[FFmpeg-devel] [PATCH V2 1/2] libavfilter/dnn: add script to convert TensorFlow model (.pb) to native model (.model)

[Guo, Yejun]

> -----Original Message-----
> From: ffmpeg-devel [mailto:ffmpeg-devel-bounces at ffmpeg.org] On Behalf Of
> Pedro Arthur
> Sent: Wednesday, June 12, 2019 3:43 AM
> To: FFmpeg development discussions and patches <ffmpeg-devel at ffmpeg.org>
> Subject: Re: [FFmpeg-devel] [PATCH V2 1/2] libavfilter/dnn: add script to
> convert TensorFlow model (.pb) to native model (.model)
> 
> Hi,
> 
> Em ter, 11 de jun de 2019 às 05:00, Guo, Yejun <yejun.guo at intel.com>
> escreveu:
> >
> >
> > there are three options for the place to put these .py scripts.
> > 1) at libavfilter/dnn/python/
> >   the point is to put all the dnn stuffs together
> > 2) at tools/python/
> >   the point is that there is already a .py script under tools/
> > 3) create a new project controlled by ffmpeg
> >   the point is that the python scripts should not be part of ffmpeg source
> tree.
> >   (btw, how to apply such sub project?)
> >
> I think option (2) is better as it is already there, even if (1) is
> more convenient.

thanks, there are two comments suggest to put under tools/, I'll put all the python scripts under tools/python if no more other comments.

> 
> 
> > My idea is that the script generates dnn native model file which is loaded by
> ffmpeg c code,
> > it is better to put the script within the ffmpeg source tree, and all the dnn
> stuffs would be better to put together, thanks.
> >
> > anyway, I'm open to any option, just to make the progress continue ...
> >
> > >
> > > ping for review, thanks.
> > >
> > > Here is my rough plan after this patch.
> > > - move dnn relative .h/.c from libavfilter to libavfilter/dnn, it is expected
> there
> > > will be more files for dnn module (code for both model loading and
> execution).
> > > - add a layer for padding (tf.pad) for native mode and its fate test.
> > > - change the script to add tf.pad support, and so the native model and the tf
> > > model of vf_sr will be the same.
> > >  in current implementation, the two models have a little difference, it
> makes
> > > the script not a general solution to convert tf model to native model.
> > > - add layer maximum and fate test. This layer appears in tf model, but not in
> > > native model, of vf_sr.
> > > - introduce operand concept in native mode (both execution and model), to
> > > support data split and merge/concat in the network, such split/concat is
> very
> > > common.
> > >  it also makes possible to reuse memory for the intermediate data as the
> > > output of the hidden layers.
> > > - tune conv2d layer performance (it is very slow now) or add more layers for
> > > native mode.
> > >
> > > _______________________________________________
> > > ffmpeg-devel mailing list
> > > ffmpeg-devel at ffmpeg.org
> > > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> > >
> > > To unsubscribe, visit link above, or email
> > > ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".
> > _______________________________________________
> > ffmpeg-devel mailing list
> > ffmpeg-devel at ffmpeg.org
> > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> >
> > To unsubscribe, visit link above, or email
> > ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel at ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".