diff --git a/tools/pot/docs/range_supervision/images/scheme3.png b/tools/pot/docs/range_supervision/images/scheme3.png deleted file mode 100644 index b46f6545f0f..00000000000 --- a/tools/pot/docs/range_supervision/images/scheme3.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d2c7919ea4b1fec95e1b15648194f7e2227793a661c55a242705e44fdc4c0f2f -size 25732 diff --git a/tools/pot/docs/range_supervision/images/scheme3.svg b/tools/pot/docs/range_supervision/images/scheme3.svg new file mode 100644 index 00000000000..1df476de97f --- /dev/null +++ b/tools/pot/docs/range_supervision/images/scheme3.svg @@ -0,0 +1,631 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tools/pot/openvino/tools/pot/algorithms/quantization/range_supervision/README.md b/tools/pot/openvino/tools/pot/algorithms/quantization/range_supervision/README.md index 7a762ffeda5..b270b6671a5 100644 --- a/tools/pot/openvino/tools/pot/algorithms/quantization/range_supervision/README.md +++ b/tools/pot/openvino/tools/pot/algorithms/quantization/range_supervision/README.md @@ -11,7 +11,7 @@ Deep neural network find applications in many scenarios where the prediction is The process flow follows the diagram [Fig 1](#Schematic). Starting from the internal representation (IR) of an OpenVINO model, the POT RangeSupervision algorithm is called to **add protection layers into the model graph**. This step requires **appropriate threshold values that are automatically extracted from a specified test dataset**. The result is an IR representation of the model with additional "RangeSupervision" layers after each supported activation layer. The original and the modified model can be called in the same way through the OpenVINO inference engine to evaluate the impact on accuracy, performance, and dependability in the presence of potential soft errors (for example using the *benchmark_app* and *accuracy_checker* functions). **The algorithm is designed to provide efficient protection at negligible performance overhead or accuracy impact in the absence of faults.** Bound extraction is a one-time effort and the protected IR model returned by the RangeSupervision algorithm can be used independently from there on. No changes in the learned parameters of the network are needed. @anchor schematic -![Schematic](../../../../../../docs/range_supervision/images/scheme3.png) +![Schematic](../../../../../../docs/range_supervision/images/scheme3.svg) *Fig 1: Schematic of RangeSupervision process flow.*