yocto@lists.yoctoproject.org | Incorporating Xilinx DNNDK into Yocto

Home Messages Hashtags Subgroups

Date Date 1 - 5 of 5

Incorporating Xilinx DNNDK into Yocto

Emily #45011 Hi all - Xilinx has the Deep Neural Network Development Kit (DNNDK) that they just released the source code for in the last month or so. They have the code written nicely in the form of yocto recipes but it doesn't appear to be an actual layer: https://github.com/Xilinx/Edge-AI-Platform-Tutorials/tree/master/docs/DPU-Integration/reference-files/files . Is there a possibility of creating a layer for it? Or should I look into other options, like adding it as a submodule to my custom layer meta-l1calo: https://github.com/kratsg/meta-l1calo? Or if anyone has additional options, suggestions are appreciated! Thanks for the help! Emily
More All Messages By This Member
Khem Raj #45013 On Fri, May 3, 2019 at 2:09 PM Emily S <easmith5555@...> wrote: Hi all - Xilinx has the Deep Neural Network Development Kit (DNNDK) that they just released the source code for in the last month or so. They have the code written nicely in the form of yocto recipes but it doesn't appear to be an actual layer: https://github.com/Xilinx/Edge-AI-Platform-Tutorials/tree/master/docs/DPU-Integration/reference-files/files . Is there a possibility of creating a layer for it? Or should I look into other options, like adding it as a submodule to my custom layer meta-l1calo: https://github.com/kratsg/meta-l1calo? Or if anyone has additional options, suggestions are appreciated! I think we need meta-ai Thanks for the help! Emily -- _______________________________________________ yocto mailing list yocto@... https://lists.yoctoproject.org/listinfo/yocto
More All Messages By This Member
Randy MacLeod #45014 On 5/3/19 7:36 PM, Khem Raj wrote: On Fri, May 3, 2019 at 2:09 PM Emily S <easmith5555@...> wrote: Hi all - Xilinx has the Deep Neural Network Development Kit (DNNDK) that they just released the source code for in the last month or so. They have the code written nicely in the form of yocto recipes but it doesn't appear to be an actual layer: https://github.com/Xilinx/Edge-AI-Platform-Tutorials/tree/master/docs/DPU-Integration/reference-files/files . Is there a possibility of creating a layer for it? Or should I look into other options, like adding it as a submodule to my custom layer meta-l1calo: https://github.com/kratsg/meta-l1calo? Or if anyone has additional options, suggestions are appreciated! I think we need meta-ai or add to: https://github.com/nnsuite/meta-neural-network Is most of the code Xilinx HW specific? If so then a general layer may not be appropriate. ../Randy Thanks for the help! Emily -- _______________________________________________ yocto mailing list yocto@... https://lists.yoctoproject.org/listinfo/yocto -- # Randy MacLeod # Wind River Linux
More All Messages By This Member
Emily #45021 Hi Randy - Good point it might be. Should I ask the meta-Xilinx maintainers about getting it in there? Best, Emily toggle quoted message Show quoted text On May 3, 2019, at 8:41 PM, Randy MacLeod <randy.macleod@...> wrote: On 5/3/19 7:36 PM, Khem Raj wrote: On Fri, May 3, 2019 at 2:09 PM Emily S <easmith5555@...> wrote: Hi all - Xilinx has the Deep Neural Network Development Kit (DNNDK) that they just released the source code for in the last month or so. They have the code written nicely in the form of yocto recipes but it doesn't appear to be an actual layer: https://github.com/Xilinx/Edge-AI-Platform-Tutorials/tree/master/docs/DPU-Integration/reference-files/files . Is there a possibility of creating a layer for it? Or should I look into other options, like adding it as a submodule to my custom layer meta-l1calo: https://github.com/kratsg/meta-l1calo? Or if anyone has additional options, suggestions are appreciated! I think we need meta-ai or add to: https://github.com/nnsuite/meta-neural-network Is most of the code Xilinx HW specific? If so then a general layer may not be appropriate. ../Randy Thanks for the help! Emily -- _______________________________________________ yocto mailing list yocto@... https://lists.yoctoproject.org/listinfo/yocto -- # Randy MacLeod # Wind River Linux
More All Messages By This Member
Bruce Ashfield #45026 On Sat, May 4, 2019 at 10:07 AM Emily Smith <easmith5555@...> wrote: Hi Randy - Good point it might be. Should I ask the meta-Xilinx maintainers about getting it in there? That's probably the right thing to do, and/or just ask on the xilinx mailing list what the plans are for releasing the code in a layer. Bruce Best, Emily > On May 3, 2019, at 8:41 PM, Randy MacLeod <randy.macleod@...> wrote: > >> On 5/3/19 7:36 PM, Khem Raj wrote: >>> On Fri, May 3, 2019 at 2:09 PM Emily S <easmith5555@...> wrote: >>> >>> Hi all - >>> >>> Xilinx has the Deep Neural Network Development Kit (DNNDK) that they just released the source code for in the last month or so. They have the code written nicely in the form of yocto recipes but it doesn't appear to be an actual layer: https://github.com/Xilinx/Edge-AI-Platform-Tutorials/tree/master/docs/DPU-Integration/reference-files/files . Is there a possibility of creating a layer for it? Or should I look into other options, like adding it as a submodule to my custom layer meta-l1calo: https://github.com/kratsg/meta-l1calo? >>> >>> Or if anyone has additional options, suggestions are appreciated! >> I think we need meta-ai > > or add to: > https://github.com/nnsuite/meta-neural-network > > Is most of the code Xilinx HW specific? > If so then a general layer may not be appropriate. > > ../Randy > >>> Thanks for the help! >>> Emily >>> -- >>> _______________________________________________ >>> yocto mailing list >>> yocto@... >>> https://lists.yoctoproject.org/listinfo/yocto > > > -- > # Randy MacLeod > # Wind River Linux -- _______________________________________________ yocto mailing list yocto@... https://lists.yoctoproject.org/listinfo/yocto -- - Thou shalt not follow the NULL pointer, for chaos and madness await thee at its end - "Use the force Harry" - Gandalf, Star Trek II
More All Messages By This Member

1 - 5 of 5

1

Previous Topic Next Topic

Home Hashtags Subgroups Terms