From 1cf3fe96af10e9eef20e4f0ed3e0d86e373ec97e Mon Sep 17 00:00:00 2001 From: Sebastian Golebiewski Date: Thu, 31 Aug 2023 14:00:31 +0200 Subject: [PATCH] [DOCS] Improve NNCF workflow images (#19040) * Update DEVELOPMENT_FLOW_V3_crunch.svg * Update DEVELOPMENT_FLOW_V3_crunch.svg * update * Update DEVELOPMENT_FLOW_V3_crunch.svg * Update DEVELOPMENT_FLOW_V3_crunch.svg * Update DEVELOPMENT_FLOW_V3_crunch.svg * Update docs/optimization_guide/model_optimization_guide.md --- docs/_static/images/DEVELOPMENT_FLOW_V3_crunch.svg | 4 ++-- docs/optimization_guide/model_optimization_guide.md | 4 +++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/docs/_static/images/DEVELOPMENT_FLOW_V3_crunch.svg b/docs/_static/images/DEVELOPMENT_FLOW_V3_crunch.svg index 06260ca93d5..99023d14b6c 100644 --- a/docs/_static/images/DEVELOPMENT_FLOW_V3_crunch.svg +++ b/docs/_static/images/DEVELOPMENT_FLOW_V3_crunch.svg @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:33de308a6476f054ae4d0b1ca356659003c8ba36cf9583f08963663259c0c1d4 -size 263357 +oid sha256:d02f98d7e50d663e0f525366b59cac16175ad437ee54147950a62b9bccb85030 +size 413331 diff --git a/docs/optimization_guide/model_optimization_guide.md b/docs/optimization_guide/model_optimization_guide.md index c6f245ba5f9..718fd5310aa 100644 --- a/docs/optimization_guide/model_optimization_guide.md +++ b/docs/optimization_guide/model_optimization_guide.md @@ -18,7 +18,9 @@ Model optimization is an optional offline step of improving the final model perf .. note:: OpenVINO also supports optimized models (for example, quantized) from source frameworks such as PyTorch, TensorFlow, and ONNX (in Q/DQ; Quantize/DeQuantize format). No special steps are required in this case and optimized models can be converted to the OpenVINO Intermediate Representation format (IR) right away. -Post-training Quantization is the fastest way to optimize a model and should be applied first, but it is limited in terms of achievable accuracy-performance trade-off. In case of poor accuracy or performance after Post-training Quantization, Training-time Optimization can be used as an option. +Post-training Quantization is the fastest way to optimize a model and should be applied first, but it is limited in terms of achievable accuracy-performance trade-off. The recommended approach to obtain OpenVINO quantized model is to convert a model from original framework to ``ov.Model`` and ensure that the model works correctly in OpenVINO, for example, by calculating the model metrics. Then, ``ov.Model`` can be used as input for the ``nncf.quantize()`` method to get the quantized model (see the diagram below). + +In case of unsatisfactory accuracy or performance after Post-training Quantization, Training-time Optimization can be used as an option. .. image:: _static/images/DEVELOPMENT_FLOW_V3_crunch.svg