[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
> Guo, Yejun
> Sent: Monday, June 10, 2019 11:10 AM
> To: 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)
> 
> 
> 
> > -----Original Message-----
> > From: Guo, Yejun
> > Sent: Tuesday, June 04, 2019 3:10 PM
> > To: ffmpeg-devel at ffmpeg.org
> > Cc: Guo, Yejun <yejun.guo at intel.com>
> > Subject: [PATCH V2 1/2] libavfilter/dnn: add script to convert TensorFlow
> model
> > (.pb) to native model (.model)
> >
> > For example, given TensorFlow model file espcn.pb,
> > to generate native model file espcn.model, just run:
> > python convert.py espcn.pb
> >
> > In current implementation, the native model file is generated for
> > specific dnn network with hard-code python scripts maintained out of ffmpeg.
> > For example, srcnn network used by vf_sr is generated with
> >
> https://github.com/HighVoltageRocknRoll/sr/blob/master/generate_header_a
> > nd_model.py#L85
> >
> > In this patch, the script is designed as a general solution which
> > converts general TensorFlow model .pb file into .model file. The script
> > now has some tricky to be compatible with current implemention, will
> > be refined step by step.
> >
> > The script is also added into ffmpeg source tree. It is expected there
> > will be many more patches and community needs the ownership of it.
> >
> > Another technical direction is to do the conversion in c/c++ code within
> > ffmpeg source tree. While .pb file is organized with protocol buffers,
> > it is not easy to do such work with tiny c/c++ code, see more discussion
> > at http://ffmpeg.org/pipermail/ffmpeg-devel/2019-May/244496.html. So,
> > choose the python script.
> >
> > Signed-off-by: Guo, Yejun <yejun.guo at intel.com>
> > ---
> >  .gitignore                                        |   1 +
> >  libavfilter/dnn/python/convert.py                 |  52 ++++++
> >  libavfilter/dnn/python/convert_from_tensorflow.py | 201
> > ++++++++++++++++++++++
> >  3 files changed, 254 insertions(+)
> >  create mode 100644 libavfilter/dnn/python/convert.py
> >  create mode 100644 libavfilter/dnn/python/convert_from_tensorflow.py

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?)

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".