fujunwei comments

Repositories
Issues
Comments

Results 61 comments of


                                            fujunwei

[GNA] Fix the workaround of using scale of float32 model to do int8 inference on GNA plugin

GNA plugin support online and offline quantization. Online approach quantize model with input scale factor when loading network with calling [GNAPlugin::LoadNetwork(ICNNNetwork &network)](https://github.com/opencv/dldt/blob/2020/inference-engine/src/gna_plugin/gna_plugin.cpp#L340), below section is to quantize model with I16...