_01.png b/docs/OV_Runtime_UG/img/conv_simple_01.png similarity index 100% rename from docs/IE_DG/img/conv_simple_01.png rename to docs/OV_Runtime_UG/img/conv_simple_01.png diff --git a/docs/IE_DG/img/conv_sum_relu_01.png b/docs/OV_Runtime_UG/img/conv_sum_relu_01.png similarity index 100% rename from docs/IE_DG/img/conv_sum_relu_01.png rename to docs/OV_Runtime_UG/img/conv_sum_relu_01.png diff --git a/docs/IE_DG/img/cpu_int8_flow.png b/docs/OV_Runtime_UG/img/cpu_int8_flow.png similarity index 100% rename from docs/IE_DG/img/cpu_int8_flow.png rename to docs/OV_Runtime_UG/img/cpu_int8_flow.png diff --git a/docs/IE_DG/img/cpu_streams_explained.png b/docs/OV_Runtime_UG/img/cpu_streams_explained.png similarity index 100% rename from docs/IE_DG/img/cpu_streams_explained.png rename to docs/OV_Runtime_UG/img/cpu_streams_explained.png diff --git a/docs/IE_DG/img/deploy_encrypted_model.png b/docs/OV_Runtime_UG/img/deploy_encrypted_model.png similarity index 100% rename from docs/IE_DG/img/deploy_encrypted_model.png rename to docs/OV_Runtime_UG/img/deploy_encrypted_model.png diff --git a/docs/IE_DG/img/deploy_encrypted_model.vsdx b/docs/OV_Runtime_UG/img/deploy_encrypted_model.vsdx similarity index 100% rename from docs/IE_DG/img/deploy_encrypted_model.vsdx rename to docs/OV_Runtime_UG/img/deploy_encrypted_model.vsdx diff --git a/docs/IE_DG/img/development_deployment.png b/docs/OV_Runtime_UG/img/development_deployment.png similarity index 100% rename from docs/IE_DG/img/development_deployment.png rename to docs/OV_Runtime_UG/img/development_deployment.png diff --git a/docs/IE_DG/img/diagram_workflow.svg b/docs/OV_Runtime_UG/img/diagram_workflow.svg similarity index 100% rename from docs/IE_DG/img/diagram_workflow.svg rename to docs/OV_Runtime_UG/img/diagram_workflow.svg diff --git a/docs/IE_DG/img/example_sample_output.png b/docs/OV_Runtime_UG/img/example_sample_output.png similarity index 100% rename from docs/IE_DG/img/example_sample_output.png rename to docs/OV_Runtime_UG/img/example_sample_output.png diff --git a/docs/IE_DG/img/fpga_full_workflow.png b/docs/OV_Runtime_UG/img/fpga_full_workflow.png similarity index 100% rename from docs/IE_DG/img/fpga_full_workflow.png rename to docs/OV_Runtime_UG/img/fpga_full_workflow.png diff --git a/docs/IE_DG/img/fpga_platform_hub.png b/docs/OV_Runtime_UG/img/fpga_platform_hub.png similarity index 100% rename from docs/IE_DG/img/fpga_platform_hub.png rename to docs/OV_Runtime_UG/img/fpga_platform_hub.png diff --git a/docs/IE_DG/img/fullyconnected_activation_01.png b/docs/OV_Runtime_UG/img/fullyconnected_activation_01.png similarity index 100% rename from docs/IE_DG/img/fullyconnected_activation_01.png rename to docs/OV_Runtime_UG/img/fullyconnected_activation_01.png diff --git a/docs/nGraph_DG/img/graph_rewrite_efficient_search.png b/docs/OV_Runtime_UG/img/graph_rewrite_efficient_search.png similarity index 100% rename from docs/nGraph_DG/img/graph_rewrite_efficient_search.png rename to docs/OV_Runtime_UG/img/graph_rewrite_efficient_search.png diff --git a/docs/nGraph_DG/img/graph_rewrite_execution.png b/docs/OV_Runtime_UG/img/graph_rewrite_execution.png similarity index 100% rename from docs/nGraph_DG/img/graph_rewrite_execution.png rename to docs/OV_Runtime_UG/img/graph_rewrite_execution.png diff --git a/docs/IE_DG/img/group_convolutions_01.png b/docs/OV_Runtime_UG/img/group_convolutions_01.png similarity index 100% rename from docs/IE_DG/img/group_convolutions_01.png rename to docs/OV_Runtime_UG/img/group_convolutions_01.png diff --git a/docs/IE_DG/img/hor_fusion_1.png b/docs/OV_Runtime_UG/img/hor_fusion_1.png similarity index 100% rename from docs/IE_DG/img/hor_fusion_1.png rename to docs/OV_Runtime_UG/img/hor_fusion_1.png diff --git a/docs/IE_DG/img/hor_fusion_2.png b/docs/OV_Runtime_UG/img/hor_fusion_2.png similarity index 100% rename from docs/IE_DG/img/hor_fusion_2.png rename to docs/OV_Runtime_UG/img/hor_fusion_2.png diff --git a/docs/IE_DG/img/hor_fusion_3.png b/docs/OV_Runtime_UG/img/hor_fusion_3.png similarity index 100% rename from docs/IE_DG/img/hor_fusion_3.png rename to docs/OV_Runtime_UG/img/hor_fusion_3.png diff --git a/docs/IE_DG/img/hor_fusion_4.png b/docs/OV_Runtime_UG/img/hor_fusion_4.png similarity index 100% rename from docs/IE_DG/img/hor_fusion_4.png rename to docs/OV_Runtime_UG/img/hor_fusion_4.png diff --git a/docs/IE_DG/img/ie_api_cpp.png b/docs/OV_Runtime_UG/img/ie_api_cpp.png similarity index 100% rename from docs/IE_DG/img/ie_api_cpp.png rename to docs/OV_Runtime_UG/img/ie_api_cpp.png diff --git a/docs/IE_DG/img/ie_api_integration_cpp.png b/docs/OV_Runtime_UG/img/ie_api_integration_cpp.png similarity index 100% rename from docs/IE_DG/img/ie_api_integration_cpp.png rename to docs/OV_Runtime_UG/img/ie_api_integration_cpp.png diff --git a/docs/IE_DG/img/ie_api_integration_python.png b/docs/OV_Runtime_UG/img/ie_api_integration_python.png similarity index 100% rename from docs/IE_DG/img/ie_api_integration_python.png rename to docs/OV_Runtime_UG/img/ie_api_integration_python.png diff --git a/docs/IE_DG/img/ie_api_python.png b/docs/OV_Runtime_UG/img/ie_api_python.png similarity index 100% rename from docs/IE_DG/img/ie_api_python.png rename to docs/OV_Runtime_UG/img/ie_api_python.png diff --git a/docs/IE_DG/img/ie_workflow_steps.png b/docs/OV_Runtime_UG/img/ie_workflow_steps.png similarity index 100% rename from docs/IE_DG/img/ie_workflow_steps.png rename to docs/OV_Runtime_UG/img/ie_workflow_steps.png diff --git a/docs/IE_DG/img/intel_logo.png b/docs/OV_Runtime_UG/img/intel_logo.png similarity index 100% rename from docs/IE_DG/img/intel_logo.png rename to docs/OV_Runtime_UG/img/intel_logo.png diff --git a/docs/IE_DG/img/ir_add_n_ref.png b/docs/OV_Runtime_UG/img/ir_add_n_ref.png similarity index 100% rename from docs/IE_DG/img/ir_add_n_ref.png rename to docs/OV_Runtime_UG/img/ir_add_n_ref.png diff --git a/docs/IE_DG/img/latency_throughput_1.png b/docs/OV_Runtime_UG/img/latency_throughput_1.png similarity index 100% rename from docs/IE_DG/img/latency_throughput_1.png rename to docs/OV_Runtime_UG/img/latency_throughput_1.png diff --git a/docs/IE_DG/img/llt2_use_const_initializer.png b/docs/OV_Runtime_UG/img/llt2_use_const_initializer.png similarity index 100% rename from docs/IE_DG/img/llt2_use_const_initializer.png rename to docs/OV_Runtime_UG/img/llt2_use_const_initializer.png diff --git a/docs/IE_DG/img/low_latency_limitation_1.png b/docs/OV_Runtime_UG/img/low_latency_limitation_1.png similarity index 100% rename from docs/IE_DG/img/low_latency_limitation_1.png rename to docs/OV_Runtime_UG/img/low_latency_limitation_1.png diff --git a/docs/IE_DG/img/low_latency_limitation_2.png b/docs/OV_Runtime_UG/img/low_latency_limitation_2.png similarity index 100% rename from docs/IE_DG/img/low_latency_limitation_2.png rename to docs/OV_Runtime_UG/img/low_latency_limitation_2.png diff --git a/docs/IE_DG/img/mkldnn_conv_sum.png b/docs/OV_Runtime_UG/img/mkldnn_conv_sum.png similarity index 100% rename from docs/IE_DG/img/mkldnn_conv_sum.png rename to docs/OV_Runtime_UG/img/mkldnn_conv_sum.png diff --git a/docs/IE_DG/img/mkldnn_conv_sum_result.png b/docs/OV_Runtime_UG/img/mkldnn_conv_sum_result.png similarity index 100% rename from docs/IE_DG/img/mkldnn_conv_sum_result.png rename to docs/OV_Runtime_UG/img/mkldnn_conv_sum_result.png diff --git a/docs/IE_DG/img/mkldnn_group_conv.png b/docs/OV_Runtime_UG/img/mkldnn_group_conv.png similarity index 100% rename from docs/IE_DG/img/mkldnn_group_conv.png rename to docs/OV_Runtime_UG/img/mkldnn_group_conv.png diff --git a/docs/nGraph_DG/img/ngraph_insert_node.png b/docs/OV_Runtime_UG/img/ngraph_insert_node.png similarity index 100% rename from docs/nGraph_DG/img/ngraph_insert_node.png rename to docs/OV_Runtime_UG/img/ngraph_insert_node.png diff --git a/docs/nGraph_DG/img/ngraph_replace_node.png b/docs/OV_Runtime_UG/img/ngraph_replace_node.png similarity index 100% rename from docs/nGraph_DG/img/ngraph_replace_node.png rename to docs/OV_Runtime_UG/img/ngraph_replace_node.png diff --git a/docs/IE_DG/img/opt-notice-en_080411.gif b/docs/OV_Runtime_UG/img/opt-notice-en_080411.gif similarity index 100% rename from docs/IE_DG/img/opt-notice-en_080411.gif rename to docs/OV_Runtime_UG/img/opt-notice-en_080411.gif diff --git a/docs/IE_DG/img/optimizations/groups.png b/docs/OV_Runtime_UG/img/optimizations/groups.png similarity index 100% rename from docs/IE_DG/img/optimizations/groups.png rename to docs/OV_Runtime_UG/img/optimizations/groups.png diff --git a/docs/IE_DG/img/optimizations/inception_v4.png b/docs/OV_Runtime_UG/img/optimizations/inception_v4.png similarity index 100% rename from docs/IE_DG/img/optimizations/inception_v4.png rename to docs/OV_Runtime_UG/img/optimizations/inception_v4.png diff --git a/docs/IE_DG/img/optimizations/resnet_269.png b/docs/OV_Runtime_UG/img/optimizations/resnet_269.png similarity index 100% rename from docs/IE_DG/img/optimizations/resnet_269.png rename to docs/OV_Runtime_UG/img/optimizations/resnet_269.png diff --git a/docs/IE_DG/img/optimizations/resnet_optimization.png b/docs/OV_Runtime_UG/img/optimizations/resnet_optimization.png similarity index 100% rename from docs/IE_DG/img/optimizations/resnet_optimization.png rename to docs/OV_Runtime_UG/img/optimizations/resnet_optimization.png diff --git a/docs/IE_DG/img/output_trimmed.png b/docs/OV_Runtime_UG/img/output_trimmed.png similarity index 100% rename from docs/IE_DG/img/output_trimmed.png rename to docs/OV_Runtime_UG/img/output_trimmed.png diff --git a/docs/IE_DG/img/pooling_fakequant_01.png b/docs/OV_Runtime_UG/img/pooling_fakequant_01.png similarity index 100% rename from docs/IE_DG/img/pooling_fakequant_01.png rename to docs/OV_Runtime_UG/img/pooling_fakequant_01.png diff --git a/docs/nGraph_DG/img/register_new_node.png b/docs/OV_Runtime_UG/img/register_new_node.png similarity index 100% rename from docs/nGraph_DG/img/register_new_node.png rename to docs/OV_Runtime_UG/img/register_new_node.png diff --git a/docs/IE_DG/img/resnet_269.png b/docs/OV_Runtime_UG/img/resnet_269.png similarity index 100% rename from docs/IE_DG/img/resnet_269.png rename to docs/OV_Runtime_UG/img/resnet_269.png diff --git a/docs/IE_DG/img/state_network_example.png b/docs/OV_Runtime_UG/img/state_network_example.png similarity index 100% rename from docs/IE_DG/img/state_network_example.png rename to docs/OV_Runtime_UG/img/state_network_example.png diff --git a/docs/nGraph_DG/img/transformations_structure.png b/docs/OV_Runtime_UG/img/transformations_structure.png similarity index 100% rename from docs/nGraph_DG/img/transformations_structure.png rename to docs/OV_Runtime_UG/img/transformations_structure.png diff --git a/docs/IE_DG/img/vtune_async.png b/docs/OV_Runtime_UG/img/vtune_async.png similarity index 100% rename from docs/IE_DG/img/vtune_async.png rename to docs/OV_Runtime_UG/img/vtune_async.png diff --git a/docs/IE_DG/img/vtune_option.png b/docs/OV_Runtime_UG/img/vtune_option.png similarity index 100% rename from docs/IE_DG/img/vtune_option.png rename to docs/OV_Runtime_UG/img/vtune_option.png diff --git a/docs/IE_DG/img/vtune_regular.png b/docs/OV_Runtime_UG/img/vtune_regular.png similarity index 100% rename from docs/IE_DG/img/vtune_regular.png rename to docs/OV_Runtime_UG/img/vtune_regular.png diff --git a/docs/IE_DG/img/vtune_timeline.png b/docs/OV_Runtime_UG/img/vtune_timeline.png similarity index 100% rename from docs/IE_DG/img/vtune_timeline.png rename to docs/OV_Runtime_UG/img/vtune_timeline.png diff --git a/docs/IE_DG/img/vtune_topdown_view.jpg b/docs/OV_Runtime_UG/img/vtune_topdown_view.jpg similarity index 100% rename from docs/IE_DG/img/vtune_topdown_view.jpg rename to docs/OV_Runtime_UG/img/vtune_topdown_view.jpg diff --git a/docs/IE_DG/img/yolo_tiny_v1.png b/docs/OV_Runtime_UG/img/yolo_tiny_v1.png similarity index 100% rename from docs/IE_DG/img/yolo_tiny_v1.png rename to docs/OV_Runtime_UG/img/yolo_tiny_v1.png diff --git a/docs/OV_Runtime_UG/model_representation.md b/docs/OV_Runtime_UG/model_representation.md new file mode 100644 index 00000000000..91202aeb8c8 --- /dev/null +++ b/docs/OV_Runtime_UG/model_representation.md @@ -0,0 +1,91 @@ +# Model Representation in OpenVINO™ Runtime {#openvino_docs_OV_Runtime_UG_Model_Representation} + +In OpenVINO™ Runtime a model is represented by the `ov::Model` class. + +## Model Representation + +The `ov::Model` object stores shared pointers to `ov::op::v0::Parameter`, `ov::op::v0::Result` and `ov::op::Sink` operations that are inputs, outputs and sinks of the graph. +Sinks of the graph have no consumers and are not included in the results vector. All other operations hold each other via shared pointers: child operation holds its parent (hard link). If an operation has no consumers and it's not the `Result` or `Sink` operation +(shared pointer counter is zero), then it will be destructed and won't be accessible anymore. + +Each operation in `ov::Model` has the `std::shared_ptr` type. + +For details on how to build a model in OpenVINO™ Runtime, see the [Build a Model in OpenVINO™ Runtime](@ref build_model) section. + +## Operations + +The `ov::Op` class represents any abstract operation in the model representation. Use this class to create [custom operations](../OV_Runtime_UG/Extensibility_DG/AddingNGraphOps.md). + +## Operation Sets + +Operation set (opset) is a collection of operations that can be used to construct a model. The `ov::OpSet` class provides a functionality to work with operation sets. +For each operation set, OpenVINO™ Runtime provides a separate namespace, for example `opset8`. +Each OpenVINO™ Release release introduces new operations and add these operations to a new operation set. New operation sets help to introduce a new version of operations that change behavior of previous operations. Using operation sets allows you to avoid changes in your application if new operations have been introduced. + +## Static and Partial Shapes + +There are two types used for shape representation: + +* `ov::Shape` - Represents static (fully defined) shapes. + +* `ov::PartialShape` - Represents dynamic shapes. That means that the rank or some of dimensions are dynamic (undefined). `ov::PartialShape` can be converted to `ov::Shape` using the `get_shape()` method if all dimensions are static; otherwise the conversion raises an exception. + + +## Build a Model in OpenVINO™ Runtime {#build_model} + +You can create a model from source. This section illustrates how to construct a model composed of operations from an available operation set. + +Operation set `opsetX` integrates a list of pre-compiled operations that work for this purpose. In other words, `opsetX` defines a set of operations for building a graph. + +For a complete list of operation sets supported in OpenVINO™ toolkit, see [Available Operations Sets](../ops/opset.md). + +To add suport of custom operations, see the [Add Custom OpenVINO Operations](../OV_Runtime_UG/Extensibility_DG/Intro.md) document. + +To build an `ov::Model` instance from `opset8` operations, include the following files: + + - C++ + @snippet example_ngraph_utils.cpp ov:include + + - Python + ```python + import openvino.runtime.opset8 as ov + from openvino.runtime import Model + ``` + +The following code demonstrates how to create a simple model: + + - C++ + @snippet example_ngraph_utils.cpp ov:create_simple_model + + - Python + ```python + TBD + ``` + + +The following code creates a model with several outputs: + + - C++ + @snippet example_ngraph_utils.cpp ov:create_advanced_model + + - Python + ```python + TBD + ``` + +## FAQ + +### Does OpenVINO™ Runtime provide any capabilities to debug the model structure and model modification? + - To receive additional messages about applied graph modifications, rebuild the OpenVINO™ Runtime library with the `-DENABLE_OPENVINO_DEBUG=ON` option. + - A model can be visualized to image from the xDot format: + @snippet example_ngraph_utils.cpp ov:visualize + - A model can be serialized to IR: + @snippet example_ngraph_utils.cpp ov:serialize + +### How can I develop my own transformation pass? + See the [Transformations Developer Guide](./nGraphTransformation.md). + +## See Also + +* [Available Operation Sets](../ops/opset.md) +* [OpenVINO™ Runtime Extensibility Developer Guide](../OV_Runtime_UG/Extensibility_DG/Intro.md) diff --git a/docs/nGraph_DG/nGraphTransformation.md b/docs/OV_Runtime_UG/nGraphTransformation.md similarity index 99% rename from docs/nGraph_DG/nGraphTransformation.md rename to docs/OV_Runtime_UG/nGraphTransformation.md index a0907b0521b..901fec6e7c5 100644 --- a/docs/nGraph_DG/nGraphTransformation.md +++ b/docs/OV_Runtime_UG/nGraphTransformation.md @@ -42,7 +42,7 @@ nGraph function is a very simple thing: it stores shared pointers to `ngraph::op Sinks of the graph have no consumers and not included into results vector. All other operations hold each other via shared pointers: child operation holds its parent (hard link). If operation has no consumers and it's not Result or Sink operation (shared pointer counter is zero) then it will be destructed and won't be accessible anymore. Each operation in `ngraph::Function` has a `std::shared_ptr` type. -For examples of how to build an nGraph function, see the [Build nGraph Function](./build_function.md) page. +For examples of how to build an nGraph function, see the [Build nGraph Function](./model_representation.md) page. ## Transformations types @@ -267,7 +267,7 @@ When developing a transformation, you need to follow these transformation rules: Use the latest version of OpSet in your transformation. An exception is op_conversion transformations, where different opsets can be used. -@snippet example_ngraph_utils.cpp ngraph:include +@snippet example_ngraph_utils.cpp ov:include ###2. Dynamic Shape and Rank @@ -387,7 +387,7 @@ The most popular tool for transformations debugging is the `ngraph::pass::Visual Usage example: -@snippet example_ngraph_utils.cpp ngraph:visualize +@snippet example_ngraph_utils.cpp ov:visualize `ngraph::pass::VisualizeTree` can be parametrized via environment variables: diff --git a/docs/IE_DG/network_state_intro.md b/docs/OV_Runtime_UG/network_state_intro.md similarity index 98% rename from docs/IE_DG/network_state_intro.md rename to docs/OV_Runtime_UG/network_state_intro.md index 908dc58dcf6..2a04dd05dc9 100644 --- a/docs/IE_DG/network_state_intro.md +++ b/docs/OV_Runtime_UG/network_state_intro.md @@ -32,7 +32,7 @@ You can find more details on these operations in [ReadValue specification](../op ## Examples of Representation of a Network with States -To get a model with states ready for inference, you can convert a model from another framework to IR with Model Optimizer or create an nGraph function (details can be found in [Build nGraph Function section](../nGraph_DG/build_function.md)). Let's represent the following graph in both forms: +To get a model with states ready for inference, you can convert a model from another framework to IR with Model Optimizer or create an nGraph function (details can be found in [Build OpenVINO Model section](../OV_Runtime_UG/model_representation.md)). Let's represent the following graph in both forms: ![state_network_example] @@ -246,7 +246,7 @@ After applying the transformation, ReadValue operations can receive other operat 1. Get CNNNetwork. Either way is acceptable: * [from IR or ONNX model](./Integrate_with_customer_application_new_API.md) - * [from nGraph Function](../nGraph_DG/build_function.md) + * [from ov::Model](../OV_Runtime_UG/model_representation.md) 2. Change the number of iterations inside TensorIterator/Loop nodes in the network using the [Reshape](ShapeInference.md) feature. @@ -350,7 +350,7 @@ After applying the transformation, ReadValue operations can receive other operat 1. Get CNNNetwork. Either way is acceptable: * [from IR or ONNX model](./Integrate_with_customer_application_new_API.md) - * [from nGraph Function](../nGraph_DG/build_function.md) + * [from ov::Model](../OV_Runtime_UG/model_representation.md) 2. [Reshape](ShapeInference.md) the CNNNetwork network if necessary. **Necessary case:** where the sequence_lengths dimension of input > 1, it means TensorIterator layer will have number_iterations > 1. We should reshape the inputs of the network to set sequence_dimension to exactly 1. diff --git a/docs/IE_DG/protecting_model_guide.md b/docs/OV_Runtime_UG/protecting_model_guide.md similarity index 100% rename from docs/IE_DG/protecting_model_guide.md rename to docs/OV_Runtime_UG/protecting_model_guide.md diff --git a/docs/IE_DG/supported_plugins/AUTO.md b/docs/OV_Runtime_UG/supported_plugins/AUTO.md similarity index 100% rename from docs/IE_DG/supported_plugins/AUTO.md rename to docs/OV_Runtime_UG/supported_plugins/AUTO.md diff --git a/docs/IE_DG/supported_plugins/CPU.md b/docs/OV_Runtime_UG/supported_plugins/CPU.md similarity index 100% rename from docs/IE_DG/supported_plugins/CPU.md rename to docs/OV_Runtime_UG/supported_plugins/CPU.md diff --git a/docs/IE_DG/supported_plugins/Device_Plugins.md b/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md similarity index 100% rename from docs/IE_DG/supported_plugins/Device_Plugins.md rename to docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md diff --git a/docs/IE_DG/supported_plugins/GNA.md b/docs/OV_Runtime_UG/supported_plugins/GNA.md similarity index 100% rename from docs/IE_DG/supported_plugins/GNA.md rename to docs/OV_Runtime_UG/supported_plugins/GNA.md diff --git a/docs/IE_DG/supported_plugins/GPU.md b/docs/OV_Runtime_UG/supported_plugins/GPU.md similarity index 100% rename from docs/IE_DG/supported_plugins/GPU.md rename to docs/OV_Runtime_UG/supported_plugins/GPU.md diff --git a/docs/IE_DG/supported_plugins/GPU_RemoteBlob_API.md b/docs/OV_Runtime_UG/supported_plugins/GPU_RemoteBlob_API.md similarity index 100% rename from docs/IE_DG/supported_plugins/GPU_RemoteBlob_API.md rename to docs/OV_Runtime_UG/supported_plugins/GPU_RemoteBlob_API.md diff --git a/docs/IE_DG/supported_plugins/HDDL.md b/docs/OV_Runtime_UG/supported_plugins/HDDL.md similarity index 100% rename from docs/IE_DG/supported_plugins/HDDL.md rename to docs/OV_Runtime_UG/supported_plugins/HDDL.md diff --git a/docs/IE_DG/supported_plugins/HETERO.md b/docs/OV_Runtime_UG/supported_plugins/HETERO.md similarity index 100% rename from docs/IE_DG/supported_plugins/HETERO.md rename to docs/OV_Runtime_UG/supported_plugins/HETERO.md diff --git a/docs/IE_DG/supported_plugins/MULTI.md b/docs/OV_Runtime_UG/supported_plugins/MULTI.md similarity index 100% rename from docs/IE_DG/supported_plugins/MULTI.md rename to docs/OV_Runtime_UG/supported_plugins/MULTI.md diff --git a/docs/IE_DG/supported_plugins/MYRIAD.md b/docs/OV_Runtime_UG/supported_plugins/MYRIAD.md similarity index 100% rename from docs/IE_DG/supported_plugins/MYRIAD.md rename to docs/OV_Runtime_UG/supported_plugins/MYRIAD.md diff --git a/docs/IE_DG/supported_plugins/Supported_Devices.md b/docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md similarity index 100% rename from docs/IE_DG/supported_plugins/Supported_Devices.md rename to docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md diff --git a/docs/IE_DG/supported_plugins/VPU.md b/docs/OV_Runtime_UG/supported_plugins/VPU.md similarity index 100% rename from docs/IE_DG/supported_plugins/VPU.md rename to docs/OV_Runtime_UG/supported_plugins/VPU.md diff --git a/docs/api/api_reference.rst b/docs/api/api_reference.rst index c2cb1d8a1f9..7010d07c283 100644 --- a/docs/api/api_reference.rst +++ b/docs/api/api_reference.rst @@ -5,8 +5,6 @@ API Reference The OpenVINO toolkit has APIs available for Python, C, and C++. Most features exist for all APIs, but there are some differences. The C++ API is the most comprehensive. -There is also an nGraph API available for Python and C++, with enhanced operation sets and other features. Read `nGraph `_ and `Introduction to the nGraph <../openvino_docs_nGraph_DG_Introduction.html>`_ for more information. - API references available: diff --git a/docs/benchmarks/performance_benchmarks_faq.md b/docs/benchmarks/performance_benchmarks_faq.md index 612dca3e5b6..2010111bf3b 100644 --- a/docs/benchmarks/performance_benchmarks_faq.md +++ b/docs/benchmarks/performance_benchmarks_faq.md @@ -48,7 +48,7 @@ The image size used in the inference depends on the network being benchmarked. T | [vgg19-caffe](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/vgg19-caffe2) | VGG-19 | classification | 224x224| #### 7. Where can I purchase the specific hardware used in the benchmarking? -Intel partners with various vendors all over the world. Visit the [Intel® AI: In Production Partners & Solutions Catalog](https://www.intel.com/content/www/us/en/internet-of-things/ai-in-production/partners-solutions-catalog.html) for a list of Equipment Makers and the [Supported Devices](../IE_DG/supported_plugins/Supported_Devices.md) documentation. You can also remotely test and run models before purchasing any hardware by using [Intel® DevCloud for the Edge](http://devcloud.intel.com/edge/). +Intel partners with various vendors all over the world. Visit the [Intel® AI: In Production Partners & Solutions Catalog](https://www.intel.com/content/www/us/en/internet-of-things/ai-in-production/partners-solutions-catalog.html) for a list of Equipment Makers and the [Supported Devices](../OV_Runtime_UG/supported_plugins/Supported_Devices.md) documentation. You can also remotely test and run models before purchasing any hardware by using [Intel® DevCloud for the Edge](http://devcloud.intel.com/edge/). #### 8. How can I optimize my models for better performance or accuracy? We published a set of guidelines and recommendations to optimize your models available in the [optimization guide](../optimization_guide/dldt_optimization_guide.md). For further support, please join the conversation in the [Community Forum](https://software.intel.com/en-us/forums/intel-distribution-of-openvino-toolkit). diff --git a/docs/documentation.md b/docs/documentation.md index e421351fca7..ae477d00ebb 100644 --- a/docs/documentation.md +++ b/docs/documentation.md @@ -18,7 +18,6 @@ :hidden: openvino_docs_IE_DG_Deep_Learning_Inference_Engine_DevGuide - openvino_docs_nGraph_DG_DevGuide openvino_docs_install_guides_deployment_manager_tool openvino_inference_engine_tools_compile_tool_README @@ -95,7 +94,7 @@ This section provides reference documents that guide you through developing your With the [Model Downloader](@ref omz_tools_downloader) and [Model Optimizer](MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) guides, you will learn to download pre-trained models and convert them for use with the OpenVINO™ toolkit. You can provide your own model or choose a public or Intel model from a broad selection provided in the [Open Model Zoo](model_zoo.md). ## Deploying Inference -The [Inference Engine Developer Guide](IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) explains the process of creating your own application that runs inference with the OpenVINO™ toolkit. The [API Reference](./api_references.html) defines the Inference Engine API for Python, C++, and C and the nGraph API for Python and C++. The Inference Engine API is what you'll use to create an OpenVINO™ application, while the nGraph API is available for using enhanced operations sets and other features. After writing your application, you can use the [Deployment Manager](install_guides/deployment-manager-tool.md) for deploying to target devices. +The [OpenVINO™ Runtime User Guide](OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) explains the process of creating your own application that runs inference with the OpenVINO™ toolkit. The [API Reference](./api_references.html) defines the Inference Engine API for Python, C++, and C and the nGraph API for Python and C++. The Inference Engine API is what you'll use to create an OpenVINO™ application, while the nGraph API is available for using enhanced operations sets and other features. After writing your application, you can use the [Deployment Manager](install_guides/deployment-manager-tool.md) for deploying to target devices. ## Tuning for Performance The toolkit provides a [Performance Optimization Guide](optimization_guide/dldt_optimization_guide.md) and utilities for squeezing the best performance out of your application, including [Accuracy Checker](@ref omz_tools_accuracy_checker), [Post-Training Optimization Tool](@ref pot_README), and other tools for measuring accuracy, benchmarking performance, and tuning your application. @@ -104,4 +103,4 @@ The toolkit provides a [Performance Optimization Guide](optimization_guide/dldt_ You can choose to use the [OpenVINO™ Deep Learning Workbench](@ref workbench_docs_Workbench_DG_Introduction), a web-based tool that guides you through the process of converting, measuring, optimizing, and deploying models. This tool also serves as a low-effort introduction to the toolkit and provides a variety of useful interactive charts for understanding performance. ## Media Processing -The OpenVINO™ toolkit comes with several sets of libraries and tools that add capability and flexibility to the toolkit. These include [DL Streamer](@ref gst_samples_README), a utility that eases creation of pipelines via command line or API, and optimized versions of OpenCV and OpenCL. \ No newline at end of file +The OpenVINO™ toolkit comes with several sets of libraries and tools that add capability and flexibility to the toolkit. These include [DL Streamer](@ref gst_samples_README), a utility that eases creation of pipelines via command line or API, and optimized versions of OpenCV and OpenCL. diff --git a/docs/get_started/get_started_demos.md b/docs/get_started/get_started_demos.md index 25b5262491f..25eb5786d5e 100644 --- a/docs/get_started/get_started_demos.md +++ b/docs/get_started/get_started_demos.md @@ -869,6 +869,6 @@ To run the **Security Barrier Camera Demo Application** using an input image on For more samples and demos, you can visit the samples and demos pages below. You can review samples and demos by complexity or by usage, run the relevant application, and adapt the code for your use. -[Samples](../IE_DG/Samples_Overview.md) +[Samples](../OV_Runtime_UG/Samples_Overview.md) -[Demos](@ref omz_demos) \ No newline at end of file +[Demos](@ref omz_demos) diff --git a/docs/install_guides/installing-openvino-apt.md b/docs/install_guides/installing-openvino-apt.md index bcd7d63c103..39ef1be0d7e 100644 --- a/docs/install_guides/installing-openvino-apt.md +++ b/docs/install_guides/installing-openvino-apt.md @@ -21,7 +21,7 @@ The following components are installed with the OpenVINO runtime package: | Component | Description| |-----------|------------| -| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md)| The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications. | +| [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md)| The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications. | | [OpenCV*](https://docs.opencv.org/master/) | OpenCV* community version compiled for Intel® hardware. | | Deep Learning Streamer (DL Streamer) | Streaming analytics framework, based on GStreamer, for constructing graphs of media analytics components. For the DL Streamer documentation, see [DL Streamer Samples](@ref gst_samples_README), [API Reference](https://openvinotoolkit.github.io/dlstreamer_gst/), [Elements](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/Elements), [Tutorial](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/DL-Streamer-Tutorial). | @@ -32,9 +32,9 @@ The following components are installed with the OpenVINO developer package: | Component | Description| |-----------|------------| | [Model Optimizer](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) | This tool imports, converts, and optimizes models that were trained in popular frameworks to a format usable by Intel tools, especially the Inference Engine. 
Popular frameworks include Caffe\*, TensorFlow\*, MXNet\*, and ONNX\*. | -| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) | The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications.| +| [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) | The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications.| | [OpenCV*](https://docs.opencv.org/master/) | OpenCV\* community version compiled for Intel® hardware | -| [Sample Applications](../IE_DG/Samples_Overview.md) | A set of simple console applications demonstrating how to use the Inference Engine in your applications. | +| [Sample Applications](../OV_Runtime_UG/Samples_Overview.md) | A set of simple console applications demonstrating how to use the Inference Engine in your applications. | | [Demo Applications](@ref omz_demos) | A set of console applications that demonstrate how you can use the Inference Engine in your applications to solve specific use cases. | | Additional Tools | A set of tools to work with your models including [Accuracy Checker utility](@ref omz_tools_accuracy_checker), [Post-Training Optimization Tool Guide](@ref pot_README), [Model Downloader](@ref omz_tools_downloader) and other | | [Documentation for Pre-Trained Models ](@ref omz_models_group_intel) | Documentation for the pre-trained models available in the [Open Model Zoo repo](https://github.com/openvinotoolkit/open_model_zoo). | @@ -158,7 +158,7 @@ sudo apt autoremove intel-openvino--ubuntu-.< - Intel® Distribution of OpenVINO™ toolkit home page: [https://software.intel.com/en-us/openvino-toolkit](https://software.intel.com/en-us/openvino-toolkit). - OpenVINO™ toolkit online documentation: [https://docs.openvino.ai](https://docs.openvino.ai). - [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md). -- [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md). -- For more information on Sample Applications, see the [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md). +- [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md). +- For more information on Sample Applications, see the [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md). - For IoT Libraries & Code Samples see the [Intel® IoT Developer Kit](https://github.com/intel-iot-devkit). diff --git a/docs/install_guides/installing-openvino-conda.md b/docs/install_guides/installing-openvino-conda.md index d933d60dc45..d272429ef5a 100644 --- a/docs/install_guides/installing-openvino-conda.md +++ b/docs/install_guides/installing-openvino-conda.md @@ -16,7 +16,7 @@ The **runtime package** includes the following components installed by default: | Component | Description | |-----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications. | +| [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications. | ## System Requirements @@ -81,7 +81,7 @@ Now you can start developing your application. - Intel® Distribution of OpenVINO™ toolkit home page: [https://software.intel.com/en-us/openvino-toolkit](https://software.intel.com/en-us/openvino-toolkit). - OpenVINO™ toolkit online documentation: [https://docs.openvino.ai](https://docs.openvino.ai). - [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md). -- [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md). -- For more information on Sample Applications, see the [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md). +- [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md). +- For more information on Sample Applications, see the [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md). - Intel® Distribution of OpenVINO™ toolkit Anaconda* home page: [https://anaconda.org/intel/openvino-ie4py](https://anaconda.org/intel/openvino-ie4py) diff --git a/docs/install_guides/installing-openvino-linux.md b/docs/install_guides/installing-openvino-linux.md index cce38ad353e..e23f9d36df3 100644 --- a/docs/install_guides/installing-openvino-linux.md +++ b/docs/install_guides/installing-openvino-linux.md @@ -218,8 +218,8 @@ Use the `--trusted-host` parameter if the URL above is `http` instead of `https` @endsphinxdirective - Convert models for use with OpenVINO™: [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) - - Write your own OpenVINO™ applications: [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) - - Information on sample applications: [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md) + - Write your own OpenVINO™ applications: [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) + - Information on sample applications: [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md) - Information on a supplied set of models: [Overview of OpenVINO™ Toolkit Pre-Trained Models](../model_zoo.md) - IoT libraries and code samples in the GitHUB repository: [Intel® IoT Developer Kit](https://github.com/intel-iot-devkit) @@ -236,4 +236,4 @@ Use the `--trusted-host` parameter if the URL above is `http` instead of `https` -@endsphinxdirective \ No newline at end of file +@endsphinxdirective diff --git a/docs/install_guides/installing-openvino-macos.md b/docs/install_guides/installing-openvino-macos.md index b4588fff2f7..7a4a1dc062f 100644 --- a/docs/install_guides/installing-openvino-macos.md +++ b/docs/install_guides/installing-openvino-macos.md @@ -9,9 +9,9 @@ By default, the [OpenVINO™ Toolkit](https://docs.openvino.ai/latest/index.html | Component | Description | |-----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | [Model Optimizer](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) | This tool imports, converts, and optimizes models that were trained in popular frameworks to a format usable by Intel tools, especially the Inference Engine.
Popular frameworks include Caffe*, TensorFlow*, MXNet\*, Kaldi\* and ONNX\*. | -| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications | +| [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications | | [OpenCV\*](https://docs.opencv.org/master/) | OpenCV\* community version compiled for Intel® hardware | -| [Inference Engine Code Samples](../IE_DG/Samples_Overview.md) | A set of simple command-line applications demonstrating how to utilize specific OpenVINO capabilities in an application and how to perform specific tasks, such as loading a model, running inference, querying specific device capabilities, and more. | +| [Inference Engine Code Samples](../OV_Runtime_UG/Samples_Overview.md) | A set of simple command-line applications demonstrating how to utilize specific OpenVINO capabilities in an application and how to perform specific tasks, such as loading a model, running inference, querying specific device capabilities, and more. | | [Demo Applications](@ref omz_demos) | A set of command-line applications that serve as robust templates to help you implement multi-stage pipelines and specific deep learning scenarios. | | Additional Tools | A set of tools to work with your models, including [Accuracy Checker utility](@ref omz_tools_accuracy_checker), [Post-Training Optimization Tool](@ref pot_README), [Model Downloader](@ref omz_tools_downloader), and others | | [Documentation for Pre-Trained Models ](@ref omz_models_group_intel) | Documentation for the pre-trained models available in the [Open Model Zoo repo](https://github.com/openvinotoolkit/open_model_zoo). | @@ -198,8 +198,8 @@ To uninstall, follow the steps on the [Uninstalling page](uninstalling-openvino. - Get started with samples and demos: [Get Started Guide](../get_started.md) - Intel® Distribution of OpenVINO™ toolkit home page: [https://software.intel.com/en-us/openvino-toolkit](https://software.intel.com/en-us/openvino-toolkit) - Convert models for use with OpenVINO™: [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) -- Write your own OpenVINO™ applications: [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) -- Information on sample applications: [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md) +- Write your own OpenVINO™ applications: [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) +- Information on sample applications: [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md) - Information on a supplied set of models: [Overview of OpenVINO™ Toolkit Pre-Trained Models](@ref omz_models_group_intel) - IoT libraries and code samples: [Intel® IoT Developer Kit](https://github.com/intel-iot-devkit) diff --git a/docs/install_guides/installing-openvino-pip.md b/docs/install_guides/installing-openvino-pip.md index 78ec6bfd1d4..9b5f427fe88 100644 --- a/docs/install_guides/installing-openvino-pip.md +++ b/docs/install_guides/installing-openvino-pip.md @@ -11,5 +11,5 @@ Intel® Distribution of OpenVINO™ Toolkit provides the following packages avai - [Intel® Distribution of OpenVINO™ toolkit](https://software.intel.com/en-us/openvino-toolkit) - [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) -- [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) -- [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md) +- [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) +- [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md) diff --git a/docs/install_guides/installing-openvino-raspbian.md b/docs/install_guides/installing-openvino-raspbian.md index 64508a75ee6..f29bbf18e4c 100644 --- a/docs/install_guides/installing-openvino-raspbian.md +++ b/docs/install_guides/installing-openvino-raspbian.md @@ -22,9 +22,9 @@ The OpenVINO toolkit for Raspbian OS is an archive with pre-installed header fil | Component | Description | | :-------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications. | +| [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) | This is the engine that runs the deep learning model. It includes a set of libraries for an easy inference integration into your applications. | | [OpenCV\*](https://docs.opencv.org/master/) | OpenCV\* community version compiled for Intel® hardware. | -| [Sample Applications](../IE_DG/Samples_Overview.md) | A set of simple console applications demonstrating how to use Intel's Deep Learning Inference Engine in your applications. | +| [Sample Applications](../OV_Runtime_UG/Samples_Overview.md) | A set of simple console applications demonstrating how to use Intel's Deep Learning Inference Engine in your applications. | > **NOTE**: > * The package does not include the [Model Optimizer](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md). To convert models to Intermediate Representation (IR), you need to install it separately to your host machine. diff --git a/docs/install_guides/installing-openvino-windows.md b/docs/install_guides/installing-openvino-windows.md index 638c88fdcb7..102c2324819 100644 --- a/docs/install_guides/installing-openvino-windows.md +++ b/docs/install_guides/installing-openvino-windows.md @@ -137,8 +137,8 @@ To uninstall the toolkit, follow the steps on the [Uninstalling page](uninstalli @endsphinxdirective - Convert models for use with OpenVINO™: [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) -- Write your own OpenVINO™ applications: [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md) -- Information on sample applications: [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md) +- Write your own OpenVINO™ applications: [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md) +- Information on sample applications: [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md) - Information on a supplied set of models: [Overview of OpenVINO™ Toolkit Pre-Trained Models](../model_zoo.md) - IoT libraries and code samples: [Intel® IoT Developer Kit](https://github.com/intel-iot-devkit) @@ -155,4 +155,4 @@ To learn more about converting models from specific frameworks, go to: -@endsphinxdirective \ No newline at end of file +@endsphinxdirective diff --git a/docs/install_guides/installing-openvino-yum.md b/docs/install_guides/installing-openvino-yum.md index f43533e6816..16dceb9827d 100644 --- a/docs/install_guides/installing-openvino-yum.md +++ b/docs/install_guides/installing-openvino-yum.md @@ -22,7 +22,7 @@ The following components are installed with the OpenVINO runtime package: | Component | Description| |-----------|------------| -| [Inference Engine](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md)| The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications. | +| [Inference Engine](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md)| The engine that runs a deep learning model. It includes a set of libraries for an easy inference integration into your applications. | | [OpenCV*](https://docs.opencv.org/master/) | OpenCV* community version compiled for Intel® hardware. | | Deep Learning Stream (DL Streamer) | Streaming analytics framework, based on GStreamer, for constructing graphs of media analytics components. For the DL Streamer documentation, see [DL Streamer Samples](@ref gst_samples_README), [API Reference](https://openvinotoolkit.github.io/dlstreamer_gst/), [Elements](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/Elements), [Tutorial](https://github.com/openvinotoolkit/dlstreamer_gst/wiki/DL-Streamer-Tutorial). | @@ -138,7 +138,7 @@ sudo yum autoremove intel-openvino-runtime-centos-. - Intel® Distribution of OpenVINO™ toolkit home page: [https://software.intel.com/en-us/openvino-toolkit](https://software.intel.com/en-us/openvino-toolkit) - OpenVINO™ toolkit online documentation: [https://docs.openvino.ai](https://docs.openvino.ai) - [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md). -- [Inference Engine Developer Guide](../IE_DG/Deep_Learning_Inference_Engine_DevGuide.md). -- For more information on Sample Applications, see the [Inference Engine Samples Overview](../IE_DG/Samples_Overview.md). +- [Inference Engine Developer Guide](../OV_Runtime_UG/Deep_Learning_Inference_Engine_DevGuide.md). +- For more information on Sample Applications, see the [Inference Engine Samples Overview](../OV_Runtime_UG/Samples_Overview.md). - For IoT Libraries & Code Samples see the [Intel® IoT Developer Kit](https://github.com/intel-iot-devkit). diff --git a/docs/model_server/README.md b/docs/model_server/README.md index 2fe6c550b0c..6bdd36eae29 100644 --- a/docs/model_server/README.md +++ b/docs/model_server/README.md @@ -18,8 +18,8 @@ Review the [Architecture Concept](https://github.com/openvinotoolkit/model_serve A few key features: - Support for multiple frameworks. Serve models trained in popular formats such as Caffe\*, TensorFlow\*, MXNet\*, and ONNX*. - Deploy new [model versions](https://github.com/openvinotoolkit/model_server/blob/main/docs/docker_container.md#model-version-policy) without changing client code. -- Support for AI accelerators including [Intel Movidius Myriad VPUs](../IE_DG/supported_plugins/VPU.md), -[GPU](../IE_DG/supported_plugins/GPU.md), and [HDDL](../IE_DG/supported_plugins/HDDL.md). +- Support for AI accelerators including [Intel Movidius Myriad VPUs](../OV_Runtime_UG/supported_plugins/VPU.md), +[GPU](../OV_Runtime_UG/supported_plugins/GPU.md), and [HDDL](../OV_Runtime_UG/supported_plugins/HDDL.md). - The server can be enabled both on [Bare Metal Hosts](https://github.com/openvinotoolkit/model_server/blob/main/docs/host.md) or in [Docker* containers](https://github.com/openvinotoolkit/model_server/blob/main/docs/docker_container.md). - [Kubernetes deployments](https://github.com/openvinotoolkit/model_server/blob/main/deploy). The server can be deployed in a Kubernetes cluster allowing the inference service to scale horizontally and ensure high availability. diff --git a/docs/nGraph_DG/build_function.md b/docs/nGraph_DG/build_function.md deleted file mode 100644 index 5f5a232dbff..00000000000 --- a/docs/nGraph_DG/build_function.md +++ /dev/null @@ -1,36 +0,0 @@ -# Build nGraph Function {#openvino_docs_nGraph_DG_build_function} - -This section illustrates how to construct an nGraph function -composed of operations from an available opset. Once created, -it can wrap into a `CNNNetwork`, creating utility for data scientists -or app developers to define a deep-learning model in a neutral way -that does not depend on existing Deep Learning (DL) frameworks. - -Operation Set `opsetX` integrates a list of nGraph pre-compiled operations that work -for this purpose. In other words, `opsetX` defines a set of operations for building a graph. - -For a complete list of operation sets supported by Inference Engine, see [Available Operations Sets](../ops/opset.md). - -To add custom nGraph operations to an existing `CNNNetwork`, see -the [Add Custom nGraph Operations](../IE_DG/Extensibility_DG/Intro.md) document. - -Below you can find examples on to how build `ngraph::Function` from the `opset3` operations: - -@snippet example_ngraph_utils.cpp ngraph:include - -@snippet example_ngraph_utils.cpp ngraph_utils:simple_function - -@snippet example_ngraph_utils.cpp ngraph_utils:advanced_function - -To wrap it into a CNNNetwork, use: -```cpp -CNNNetwork net (ng_function); -``` -## See Also - -* [Available Operation Sets](../ops/opset.md) -* [Operation Set `opset1` Specification](../ops/opset1.md) -* [Operation Set `opset2` Specification](../ops/opset2.md) -* [Operation Set `opset3` Specification](../ops/opset3.md) -* [Operation Set `opset4` Specification](../ops/opset4.md) -* [Inference Engine Extensibility Developer Guide](../IE_DG/Extensibility_DG/Intro.md) diff --git a/docs/nGraph_DG/intro.md b/docs/nGraph_DG/intro.md deleted file mode 100644 index f096321ef5d..00000000000 --- a/docs/nGraph_DG/intro.md +++ /dev/null @@ -1,46 +0,0 @@ -# Introduction to the nGraph {#openvino_docs_nGraph_DG_Introduction} - -The Inference Engine integrates the nGraph to represent a model in run time underneath of the conventional -`CNNNetwork` API, which is an instance of `ngraph::Function`. - -Besides the representation update, nGraph supports new features: - -1. nGraph contains several [sets of operations which are called `opset1`, `opset2` and etc.](../ops/opset.md). -Operations from these operation sets are generated by the Model Optimizer and are accepted in the Inference Engine. - -2. Operation version is attached to each operation rather than to the entire IR file format. -IR is still versioned but has a different meaning. For details, see [Deep Learning Network Intermediate Representation and Operation Sets in OpenVINO™](../MO_DG/IR_and_opsets.md). - -3. Creating models at runtime without loading IR from an xml/binary file. You can enable it by creating -`ngraph::Function` passing it to `CNNNetwork`. - -4. Runtime reshape capability and constant folding are implemented through the nGraph code for more operations compared to previous releases. -As a result, more models can be reshaped. For details, see the [dedicated guide about the reshape capability](../IE_DG/ShapeInference.md). - -5. Loading [model from ONNX format](../IE_DG/ONNX_Support.md) without converting it to the Inference Engine IR. - -6. nGraph representation supports dynamic shapes. You can use `CNNNetwork::reshape()` method in order to specialize input shapes. - -A complete picture of the existing flow is shown below. - -![](img/TopLevelNGraphFlow.png) - -## Read the Intermediate Representation to `CNNNetwork` - -The IR version 10 automatically triggers the nGraph flow inside the Inference Engine. -When such IR is read in an application, the Inference Engine IR reader produces `CNNNetwork` that encapsulates the `ngraph::Function` instance underneath. - -Interpretation of the IR version 10 differs from the old IR version. -Besides having a different operations set, the IR version 10 ignores the shapes and data types assigned to the ports in an XML file. -Both shapes and types are reinferred while loading to the Inference Engine using the nGraph shape and type propagation function that is a part of each nGraph operation. - -## Build a Model in the Application - -Alternative method to feed the Inference Engine with a model is to create the model in the run time. -It is achieved by creation of the `ngraph::Function` construction using nGraph operation classes and optionally user-defined operations. -For details, see [Add Custom nGraph Operations](../IE_DG/Extensibility_DG/AddingNGraphOps.md) and [examples](build_function.md). -At this stage, the code is completely independent of the rest of the Inference Engine code and can be built separately. -After you construct an instance of `ngraph::Function`, you can use it to create `CNNNetwork` by passing it to the new constructor for this class. - -## See Also -- [Available Operations Sets](../ops/opset.md) diff --git a/docs/nGraph_DG/nGraph_Python_API.md b/docs/nGraph_DG/nGraph_Python_API.md deleted file mode 100644 index da6357b6bd8..00000000000 --- a/docs/nGraph_DG/nGraph_Python_API.md +++ /dev/null @@ -1,222 +0,0 @@ -# Using nGraph's Python API {#openvino_docs_nGraph_DG_PythonAPI} - -nGraph is the OpenVINO™ graph manipulation library, used to represent neural network models in the form of a computational graph. With nGraph Python APIs, you can create, inspect, and modify computational graphs. - -## nGraph namespace module - -nGraph is able to represent a large set of mathematical operations, chosen to cover most operations used in popular neural network models. The `ngraph` module is the basic namespace used to expose commonly used API methods. You can inspect the `ngraph` module or call `help` on any method for usage information. - -```python -import ngraph as ng -dir(ng) -help(ng.space_to_batch) -``` - -## Create a simple graph - -You can use nGraph's Python API to create computational models. For example, to create a model that represents the formula `y=ReLU(x + b)`, you can use the following code to create parameters `x` and `b` and create the computational graph: - - -```python -import numpy as np -import ngraph as ng - -parameter_x = ng.parameter(shape=[2, 2], dtype=np.float32, name="x") -parameter_b = ng.parameter(shape=[2, 2], dtype=np.float32, name="b") - -graph = ng.relu(parameter_x + parameter_b, name="y") -``` - -nGraph operations are organized into sets, which are released with new versions of OpenVINO. As operation signatures can change between operation sets, it is a good practice to use operations from a specific operation set in your scripts. This ensures that your code is compatible with future versions of OpenVINO. - -The example, the code above can be rewritten like this to use only operations from opset 4: - -```python -import ngraph.opset4 as ops - -parameter_x = ops.parameter(shape=[2, 2], dtype=np.float32, name="x") -parameter_b = ops.parameter(shape=[2, 2], dtype=np.float32, name="b") - -graph = ops.relu(parameter_x + parameter_b, name="y") -``` - - -## Create an nGraph function from a graph - -You can combine a graph together with its input parameters into an nGraph function object. An nGraph function can be passed to other parts of OpenVINO to perform analysis and inference. - -```python ->>> function = ng.Function(graph, [parameter_x, parameter_b], "TestFunction") - -``` - -## Run inference - -In order to run inference on an nGraph function, convert it to an Inference Engine network and call its `infer` method. - -```python ->>> from openvino.inference_engine import IECore ->>> ->>> ie_network = ng.function_to_cnn(function) ->>> ->>> ie = IECore() ->>> executable_network = ie.load_network(ie_network, 'CPU') ->>> ->>> output = executable_network.infer({ ->>> 'x': np.array([[-1, 0], [1, 2]]), ->>> 'b': np.array([[-1, 0], [0, 1]]), ->>> }) ->>> output['y'] -array([[-0., 0.], - [ 1., 3.]], dtype=float32) -``` - -## Load an nGraph function from a file - -You can load a model from a file using the Inference Engine `read_network` method: - - network = ie_core.read_network(model=model_path, weights=weights_path) - -An nGraph function can be extracted from an Inference Engine network using the `ngraph.function_from_cnn` method. -The following example shows how an ONNX model can be loaded to an nGraph Function: - -```python -from openvino.inference_engine import IECore -ie = IECore() - -model_path='/path/to/model.onnx' -network = ie.read_network(model=model_path) - -import ngraph as ng -function = ng.function_from_cnn(network) -``` - - -## Inspect an nGraph function - -You can use the nGraph function's `get_ordered_ops` method to get a topologically sorted list of its graph `Node`s. - -```python ->>> function.get_ordered_ops() -[, - , - , - , - ] -``` - -Each `Node` has a unique `name` property, assigned at creation time. User-provided names can be retrieved using the `get_friendly_name` method. `get_type_name` returns the operation type of the node and the `shape` property returns the shape of the node's output tensor. - -```python ->>> for node in function.get_ordered_ops(): ->>> print('Node name: {:15} Friendly name: {:10} Op: {:10} {}'.format( ->>> node.name, node.get_friendly_name(), node.get_type_name(), node.shape)) -Node name: Parameter_1 Friendly name: b Op: Parameter Shape{2, 2} -Node name: Parameter_0 Friendly name: x Op: Parameter Shape{2, 2} -Node name: Add_2 Friendly name: Add_2 Op: Add Shape{2, 2} -Node name: Relu_3 Friendly name: y Op: Relu Shape{2, 2} -Node name: Result_4 Friendly name: Result_4 Op: Result Shape{2, 2} -``` - -### Node relationships - -`Node`'s parents can be retrieved using the `inputs()` method, which returns `Input` objects. Each `Input` is a connection to an upstream `Output`, which is connected to a `Node`. The upstream node can be retrieved using `input.get_source_output().get_node()` methods. - -```python ->>> for node_input in node.inputs(): ->>> parent = node_input.get_source_output().get_node() ->>> print('{} node has parent {}'.format(node.get_friendly_name(), parent.get_friendly_name())) -Add_2 node has parent x -Add_2 node has parent b -``` - -By analogy, `Node`'s children can be retrieved using the `outputs()` method, which returns a list of `Output` objects. By contrast to inputs, each output can be connected to multiple downstream nodes. - -```python ->>> for node_output in node.outputs(): ->>> children = [target.get_node() for target in node_output.get_target_inputs()] ->>> print('{} node has children {}'.format(node.get_friendly_name(), ','.join([c.get_friendly_name() for c in children]))) ->>> -Add_2 node has children y -``` - -### Shapes - -Each `Input` and `Output` has an associated tensor shape, which describes what data it can accept or produce. Shapes can be dynamic, which means that they are only partially known. You can get information about this shape by calling the `get_partial_shape` method. If the returned `PartialShape` object's `is_dynamic` property returns `True`, then the shape is known partially. Otherwise, you can convert the shape to a fully known static shape (list of integers). - -```python -partial_shape = node_input.get_partial_shape() -if partial_shape.is_dynamic: - print('{} node has a dynamic shape {}'.format(node.get_friendly_name(), partial_shape)) -else: - shape = list(partial_shape.to_shape()) - print('{} node has a static shape {}'.format(node.get_friendly_name(), shape)) -``` - -### Node attributes - -Nodes may also have additional attributes. For example, a `Softmax` node has an `axis` attribute. Each attribute may be retrieved using a dedicated method, for example, `node.get_axis()`. - -```python ->>> node = ng.softmax(data=[[1, 2], [3, 4]], axis=1) ->>> node.get_axis() -1 -``` - -You can also set attribute values using corresponding setter methods, for example: - -```python -node.set_axis(0) -``` - -Currently, you can get all attributes of a node using the `get_attributes` method. - -The following code displays all attributes for all nodes in a function: - -```python -for node in function.get_ordered_ops(): - attributes = node.get_attributes() - if(attributes): - print('Operation {} of type {} has attributes:'.format(node.get_friendly_name(), node.get_type_name())) - for attr, value in attributes.items(): - print(" * {}: {}".format(attr, value)) - else: - print('Operation {} of type {} has no attributes.'.format(node.get_friendly_name(), node.get_type_name())) -``` - -### Node runtime information - -Attributes are properties of nodes in the computational graph, which will be stored when the model is serialized to a file. However, there can be additional properties of nodes, which are only important during the execution of a graph. An example of such a property is `affinity`, which determines which operation will be executed on which hardware in a heterogeneous environment. You can get and set runtime information by using the `get_rt_info` method of a node. - -> **NOTE**: If you set affinity manually, be careful at the current moment Inference Engine plugins don't support constant (`Constant`->`Result`) and empty (`Parameter`->`Result`) networks. Please avoid such subgraphs when you set affinity manually. - -```python -rt_info = node.get_rt_info() -rt_info["affinity"] = "test_affinity" -``` - -Please note that the `rt_info` API may change in future versions of OpenVINO. - -### Data of Constant nodes - -You can retrieve the data tensor associated with a `Constant` node by calling its `get_data` method: - -```python -if node.get_type_name() == 'Constant': - data = node.get_data() -``` - -## Transform graphs - -nGraph supports a growing number of transformation passes, which can be applied to a graph. For example, to perform constant folding of applicable subgraphs, you can use the `ConstantFolding` pass. To do this, create an optimization pass `Manager`, register the passes you want to execute, and feed an nGraph function to the configured pass manager. - -The following code example illustrates the process: - -```python -from ngraph.impl.passes import Manager -pass_manager = Manager() -pass_manager.register_pass('ConstantFolding') -pass_manager.run_passes(function) -``` - -Please note that the list of available transformations may change in future versions of OpenVINO. diff --git a/docs/nGraph_DG/nGraph_basic_concepts.md b/docs/nGraph_DG/nGraph_basic_concepts.md deleted file mode 100644 index 4648c2613eb..00000000000 --- a/docs/nGraph_DG/nGraph_basic_concepts.md +++ /dev/null @@ -1,39 +0,0 @@ -# nGraph Basic Concepts {#openvino_docs_nGraph_DG_basic_concepts} - -The nGraph represents neural networks in uniform format. User can create different operations and combined their to one `ngraph::Function`. - -## nGraph Function and Graph Representation - -nGraph function is a very simple thing: it stores shared pointers to `ngraph::op::Parameter`, `ngraph::op::Result` and `ngraph::op::Sink` operations that are inputs, outputs and sinks of the graph. -Sinks of the graph have no consumers and are not included in the results vector. All other operations hold each other via shared pointers: child operation holds its parent (hard link). If operation has no consumers and it's not Result or Sink operation -(shared pointer counter is zero) then it will be destructed and won't be accessible anymore. Each operation in `ngraph::Function` has a `std::shared_ptr` type. - -For details on how to build an nGraph Function, see the [Build nGraph Function](./build_function.md) page. - -## Operations - -`ngraph::Op` represents any abstract operations in the nGraph representation. You need to use this class to create [custom operations](../IE_DG/Extensibility_DG/AddingNGraphOps.md). - -## Operation Sets - -Operation set represents the set of some nGraph operations. `nGraph::Opset` is a class which provide a functionality to work with operation sets. -Custom operation set should be created to support custom operation. Please read [Extensibility DevGuide](../IE_DG/Extensibility_DG/Intro.md) for more details. - -## Static and Partial Shapes - -nGraph has two types for shape representation: - -* `ngraph::Shape` - Represents static (fully defined) shapes. - -* `ngraph::PartialShape` - Represents dynamic shapes. That means that the rank or some of dimensions are dynamic (undefined). `ngraph::PartialShape` can be converted to `ngraph::Shape` using the `get_shape()` method if all dimensions are static; otherwise the conversion raises an exception. - -For examples, see the Dynamic Shape and Rank section in the [Overview of Transformations API](./nGraphTransformation.md). - - -## Transformation API - -nGraph transformation API allows you to manipulate the graph represented by `nGraph::Function`. For more details, see the [Overview of Transformations API](./nGraphTransformation.md) section. - -## Pattern Matcher - -For more details, see the Pattern Matching section in the [Overview of Transformations API](./nGraphTransformation.md). diff --git a/docs/nGraph_DG/nGraph_debug_capabilities.md b/docs/nGraph_DG/nGraph_debug_capabilities.md deleted file mode 100644 index 2c49e1f4b54..00000000000 --- a/docs/nGraph_DG/nGraph_debug_capabilities.md +++ /dev/null @@ -1,18 +0,0 @@ -# nGraph Debug Capabilities {#openvino_docs_nGraph_DG_Debug_capabilities} - -nGraph representation provides an API to get detailed information about the graph structure. - -To receive additional messages about applied graph modifications, rebuild the nGraph library with -the `-DENABLE_OPENVINO_DEBUG=ON` option. - -To visualize the nGraph function to the xDot format or to an image file, use the -`ngraph::pass::VisualizeTree` graph transformation pass: -```cpp -#include - -std::shared_ptr nGraph; -... -ngraph::pass::VisualizeTree("after.png").run_on_function(nGraph); // Visualize the nGraph function to an image -``` - -> **NOTE**: Graphviz is required for visualization to image. diff --git a/docs/nGraph_DG/nGraph_dg.md b/docs/nGraph_DG/nGraph_dg.md deleted file mode 100644 index c4aa4a9db5b..00000000000 --- a/docs/nGraph_DG/nGraph_dg.md +++ /dev/null @@ -1,16 +0,0 @@ -# nGraph Developer Guide {#openvino_docs_nGraph_DG_DevGuide} - -@sphinxdirective - -.. toctree:: - :maxdepth: 1 - - openvino_docs_nGraph_DG_Introduction - openvino_docs_nGraph_DG_basic_concepts - openvino_docs_MO_DG_IR_and_opsets - openvino_docs_nGraph_DG_build_function - openvino_docs_nGraph_DG_Debug_capabilities - ngraph_transformation - openvino_docs_nGraph_DG_PythonAPI - -@endsphinxdirective \ No newline at end of file diff --git a/docs/ops/opset8.md b/docs/ops/opset8.md index d20b2a46ae7..a6274cdf968 100644 --- a/docs/ops/opset8.md +++ b/docs/ops/opset8.md @@ -1,4 +1,4 @@ -# Operation Set `opset8` Specification {#openvino_docs_ops_opset8} +# opset8 {#openvino_docs_ops_opset8} This specification document describes the `opset8` operation set supported in OpenVINO™. Support for each particular operation from the list below depends on the capabilities of an inference plugin diff --git a/docs/optimization_guide/dldt_deployment_optimization_guide.md b/docs/optimization_guide/dldt_deployment_optimization_guide.md index 1fd27f17287..4293b3b4140 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_guide.md +++ b/docs/optimization_guide/dldt_deployment_optimization_guide.md @@ -92,7 +92,7 @@ More importantly, an infer request encapsulates the reference to the “executab If your application simultaneously executes multiple infer requests: - For the CPU, the best solution, you can use the CPU "throughput" mode. -- If latency is of more concern, you can try the `EXCLUSIVE_ASYNC_REQUESTS` [configuration option](../IE_DG/supported_plugins/CPU.md) that limits the number of the simultaneously executed requests for all (executable) networks that share the specific device to just one: +- If latency is of more concern, you can try the `EXCLUSIVE_ASYNC_REQUESTS` [configuration option](../OV_Runtime_UG/supported_plugins/CPU.md) that limits the number of the simultaneously executed requests for all (executable) networks that share the specific device to just one: @snippet snippets/dldt_optimization_guide7.cpp part7 @@ -113,14 +113,14 @@ In the Inference Engine, there is no notion of requests priorities. It is left t Inference precision directly affects the performance. Model Optimizer can produce an IR with different precision. For example, an FP16 IR initially targets VPU and GPU devices, while, for example, for the CPU, an FP16 IR is typically up-scaled to the regular FP32 automatically upon loading. But notice that further device-specific inference precision settings are available, -for example, [8-bit integer](../IE_DG/Int8Inference.md) or [bfloat16](../IE_DG/Bfloat16Inference.md), which is specific to the CPU inference, below. -Note that for the [MULTI device](../IE_DG/supported_plugins/MULTI.md) plugin that supports automatic inference on multiple devices in parallel, you can use an FP16 IR (no need for FP32). +for example, [8-bit integer](../OV_Runtime_UG/Int8Inference.md) or [bfloat16](../OV_Runtime_UG/Bfloat16Inference.md), which is specific to the CPU inference, below. +Note that for the [MULTI device](../OV_Runtime_UG/supported_plugins/MULTI.md) plugin that supports automatic inference on multiple devices in parallel, you can use an FP16 IR (no need for FP32). You can find more information, including preferred data types for specific devices, in the -[Supported Devices](../IE_DG/supported_plugins/Supported_Devices.md) document. +[Supported Devices](../OV_Runtime_UG/supported_plugins/Supported_Devices.md) document. By default, plugins enable the optimizations that allow lower precision if the acceptable range of accuracy is preserved. -For example, for the CPU that supports the AVX512_BF16 instructions, an FP16/FP32 model is converted to a [bfloat16](../IE_DG/Bfloat16Inference.md) IR to accelerate inference. +For example, for the CPU that supports the AVX512_BF16 instructions, an FP16/FP32 model is converted to a [bfloat16](../OV_Runtime_UG/Bfloat16Inference.md) IR to accelerate inference. To compare the associated speedup, run the example command below to disable this feature on the CPU device with the AVX512_BF16 support and get regular FP32 execution: @@ -129,10 +129,10 @@ $ benchmark_app -m -enforcebf16=false ``` Notice that for quantized (e.g. INT8) models the bfloat16 calculations (of the layers that remain in FP32) is disabled by default. -Refer to the [CPU Plugin documentation](../IE_DG/supported_plugins/CPU.md) for more details. +Refer to the [CPU Plugin documentation](../OV_Runtime_UG/supported_plugins/CPU.md) for more details. Similarly, the GPU device automatically executes FP16 for the layers that remain in FP16 in the quantized models (assuming that the FP16 model was quantized). -Refer to the ENABLE_FP16_FOR_QUANTIZED_MODELS key in the [GPU Plugin documentation](../IE_DG/supported_plugins/GPU.md). +Refer to the ENABLE_FP16_FOR_QUANTIZED_MODELS key in the [GPU Plugin documentation](../OV_Runtime_UG/supported_plugins/GPU.md). ## Device Optimizations @@ -142,20 +142,20 @@ The Inference Engine supports several target devices (CPU, GPU, Intel® Movid CPU plugin completely relies on the Intel® Math Kernel Library for Deep Neural Networks (Intel® MKL-DNN) for major primitives acceleration, for example, Convolutions or FullyConnected. -The only hint you can get from that is how the major primitives are accelerated (and you cannot change this). For example, on the Core machines, you should see variations of the `jit_avx2` when inspecting the internal inference performance counters (and additional '_int8' postfix for [int8 inference](../IE_DG/Int8Inference.md)). If you are an advanced user, you can further trace the CPU execution with (see Intel® VTune™). +The only hint you can get from that is how the major primitives are accelerated (and you cannot change this). For example, on the Core machines, you should see variations of the `jit_avx2` when inspecting the internal inference performance counters (and additional '_int8' postfix for [int8 inference](../OV_Runtime_UG/Int8Inference.md)). If you are an advanced user, you can further trace the CPU execution with (see Intel® VTune™). Internally, the Inference Engine has a threading abstraction level, which allows for compiling the [open source version](https://github.com/opencv/dldt) with either Intel® Threading Building Blocks (Intel® TBB) which is now default, or OpenMP* as an alternative parallelism solution. When using inference on the CPU, this is particularly important to align threading model with the rest of your application (and any third-party libraries that you use) to avoid oversubscription. For more information, see Note on the App-Level Threading section. Since R1 2019, the OpenVINO™ toolkit comes pre-compiled with Intel TBB, so any OpenMP* API or environment settings (like `OMP_NUM_THREADS`) has no effect. - Certain tweaks (like number of threads used for inference on the CPU) are still possible via [CPU configuration options](../IE_DG/supported_plugins/CPU.md). + Certain tweaks (like number of threads used for inference on the CPU) are still possible via [CPU configuration options](../OV_Runtime_UG/supported_plugins/CPU.md). Finally, the OpenVINO CPU inference is NUMA-aware, please refer to the Tips for inference on NUMA systems section. Other general recommendations: - Usually, batching improves CPU performance. However, the need to gather frames in the batch might complicate the application logic. Instead, you can keep a separate infer request per camera or other source of input and process the requests in parallel. For more information, see the next section. - If your application simultaneously performs inference of multiple models on the same CPU, make sure you do not oversubscribe the machine. See Performance Aspects of Running Multiple Requests Simultaneously for more information. - Notice that the heterogeneous execution might implicitly load the CPU. For details, refer to the Heterogeneity section. -- Consider [8-bit integer inference on the CPU](../IE_DG/Int8Inference.md). +- Consider [8-bit integer inference on the CPU](../OV_Runtime_UG/Int8Inference.md). #### Throughput Mode for CPU Unlike most accelerators, CPU is perceived as an inherently latency-oriented device. @@ -174,7 +174,7 @@ For example, on an 8-core CPU, compare the `-nstreams 1` (which is a legacy, lat In addition, you can play with the batch size to find the throughput sweet spot. If your application is hard or impossible to change in accordance with the multiple-requests logic, consider the "multiple-instance" trick to improve the throughput: -- For multi-socket execution, it is recommended to set [`KEY_CPU_THREADS_NUM`](../IE_DG/supported_plugins/CPU.md) to the number of cores per socket, and run as many instances of the application as you have sockets. +- For multi-socket execution, it is recommended to set [`KEY_CPU_THREADS_NUM`](../OV_Runtime_UG/supported_plugins/CPU.md) to the number of cores per socket, and run as many instances of the application as you have sockets. - Similarly, for extremely lightweight networks (running faster than 1ms) and/or many-core machines (16+ cores), try limiting the number of CPU inference threads to just `#‍phys` cores and further, while trying to saturate the machine with running multiple instances of the application. ### GPU Checklist @@ -184,11 +184,11 @@ Inference Engine relies on the [Compute Library for Deep Neural Networks (clDNN) - Prefer `FP16` over `FP32`, as the Model Optimizer can generate both variants and the `FP32` is default. - Try to group individual infer jobs by using batches. - Notice that using the GPU introduces one-time overhead (order of few seconds) of compiling the OpenCL kernels. The compilation happens upon loading the network to the GPU plugin and does not affect the inference time. -- If your application is simultaneously using the inference on the CPU or otherwise loads the host heavily, make sure that the OpenCL driver threads do not starve. You can use [CPU configuration options](../IE_DG/supported_plugins/CPU.md) to limit number of inference threads for the CPU plugin. +- If your application is simultaneously using the inference on the CPU or otherwise loads the host heavily, make sure that the OpenCL driver threads do not starve. You can use [CPU configuration options](../OV_Runtime_UG/supported_plugins/CPU.md) to limit number of inference threads for the CPU plugin. - In the GPU-only scenario, a GPU driver might occupy a CPU core with spin-looped polling for completion. If the _CPU_ utilization is a concern, consider the `KEY_CLDND_PLUGIN_THROTTLE` configuration option. > **NOTE**: See the [Benchmark App Sample](../../samples/cpp/benchmark_app/README.md) code for a usage example. -Notice that while disabling the polling, this option might reduce the GPU performance, so usually this option is used with multiple [GPU streams](../IE_DG/supported_plugins/GPU.md). +Notice that while disabling the polling, this option might reduce the GPU performance, so usually this option is used with multiple [GPU streams](../OV_Runtime_UG/supported_plugins/GPU.md). ### Intel® Movidius™ Myriad™ X Visual Processing Unit and Intel® Vision Accelerator Design with Intel® Movidius™ VPUs @@ -199,7 +199,7 @@ Intel® Vision Accelerator Design with Intel® Movidius™ VPUs requir ## Heterogeneity -Heterogeneous execution (constituted by the dedicated Inference Engine [“Hetero” plugin](../IE_DG/supported_plugins/HETERO.md)) enables to schedule a network inference to the multiple devices. +Heterogeneous execution (constituted by the dedicated Inference Engine [“Hetero” plugin](../OV_Runtime_UG/supported_plugins/HETERO.md)) enables to schedule a network inference to the multiple devices. ### Typical Heterogeneous Scenarios of Concern @@ -231,7 +231,7 @@ Similarly, if there are too much subgraphs, the synchronization and data transfe The general affinity “rule of thumb” is to keep computationally-intensive kernels on the accelerator, and "glue" or helper kernels on the CPU. Notice that this includes the granularity considerations. For example, running some custom activation (that comes after every accelerator-equipped convolution) on the CPU might result in performance degradation due to too much data type and/or layout conversions, even though the activation itself can be extremely fast. In this case, it might make sense to consider implementing the kernel for the accelerator (see Optimizing Custom Kernels). The conversions typically manifest themselves as outstanding (comparing to CPU-only execution) 'Reorder' entries (see Internal Inference Performance Counters). -For general details on the heterogeneous plugin, refer to the [corresponding section in the Inference Engine Developer Guide](../IE_DG/supported_plugins/HETERO.md). +For general details on the heterogeneous plugin, refer to the [corresponding section in the Inference Engine Developer Guide](../OV_Runtime_UG/supported_plugins/HETERO.md). ### Trying the Heterogeneous Plugin with Inference Engine Samples @@ -270,7 +270,7 @@ The following tips are provided to give general guidance on optimizing execution ### Analyzing Heterogeneous Execution -There is a dedicated configuration option that enables dumping the visualization of the subgraphs created by the heterogeneous plugin, please see code example in the [HETERO plugin documentation](../IE_DG/supported_plugins/HETERO.md) +There is a dedicated configuration option that enables dumping the visualization of the subgraphs created by the heterogeneous plugin, please see code example in the [HETERO plugin documentation](../OV_Runtime_UG/supported_plugins/HETERO.md) After enabling the configuration key, the heterogeneous plugin generates two files: @@ -279,10 +279,10 @@ After enabling the configuration key, the heterogeneous plugin generates two fil You can use GraphViz\* utility or `.dot` converters (for example, to `.png` or `.pdf`), like xdot\*, available on Linux\* OS with `sudo apt-get install xdot`. -You can also use performance data (in the [Benchmark App](../../samples/cpp/benchmark_app/README.md), it is an option `-pc`) to get performance data on each subgraph. Again, refer to the [HETERO plugin documentation](../IE_DG/supported_plugins/HETERO.md) and to Internal Inference Performance Counters for a general counters information. +You can also use performance data (in the [Benchmark App](../../samples/cpp/benchmark_app/README.md), it is an option `-pc`) to get performance data on each subgraph. Again, refer to the [HETERO plugin documentation](../OV_Runtime_UG/supported_plugins/HETERO.md) and to Internal Inference Performance Counters for a general counters information. ## Multi-Device Execution -OpenVINO™ toolkit supports automatic multi-device execution, please see [MULTI-Device plugin description](../IE_DG/supported_plugins/MULTI.md). +OpenVINO™ toolkit supports automatic multi-device execution, please see [MULTI-Device plugin description](../OV_Runtime_UG/supported_plugins/MULTI.md). In the next chapter you can find the device-specific tips, while this section covers few recommendations for the multi-device execution: - MULTI usually performs best when the fastest device is specified first in the list of the devices. diff --git a/docs/optimization_guide/dldt_deployment_optimization_guide_additional.md b/docs/optimization_guide/dldt_deployment_optimization_guide_additional.md index adb38297f8a..9f685e57468 100644 --- a/docs/optimization_guide/dldt_deployment_optimization_guide_additional.md +++ b/docs/optimization_guide/dldt_deployment_optimization_guide_additional.md @@ -26,14 +26,14 @@ usually gives the same best latency as a single request on the single socket, bu $ benchmark_app -m -nstreams 2 ``` Number of NUMA nodes on the machine can be queried via 'lscpu'. -Please see more on the NUMA support in the [Optimization Guide](../IE_DG/supported_plugins/MULTI.md). +Please see more on the NUMA support in the [Optimization Guide](../OV_Runtime_UG/supported_plugins/MULTI.md). ## Threading - As explained in the CPU Checklist section, by default the Inference Engine uses Intel TBB as a parallel engine. Thus, any OpenVINO-internal threading (including CPU inference) uses the same threads pool, provided by the TBB. But there are also other threads in your application, so oversubscription is possible at the application level: - The rule of thumb is that you should try to have the overall number of active threads in your application equal to the number of cores in your machine. Keep in mind the spare core(s) that the OpenCL driver under the GPU plugin might also need. -- One specific workaround to limit the number of threads for the Inference Engine is using the [CPU configuration options](../IE_DG/supported_plugins/CPU.md). +- One specific workaround to limit the number of threads for the Inference Engine is using the [CPU configuration options](../OV_Runtime_UG/supported_plugins/CPU.md). - To avoid further oversubscription, use the same threading model in all modules/libraries that your application uses. Notice that third party components might bring their own threading. For example, using Inference Engine which is now compiled with the TBB by default might lead to [performance troubles](https://www.threadingbuildingblocks.org/docs/help/reference/appendices/known_issues/interoperability.html) when mixed in the same app with another computationally-intensive library, but compiled with OpenMP. You can try to compile the [open source version](https://github.com/opencv/dldt) of the Inference Engine to use the OpenMP as well. But notice that in general, the TBB offers much better composability, than other threading solutions. - If your code (or third party libraries) uses GNU OpenMP, the Intel® OpenMP (if you have recompiled Inference Engine with that) must be initialized first. This can be achieved by linking your application with the Intel OpenMP instead of GNU OpenMP, or using `LD_PRELOAD` on Linux* OS. @@ -67,4 +67,4 @@ Again, if the OpenCV and Inference Engine layouts match, the data can be wrapped Notice that original `cv::Mat`/blobs cannot be used simultaneously by the application and the Inference Engine. Alternatively, the data that the pointer references to can be copied to unlock the original data and return ownership to the original API. -To learn more about optimizations during developing step, visit [Deployment Optimization Guide](dldt_deployment_optimization_guide.md) page. \ No newline at end of file +To learn more about optimizations during developing step, visit [Deployment Optimization Guide](dldt_deployment_optimization_guide.md) page. diff --git a/docs/resources.md b/docs/resources.md index 77d805f663c..aebbd191fa1 100644 --- a/docs/resources.md +++ b/docs/resources.md @@ -39,7 +39,7 @@ This section includes a variety of reference information in three broad categori ### Additional Resources [Release Notes](https://software.intel.com/content/www/us/en/develop/articles/openvino-relnotes.html) contains change logs and notes for each OpenVINO release. -[Supported Devices](IE_DG/supported_plugins/Supported_Devices.md) is compatibility information about supported hardware accelerators. +[Supported Devices](OV_Runtime_UG/supported_plugins/Supported_Devices.md) is compatibility information about supported hardware accelerators. [Legal Information](Legal_Information.md) has trademark information and other legal statements. @@ -48,7 +48,7 @@ This section includes a variety of reference information in three broad categori [Broadcast Rules for Elementwise Operations](ops/broadcast_rules.md) explains the rules used for to support an arbitrary number of dimensions in neural nets. -[Operation Specifications](IE_DG/Operations_specifications.md) is a detailed reference of supported operations. +[Operation Specifications](OV_Runtime_UG/Operations_specifications.md) is a detailed reference of supported operations. ### Case Studies Links to [articles](https://www.intel.com/openvino-success-stories) about real-world examples of OpenVINO™ usage. diff --git a/docs/snippets/example_ngraph_utils.cpp b/docs/snippets/example_ngraph_utils.cpp index 380f7421f2e..c6d32373551 100644 --- a/docs/snippets/example_ngraph_utils.cpp +++ b/docs/snippets/example_ngraph_utils.cpp @@ -4,87 +4,90 @@ #include -#include +#include +#include +#include +#include +#include #include #include #include #include #include -// ! [ngraph:include] -#include -#include -// ! [ngraph:include] +// ! [ov:include] +#include +#include +// ! [ov:include] -using namespace ngraph; -// ! [ngraph_utils:simple_function] -std::shared_ptr create_simple_function() { - // This example shows how to create ngraph::Function +// ! [ov:create_simple_model] +std::shared_ptr create_simple_function() { + // This example shows how to create ov::Function // // Parameter--->Multiply--->Add--->Result // Constant---' / // Constant---' - // Create opset3::Parameter operation with static shape - auto data = std::make_shared(ngraph::element::f32, ngraph::Shape{3, 1, 2}); + // Create opset8::Parameter operation with static shape + auto data = std::make_shared(ov::element::f32, ov::Shape{3, 1, 2}); - auto mul_constant = ngraph::opset3::Constant::create(ngraph::element::f32, ngraph::Shape{1}, {1.5}); - auto mul = std::make_shared(data, mul_constant); + auto mul_constant = ov::opset8::Constant::create(ov::element::f32, ov::Shape{1}, {1.5}); + auto mul = std::make_shared(data, mul_constant); - auto add_constant = ngraph::opset3::Constant::create(ngraph::element::f32, ngraph::Shape{1}, {0.5}); - auto add = std::make_shared(mul, add_constant); + auto add_constant = ov::opset8::Constant::create(ov::element::f32, ov::Shape{1}, {0.5}); + auto add = std::make_shared(mul, add_constant); - // Create opset3::Result operation - auto res = std::make_shared(mul); + // Create opset8::Result operation + auto res = std::make_shared(mul); // Create nGraph function - return std::make_shared(ngraph::ResultVector{res}, ngraph::ParameterVector{data}); + return std::make_shared(ov::ResultVector{res}, ov::ParameterVector{data}); } -// ! [ngraph_utils:simple_function] +// ! [ov:create_simple_model] -// ! [ngraph_utils:advanced_function] -std::shared_ptr create_advanced_function() { +// ! [ov:create_advanced_model] +std::shared_ptr create_advanced_function() { // Advanced example with multi output operation // // Parameter->Split---0-->Result // | `--1-->Relu-->Result // `----2-->Result - auto data = std::make_shared(ngraph::element::f32, ngraph::Shape{1, 3, 64, 64}); + auto data = std::make_shared(ov::element::f32, ov::Shape{1, 3, 64, 64}); // Create Constant for axis value - auto axis_const = ngraph::opset3::Constant::create(ngraph::element::i64, ngraph::Shape{}/*scalar shape*/, {1}); + auto axis_const = ov::opset8::Constant::create(ov::element::i64, ov::Shape{}/*scalar shape*/, {1}); - // Create opset3::Split operation that splits input to three slices across 1st dimension - auto split = std::make_shared(data, axis_const, 3); + // Create opset8::Split operation that splits input to three slices across 1st dimension + auto split = std::make_shared(data, axis_const, 3); - // Create opset3::Relu operation that takes 1st Split output as input - auto relu = std::make_shared(split->output(1)/*specify explicit output*/); + // Create opset8::Relu operation that takes 1st Split output as input + auto relu = std::make_shared(split->output(1)/*specify explicit output*/); // Results operations will be created automatically based on provided OutputVector - return std::make_shared(ngraph::OutputVector{split->output(0), relu, split->output(2)}, ngraph::ParameterVector{data}); + return std::make_shared(ov::OutputVector{split->output(0), relu, split->output(2)}, ov::ParameterVector{data}); } -// ! [ngraph_utils:advanced_function] +// ! [ov:create_advanced_model] -void pattern_matcher_examples(std::shared_ptr node) { +void pattern_matcher_examples(std::shared_ptr node) { { // ! [pattern:simple_example] // Pattern example -auto input = std::make_shared(element::i64, Shape{1}); -auto shapeof = std::make_shared(input); +auto input = std::make_shared(ov::element::i64, ov::Shape{1}); +auto shapeof = std::make_shared(input); // Create Matcher with Parameter->ShapeOf pattern -auto m = std::make_shared(shapeof, "MyPatternBasedTransformation"); +auto m = std::make_shared(shapeof, "MyPatternBasedTransformation"); // ! [pattern:simple_example] // ! [pattern:callback_example] -ngraph::graph_rewrite_callback callback = [](pattern::Matcher& m) { +ov::graph_rewrite_callback callback = [](ov::pass::pattern::Matcher& m) { // Get root node - std::shared_ptr root_node = m.get_match_root(); + std::shared_ptr root_node = m.get_match_root(); // Get all nodes matched by pattern - NodeVector nodes = m.get_matched_nodes(); + ov::NodeVector nodes = m.get_matched_nodes(); // Transformation code return false; @@ -95,28 +98,28 @@ ngraph::graph_rewrite_callback callback = [](pattern::Matcher& m) { { // ! [pattern:label_example] // Detect Multiply with arbitrary first input and second as Constant -// ngraph::pattern::op::Label - represent arbitrary input -auto input = ngraph::pattern::any_input(); -auto value = ngraph::opset3::Constant::create(ngraph::element::f32, ngraph::Shape{1}, {0.5}); -auto mul = std::make_shared(input, value); -auto m = std::make_shared(mul, "MultiplyMatcher"); +// ov::pattern::op::Label - represent arbitrary input +auto input = ov::pass::pattern::any_input(); +auto value = ov::opset8::Constant::create(ov::element::f32, ov::Shape{1}, {0.5}); +auto mul = std::make_shared(input, value); +auto m = std::make_shared(mul, "MultiplyMatcher"); // ! [pattern:label_example] } { // ! [pattern:concat_example] // Detect Concat operation with arbitrary number of inputs -auto concat = ngraph::pattern::wrap_type(); -auto m = std::make_shared(concat, "ConcatMatcher"); +auto concat = ov::pass::pattern::wrap_type(); +auto m = std::make_shared(concat, "ConcatMatcher"); // ! [pattern:concat_example] } { // ! [pattern:predicate_example] // Detect Multiply->Add sequence where mul has exactly one consumer -auto mul = ngraph::pattern::wrap_type(ngraph::pattern::consumers_count(1)/*сheck consumers count*/); -auto add = ngraph::pattern::wrap_type({mul, ngraph::pattern::any_input()}); -auto m = std::make_shared(add, "MultiplyAddMatcher"); +auto mul = ov::pass::pattern::wrap_type(ov::pass::pattern::consumers_count(1)/*сheck consumers count*/); +auto add = ov::pass::pattern::wrap_type({mul, ov::pass::pattern::any_input()}); +auto m = std::make_shared(add, "MultiplyAddMatcher"); // Matcher can be used to match pattern manually on given node if (m->match(node->output(0))) { // Successfully matched @@ -126,21 +129,21 @@ if (m->match(node->output(0))) { } -bool ngraph_api_examples(std::shared_ptr node) { +bool ngraph_api_examples(std::shared_ptr node) { { // ! [ngraph:ports_example] -// Let's suppose that node is opset3::Convolution operation -// as we know opset3::Convolution has two input ports (data, weights) and one output port -Input data = node->input(0); -Input weights = node->input(1); -Output output = node->output(0); +// Let's suppose that node is opset8::Convolution operation +// as we know opset8::Convolution has two input ports (data, weights) and one output port +ov::Input data = node->input(0); +ov::Input weights = node->input(1); +ov::Output output = node->output(0); // Getting shape and type auto pshape = data.get_partial_shape(); auto el_type = data.get_element_type(); // Getting parent for input port -Output parent_output; +ov::Output parent_output; parent_output = data.get_source_output(); // Another short way to get partent for output port @@ -183,22 +186,23 @@ return true; } // ! [ngraph:replace_node] -bool ngraph_replace_node(std::shared_ptr node) { - // Step 1. Verify that node has opset3::Negative type - auto neg = std::dynamic_pointer_cast(node); +bool ngraph_replace_node(std::shared_ptr node) { + // Step 1. Verify that node has opset8::Negative type + auto neg = std::dynamic_pointer_cast(node); if (!neg) { return false; } - // Step 2. Create opset3::Multiply operation where the first input is negative operation input and second as Constant with -1 value - auto mul = std::make_shared(neg->input_value(0), - opset3::Constant::create(neg->get_element_type(), Shape{1}, {-1})); + // Step 2. Create opset8::Multiply operation where the first input is negative operation input and second as Constant with -1 value + auto mul = std::make_shared(neg->input_value(0), + ov::opset8::Constant::create(neg->get_element_type(), ov::Shape{1}, {-1})); mul->set_friendly_name(neg->get_friendly_name()); + // TODO: Move to new API ngraph::copy_runtime_info(neg, mul); // Step 3. Replace Negative operation with Multiply operation - ngraph::replace_node(neg, mul); + ov::replace_node(neg, mul); return true; // Step 4. Negative operation will be removed automatically because all consumers was moved to Multiply operation @@ -207,12 +211,12 @@ bool ngraph_replace_node(std::shared_ptr node) { // ! [ngraph:insert_node] // Step 1. Lets suppose that we have a node with single output port and we want to insert additional operation new_node after it -void insert_example(std::shared_ptr node) { +void insert_example(std::shared_ptr node) { // Get all consumers for node auto consumers = node->output(0).get_target_inputs(); // Step 2. Create new node. Let it be opset1::Relu. - auto new_node = std::make_shared(node); + auto new_node = std::make_shared(node); // Step 3. Reconnect all consumers to new_node for (auto input : consumers) { @@ -222,42 +226,53 @@ void insert_example(std::shared_ptr node) { // ! [ngraph:insert_node] // ! [ngraph:insert_node_with_copy] -void insert_example_with_copy(std::shared_ptr node) { +void insert_example_with_copy(std::shared_ptr node) { // Make a node copy auto node_copy = node->clone_with_new_inputs(node->input_values()); // Create new node - auto new_node = std::make_shared(node_copy); - ngraph::replace_node(node, new_node); + auto new_node = std::make_shared(node_copy); + ov::replace_node(node, new_node); } // ! [ngraph:insert_node_with_copy] -void eliminate_example(std::shared_ptr node) { +void eliminate_example(std::shared_ptr node) { // ! [ngraph:eliminate_node] // Suppose we have a node that we want to remove bool success = replace_output_update_name(node->output(0), node->input_value(0)); // ! [ngraph:eliminate_node] } -// ! [ngraph:visualize] -void visualization_example(std::shared_ptr f) { - ngraph::pass::Manager manager; +// ! [ov:serialize] +void serialize_example(std::shared_ptr f) { + ov::pass::Manager manager; - // Serialize ngraph::Function to before.svg file before transformation - manager.register_pass("/path/to/file/before.svg"); + // Serialize ov::Function to before.svg file before transformation + manager.register_pass("/path/to/file/before.svg"); // Run your transformation - // manager.register_pass(); + // manager.register_pass(); - // Serialize ngraph::Function to after.svg file after transformation - manager.register_pass("/path/to/file/after.svg"); + // Serialize ov::Function to after.svg file after transformation + manager.register_pass("/path/to/file/after.svg"); manager.run_passes(f); } -// ! [ngraph:visualize] +// ! [ov:serialize] -void pass_manager_example1(std::shared_ptr f) { +// ! [ov:visualize] +void visualization_example(std::shared_ptr f) { + ov::pass::Manager manager; + + // Serialize ov::Function to IR + manager.register_pass("/path/to/file/model.xml", "/path/to/file/model.bin"); + + manager.run_passes(f); +} +// ! [ov:visualize] + +void pass_manager_example1(std::shared_ptr f) { // ! [ngraph:disable_gelu] -ngraph::pass::Manager manager; +ov::pass::Manager manager; manager.register_pass(); auto pass_config = manager.get_pass_config(); @@ -267,21 +282,21 @@ manager.run_passes(f); // ! [ngraph:disable_gelu] } -void pass_manager_example2(std::shared_ptr f) { - ngraph::pass::Manager manager; - std::function)> transformation_callback; +void pass_manager_example2(std::shared_ptr f) { + ov::pass::Manager manager; + std::function)> transformation_callback; // ! [ngraph:disable_callback] // Set callback to particular transformation with specific condition auto pass_config = manager.get_pass_config(); pass_config->set_callback( - [](const std::shared_ptr &node) -> bool { + [](const std::shared_ptr &node) -> bool { return node->input_value(0).get_shape().size() <= 5lu && node->input_value(0).get_shape().size() == node->get_output_shape(0).size(); }); // Update transformation to call callback -ngraph::matcher_pass_callback callback = [=](pattern::Matcher &m) { +ov::matcher_pass_callback callback = [=](ov::pass::pattern::Matcher &m) { auto node = m.get_match_root(); if (transformation_callback(node)) { return false; @@ -292,19 +307,19 @@ ngraph::matcher_pass_callback callback = [=](pattern::Matcher &m) { // ! [ngraph:disable_callback] } -void pass_manager_example3(std::shared_ptr f) { - std::function)> transformation_callback; +void pass_manager_example3(std::shared_ptr f) { + std::function)> transformation_callback; // ! [ngraph:disabled_by_default] // Example of disabled by default transformation { - ngraph::pass::Manager manager; + ov::pass::Manager manager; manager.register_pass(); manager.run_passes(f); } // Enable disabled by default transformation inside plugin { - ngraph::pass::Manager manager; + ov::pass::Manager manager; manager.register_pass(); auto pass_config = manager.get_pass_config(); pass_config->enable(); diff --git a/samples/c/hello_classification/README.md b/samples/c/hello_classification/README.md index ab3d638b02a..f9daa132d69 100644 --- a/samples/c/hello_classification/README.md +++ b/samples/c/hello_classification/README.md @@ -17,7 +17,7 @@ Hello Classification C sample application demonstrates how to use the following | Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) | Validated images | The sample uses OpenCV\* to [read input image](https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56) (\*.bmp, \*.png) -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/hello_classification/README.md), [Python](../../python/hello_classification/README.md) | ## How It Works @@ -26,11 +26,11 @@ Upon the start-up, the sample application reads command line parameters, loads s Then, the sample creates an synchronous inference request object. When inference is done, the application outputs data to the standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -92,8 +92,8 @@ This sample is an API example, for any performance measurements please use the d ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/c/hello_nv12_input_classification/README.md b/samples/c/hello_nv12_input_classification/README.md index 9c29d8265e9..a3879a129d0 100644 --- a/samples/c/hello_nv12_input_classification/README.md +++ b/samples/c/hello_nv12_input_classification/README.md @@ -15,7 +15,7 @@ Basic Inference Engine API is covered by [Hello Classification C sample](../hell | Validated Models | [alexnet](@ref omz_models_model_alexnet) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) | Validated images | An uncompressed image in the NV12 color format - \*.yuv -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/hello_nv12_input_classification/README.md) | ## How It Works @@ -29,7 +29,7 @@ each sample step at [Integration Steps](https://docs.openvino.ai/latest/openvino ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -107,8 +107,8 @@ This sample is an API example, for any performance measurements please use the d ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/cpp/benchmark_app/README.md b/samples/cpp/benchmark_app/README.md index 45ecc92608d..436c3dc0434 100644 --- a/samples/cpp/benchmark_app/README.md +++ b/samples/cpp/benchmark_app/README.md @@ -56,7 +56,7 @@ Note that the benchmark_app usually produces optimal performance for any device But it is still may be sub-optimal for some cases, especially for very small networks. More details can read in [Performance Optimization Guide](../../../docs/optimization_guide/dldt_optimization_guide.md). -As explained in the [Performance Optimization Guide](../../../docs/optimization_guide/dldt_optimization_guide.md) section, for all devices, including new [MULTI device](../../../docs/IE_DG/supported_plugins/MULTI.md) it is preferable to use the FP16 IR for the model. +As explained in the [Performance Optimization Guide](../../../docs/optimization_guide/dldt_optimization_guide.md) section, for all devices, including new [MULTI device](../../../docs/OV_Runtime_UG/supported_plugins/MULTI.md) it is preferable to use the FP16 IR for the model. Also if latency of the CPU inference on the multi-socket machines is of concern, please refer to the same [Performance Optimization Guide](../../../docs/optimization_guide/dldt_optimization_guide.md). @@ -243,6 +243,6 @@ Below are fragments of sample output static and dynamic networks: ``` ## See Also -* [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +* [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) * [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) * [Model Downloader](@ref omz_tools_downloader) diff --git a/samples/cpp/classification_sample_async/README.md b/samples/cpp/classification_sample_async/README.md index 38babede1ff..8bb73cb95ce 100644 --- a/samples/cpp/classification_sample_async/README.md +++ b/samples/cpp/classification_sample_async/README.md @@ -21,7 +21,7 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he | Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) | Validated images | The sample uses OpenCV\* to [read input image](https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56) (\*.bmp, \*.png), single-channel `ubyte` images. -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [Python](../../../samples/python/classification_sample_async/README.md) | ## How It Works @@ -37,11 +37,11 @@ After that, the application starts inference for the first infer request and wai When inference is done, the application outputs data to the standard output stream. You can place labels in .labels file near the model to get pretty output. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -164,7 +164,7 @@ classid probability ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/cpp/hello_classification/README.md b/samples/cpp/hello_classification/README.md index 557f0edbb1d..b5e53a4fc49 100644 --- a/samples/cpp/hello_classification/README.md +++ b/samples/cpp/hello_classification/README.md @@ -17,7 +17,7 @@ Hello Classification C++ sample application demonstrates how to use the followin | Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) | Validated images | The sample uses OpenCV\* to [read input image](https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56) (\*.bmp, \*.png) -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C](../../../samples/c/hello_classification/README.md), [Python](../../../samples/python/hello_classification/README.md) | ## How It Works @@ -26,11 +26,11 @@ Upon the start-up, the sample application reads command line parameters, loads s Then, the sample creates an synchronous inference request object. When inference is done, the application outputs data to the standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -92,7 +92,7 @@ This sample is an API example, for any performance measurements please use the d ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/cpp/hello_nv12_input_classification/README.md b/samples/cpp/hello_nv12_input_classification/README.md index 668f1aedfb1..0a6611fb427 100644 --- a/samples/cpp/hello_nv12_input_classification/README.md +++ b/samples/cpp/hello_nv12_input_classification/README.md @@ -1,6 +1,6 @@ # Hello NV12 Input Classification C++ Sample {#openvino_inference_engine_samples_hello_nv12_input_classification_README} -This sample demonstrates how to execute an inference of image classification networks like AlexNet with images in NV12 color format using Synchronous Inference Request API and [input reshape feature](../../../docs/IE_DG/ShapeInference.md). +This sample demonstrates how to execute an inference of image classification networks like AlexNet with images in NV12 color format using Synchronous Inference Request API and [input reshape feature](../../../docs/OV_Runtime_UG/ShapeInference.md). Hello NV12 Input Classification C++ Sample demonstrates how to use the NV12 automatic input pre-processing API of the Inference Engine in your applications: @@ -18,7 +18,7 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he | Validated Models | [alexnet](@ref omz_models_model_alexnet) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) | Validated images | An uncompressed image in the NV12 color format - \*.yuv -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C](../../../samples/c/hello_nv12_input_classification/README.md) | ## How It Works @@ -26,11 +26,11 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he Upon the start-up, the sample application reads command-line parameters, loads specified network and an image in the NV12 color format to an Inference Engine plugin. Then, the sample creates an synchronous inference request object. When inference is done, the application outputs data to the standard output stream. You can place labels in .labels file near the model to get pretty output. -You can see the explicit description of each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +You can see the explicit description of each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -113,7 +113,7 @@ This sample is an API example, for any performance measurements please use the d ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/cpp/hello_query_device/README.md b/samples/cpp/hello_query_device/README.md index af7aac6fb66..1f1a6a7d4b8 100644 --- a/samples/cpp/hello_query_device/README.md +++ b/samples/cpp/hello_query_device/README.md @@ -1,6 +1,6 @@ # Hello Query Device C++ Sample {#openvino_inference_engine_samples_hello_query_device_README} -This sample demonstrates how to execute an query Inference Engine devices, prints their metrics and default configuration values, using [Query Device API feature](../../../docs/IE_DG/InferenceEngine_QueryAPI.md). +This sample demonstrates how to execute an query Inference Engine devices, prints their metrics and default configuration values, using [Query Device API feature](../../../docs/OV_Runtime_UG/InferenceEngine_QueryAPI.md). Hello Query Device C++ sample application demonstrates how to use the following Inference Engine C++ API in applications: @@ -12,7 +12,7 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he | Options | Values | |:--- |:--- -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [Python](../../../samples/python/hello_query_device/README.md) | ## How It Works @@ -21,7 +21,7 @@ The sample queries all available Inference Engine devices, prints their supporte ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -89,5 +89,5 @@ Available devices: ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) diff --git a/samples/cpp/hello_reshape_ssd/README.md b/samples/cpp/hello_reshape_ssd/README.md index 07775013ea5..777bb9cdafc 100644 --- a/samples/cpp/hello_reshape_ssd/README.md +++ b/samples/cpp/hello_reshape_ssd/README.md @@ -1,6 +1,6 @@ # Hello Reshape SSD C++ Sample {#openvino_inference_engine_samples_hello_reshape_ssd_README} -This sample demonstrates how to execute an inference of object detection networks like SSD-VGG using Synchronous Inference Request API, [input reshape feature](../../../docs/IE_DG/ShapeInference.md). +This sample demonstrates how to execute an inference of object detection networks like SSD-VGG using Synchronous Inference Request API, [input reshape feature](../../../docs/OV_Runtime_UG/ShapeInference.md). Hello Reshape SSD C++ sample application demonstrates how to use the following Inference Engine C++ API in applications: @@ -17,7 +17,7 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he | Validated Models | [person-detection-retail-0013](@ref omz_models_model_person_detection_retail_0013) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) | Validated images | The sample uses OpenCV\* to [read input image](https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56) (\*.bmp, \*.png) -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [Python](../../../samples/python/hello_reshape_ssd/README.md) | ## How It Works @@ -26,11 +26,11 @@ Upon the start-up the sample application reads command line parameters, loads sp Engine plugin. Then, the sample creates an synchronous inference request object. When inference is done, the application creates output image and output data to the standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -104,7 +104,7 @@ The resulting image was saved in the file: hello_reshape_ssd_batch_0.bmp ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/cpp/ngraph_function_creation_sample/README.md b/samples/cpp/ngraph_function_creation_sample/README.md index 301a5dab1af..aef78f0c905 100644 --- a/samples/cpp/ngraph_function_creation_sample/README.md +++ b/samples/cpp/ngraph_function_creation_sample/README.md @@ -1,6 +1,6 @@ # nGraph Function Creation C++ Sample {#openvino_inference_engine_samples_ngraph_function_creation_sample_README} -This sample demonstrates how to execute an synchronous inference using [nGraph function feature](../../../docs/nGraph_DG/build_function.md) to create a network, which uses weights from LeNet classification network, which is known to work well on digit classification tasks. +This sample demonstrates how to execute an synchronous inference using [OpenVINO Model feature](../../../docs/OV_Runtime_UG/model_representation.md) to create a network, which uses weights from LeNet classification network, which is known to work well on digit classification tasks. The sample supports only single-channel [MNIST database](http://yann.lecun.com/exdb/mnist) images as an input. @@ -22,18 +22,18 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he | Validated Models | LeNet | Model Format | Network weights file (\*.bin) | Validated images | single-channel `MNIST ubyte` images -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [Python](../../../samples/python/ngraph_function_creation_sample/README.md) | ## How It Works -At startup, the sample application reads command-line parameters, prepares input data, creates a network using the [nGraph function feature](../../../docs/nGraph_DG/build_function.md) and passed weights file, loads the network and image(s) to the Inference Engine plugin, performs synchronous inference and processes output data, logging each step in a standard output stream. You can place labels in .labels file near the model to get pretty output. +At startup, the sample application reads command-line parameters, prepares input data, creates a network using the [OpenVINO Model feature](../../../docs/OV_Runtime_UG/model_representation.md) and passed weights file, loads the network and image(s) to the Inference Engine plugin, performs synchronous inference and processes output data, logging each step in a standard output stream. You can place labels in .labels file near the model to get pretty output. -You can see the explicit description of each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +You can see the explicit description of each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -146,6 +146,6 @@ classid probability ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/cpp/speech_sample/README.md b/samples/cpp/speech_sample/README.md index 1ef53db097d..4a09a8b37e4 100644 --- a/samples/cpp/speech_sample/README.md +++ b/samples/cpp/speech_sample/README.md @@ -23,7 +23,7 @@ Basic Inference Engine API is covered by [Hello Classification C++ sample](../he |:--- |:--- | Validated Models | Acoustic model based on Kaldi\* neural networks (see [Model Preparation](#model-preparation) section) | Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin) -| Supported devices | See [Execution Modes](#execution-modes) section below and [List Supported Devices](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | See [Execution Modes](#execution-modes) section below and [List Supported Devices](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | ## How It Works @@ -32,7 +32,7 @@ frames according to the `-bs` parameter. Batching across utterances is not supp statistics are provided for each speech utterance as shown above. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ### GNA-specific details @@ -80,7 +80,7 @@ In addition to performing inference directly from a GNA model file, these combin ## Building -To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/IE_DG/Samples_Overview.md) section in Inference Engine Samples guide. +To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide. ## Running @@ -241,7 +241,7 @@ All of mentioned files can be downloaded from [https://storage.openvinotoolkit.o ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/python/classification_sample_async/README.md b/samples/python/classification_sample_async/README.md index 5be16749176..0c6783160b9 100644 --- a/samples/python/classification_sample_async/README.md +++ b/samples/python/classification_sample_async/README.md @@ -16,7 +16,7 @@ Basic Inference Engine API is covered by [Hello Classification Python* Sample](. | :------------------------- | :-------------------------------------------------------------------------------------------------------- | | Validated Models | [alexnet](@ref omz_models_model_alexnet) | | Model Format | Inference Engine Intermediate Representation (.xml + .bin), ONNX (.onnx) | -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/classification_sample_async/README.md) | ## How It Works @@ -24,7 +24,7 @@ Basic Inference Engine API is covered by [Hello Classification Python* Sample](. At startup, the sample application reads command-line parameters, prepares input data, loads a specified model and image(s) to the Inference Engine plugin, performs synchronous inference, and processes output data, logging each step in a standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Running @@ -146,8 +146,8 @@ The sample application logs each step in a standard output stream and outputs to ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/python/hello_classification/README.md b/samples/python/hello_classification/README.md index 51a3a4f8a7f..98c759cde3b 100644 --- a/samples/python/hello_classification/README.md +++ b/samples/python/hello_classification/README.md @@ -15,7 +15,7 @@ The following Inference Engine Python API is used in the application: | :------------------------- | :-------------------------------------------------------------------------------------------------------- | | Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1) | | Model Format | Inference Engine Intermediate Representation (.xml + .bin), ONNX (.onnx) | -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/hello_classification/README.md), [C](../../c/hello_classification/README.md) | ## How It Works @@ -23,7 +23,7 @@ The following Inference Engine Python API is used in the application: At startup, the sample application reads command-line parameters, prepares input data, loads a specified model and image to the Inference Engine plugin, performs synchronous inference, and processes output data, logging each step in a standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Running @@ -117,8 +117,8 @@ The sample application logs each step in a standard output stream and outputs to ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/python/hello_query_device/README.md b/samples/python/hello_query_device/README.md index 5cdf870c4fd..38b5fdd73a3 100644 --- a/samples/python/hello_query_device/README.md +++ b/samples/python/hello_query_device/README.md @@ -1,6 +1,6 @@ # Hello Query Device Python* Sample {#openvino_inference_engine_ie_bridges_python_sample_hello_query_device_README} -This sample demonstrates how to show Inference Engine devices and prints their metrics and default configuration values using [Query Device API feature](../../../docs/IE_DG/InferenceEngine_QueryAPI.md). +This sample demonstrates how to show Inference Engine devices and prints their metrics and default configuration values using [Query Device API feature](../../../docs/OV_Runtime_UG/InferenceEngine_QueryAPI.md). The following Inference Engine Python API is used in the application: @@ -11,7 +11,7 @@ The following Inference Engine Python API is used in the application: | Options | Values | | :------------------------- | :---------------------------------------------------------------------- | -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/hello_query_device/README.md) | ## How It Works @@ -103,7 +103,7 @@ The application prints all available devices with their supported metrics and de ``` ## See Also -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) [IECore]:https://docs.openvino.ai/latest/ie_python_api/classie__api_1_1IECore.html [IECore.get_metric]:https://docs.openvino.ai/latest/ie_python_api/classie__api_1_1IECore.html#af1cdf2ecbea6399c556957c2c2fdf8eb diff --git a/samples/python/hello_reshape_ssd/README.md b/samples/python/hello_reshape_ssd/README.md index cb49894cbf7..863772716cf 100644 --- a/samples/python/hello_reshape_ssd/README.md +++ b/samples/python/hello_reshape_ssd/README.md @@ -1,6 +1,6 @@ # Hello Reshape SSD Python* Sample {#openvino_inference_engine_ie_bridges_python_sample_hello_reshape_ssd_README} -This sample demonstrates how to do synchronous inference of object detection networks using [Shape Inference feature](../../../docs/IE_DG/ShapeInference.md). +This sample demonstrates how to do synchronous inference of object detection networks using [Shape Inference feature](../../../docs/OV_Runtime_UG/ShapeInference.md). Models with only 1 input and output are supported. The following Inference Engine Python API is used in the application: @@ -16,7 +16,7 @@ Basic Inference Engine API is covered by [Hello Classification Python* Sample](. | :------------------------- | :-------------------------------------------------------------------------------------------------------------------------- | | Validated Models | [mobilenet-ssd](@ref omz_models_model_mobilenet_ssd) | | Model Format | Inference Engine Intermediate Representation (.xml + .bin), ONNX (.onnx) | -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/hello_reshape_ssd/README.md) | ## How It Works @@ -25,7 +25,7 @@ At startup, the sample application reads command-line parameters, prepares input As a result, the program creates an output image, logging each step in a standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Running @@ -114,8 +114,8 @@ The sample application logs each step in a standard output stream and creates an ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/python/ngraph_function_creation_sample/README.md b/samples/python/ngraph_function_creation_sample/README.md index c110096d0e7..e83e8b559d6 100644 --- a/samples/python/ngraph_function_creation_sample/README.md +++ b/samples/python/ngraph_function_creation_sample/README.md @@ -1,6 +1,6 @@ # nGraph Function Creation Python* Sample {#openvino_inference_engine_ie_bridges_python_sample_ngraph_function_creation_sample_README} -This sample demonstrates how to execute an inference using [nGraph function feature](../../../docs/nGraph_DG/build_function.md) to create a network that uses weights from LeNet classification network, which is known to work well on digit classification tasks. So you don't need an XML file, the model will be created from the source code on the fly. +This sample demonstrates how to execute an inference using [OpenVINO Model feature](../../../docs/OV_Runtime_UG/model_representation.md) to create a network that uses weights from LeNet classification network, which is known to work well on digit classification tasks. So you don't need an XML file, the model will be created from the source code on the fly. In addition to regular grayscale images with a digit, the sample also supports single-channel `ubyte` images as an input. @@ -18,15 +18,15 @@ Basic Inference Engine API is covered by [Hello Classification Python* Sample](. | Validated Models | LeNet | | Model Format | Network weights file (\*.bin) | | Validated images | The sample uses OpenCV\* to [read input grayscale image](https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56) (\*.bmp, \*.png) or single-channel `ubyte` image | -| Supported devices | [All](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/ngraph_function_creation_sample/README.md) | ## How It Works -At startup, the sample application reads command-line parameters, prepares input data, creates a network using [nGraph function feature](../../../docs/nGraph_DG/build_function.md) and passed weights file, loads the network and image(s) to the Inference Engine plugin, performs synchronous inference, and processes output data, logging each step in a standard output stream. +At startup, the sample application reads command-line parameters, prepares input data, creates a network using [OpenVINO Model feature](../../../docs/OV_Runtime_UG/model_representation.md) and passed weights file, loads the network and image(s) to the Inference Engine plugin, performs synchronous inference, and processes output data, logging each step in a standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## Running @@ -109,8 +109,8 @@ The sample application logs each step in a standard output stream and outputs to ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/samples/python/speech_sample/README.md b/samples/python/speech_sample/README.md index e36a13add56..b7efee43676 100644 --- a/samples/python/speech_sample/README.md +++ b/samples/python/speech_sample/README.md @@ -19,7 +19,7 @@ Basic Inference Engine API is covered by [Hello Classification Python* Sample](. | :------------------------- | :---------------------------------------------------------------------------------------------------- | | Validated Models | Acoustic model based on Kaldi* neural networks (see [Model Preparation](#model-preparation) section) | | Model Format | Inference Engine Intermediate Representation (.xml + .bin) | -| Supported devices | See [Execution Modes](#execution-modes) section below and [List Supported Devices](../../../docs/IE_DG/supported_plugins/Supported_Devices.md) | +| Supported devices | See [Execution Modes](#execution-modes) section below and [List Supported Devices](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) | | Other language realization | [C++](../../../samples/cpp/speech_sample/README.md) | ## How It Works @@ -27,7 +27,7 @@ Basic Inference Engine API is covered by [Hello Classification Python* Sample](. At startup, the sample application reads command-line parameters, loads a specified model and input data to the Inference Engine plugin, performs synchronous inference on all speech utterances stored in the input file, logging each step in a standard output stream. You can see the explicit description of -each sample step at [Integration Steps](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. +each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) section of "Integrate the Inference Engine with Your Application" guide. ## GNA-specific details @@ -238,8 +238,8 @@ The sample application logs each step in a standard output stream. ## See Also -- [Integrate the Inference Engine with Your Application](../../../docs/IE_DG/Integrate_with_customer_application_new_API.md) -- [Using Inference Engine Samples](../../../docs/IE_DG/Samples_Overview.md) +- [Integrate the Inference Engine with Your Application](../../../docs/OV_Runtime_UG/Integrate_with_customer_application_new_API.md) +- [Using Inference Engine Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md) - [Model Downloader](@ref omz_tools_downloader) - [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) diff --git a/tools/benchmark_tool/README.md b/tools/benchmark_tool/README.md index f6954f92918..370de0e8bce 100644 --- a/tools/benchmark_tool/README.md +++ b/tools/benchmark_tool/README.md @@ -223,6 +223,6 @@ Below are fragments of sample output for CPU and GPU devices: ``` ## See Also -* [Using Inference Engine Samples](../../docs/IE_DG/Samples_Overview.md) +* [Using Inference Engine Samples](../../docs/OV_Runtime_UG/Samples_Overview.md) * [Model Optimizer](../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) * [Model Downloader](@ref omz_tools_downloader) diff --git a/tools/benchmark_tool/openvino/tools/benchmark/README.md b/tools/benchmark_tool/openvino/tools/benchmark/README.md index e35abe5a414..36b0303dd18 100644 --- a/tools/benchmark_tool/openvino/tools/benchmark/README.md +++ b/tools/benchmark_tool/openvino/tools/benchmark/README.md @@ -47,7 +47,7 @@ Notice that the benchmark_app usually produces optimal performance for any devic $benchmark_app -m -i -d CPU ``` -But it is still may be non-optimal for some cases, especially for very small networks. More details can read in [Introduction to Performance Topics](../../../../../docs/IE_DG/Intro_to_Performance.md). +But it is still may be non-optimal for some cases, especially for very small networks. More details can read in [Introduction to Performance Topics](../../../../../docs/OV_Runtime_UG/Intro_to_Performance.md). Running the application with the `-h` or `--help`' option yields the following usage message: @@ -188,6 +188,6 @@ Throughput: 73.28 FPS ``` ## See Also -* [Using Inference Engine Samples](../../../../../docs/IE_DG/Samples_Overview.md) +* [Using Inference Engine Samples](../../../../../docs/OV_Runtime_UG/Samples_Overview.md) * [Model Optimizer](../../../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md) * [Model Downloader](https://github.com/openvinotoolkit/open_model_zoo/tree/2018/model_downloader)