Hello, On Wed, 4 Jul 2018, at 16:19, Pedro Arthur wrote: > 2018-07-04 4:03 GMT-03:00 Jean-Baptiste Kempf <j...@videolan.org>: > > On Wed, 4 Jul 2018, at 01:22, Carl Eugen Hoyos wrote: > >> 2018-07-04 0:14 GMT+02:00, Jean-Baptiste Kempf <j...@videolan.org>: > >> > On Tue, 3 Jul 2018, at 20:59, Carl Eugen Hoyos wrote: > >> >> How is this case different from many arrays in libavcodec/*data*? > >> > > >> > It is very different: the arrays in *data* come either from a > >> > mathematical computation or a spec. > >> > >> (Apart from: Free and open specs?) > >> This is probably true for some of the arrays, I think it is > >> very unlikely that it's true for all of them. > > > > The point is: you can recreate all of those arrays. > > If OP dies, you can still take over. > > > >> > Else, as some Debian Developer said: "It looks like code > >> > hidden in an unsigned char array" > >> > >> Is it "code" or data that was computed with a copyrighted > >> algorithm? > It is only data, namely the weights used in the filters.
Sure, but how can we recreate this data, if you are not around? How can we check your findings? > > How can you know, if it is not explained, and you cannot reproduce it? > > How is it different from a binary blob? > > > > Anything related to NN is very annoying, if you don't share the dataset and > > the methodology. > > The paper cited in the code contains all relevant information for > anyone with basic CNN knowledge to understand the model and maintain > the code. > The whole point of training a NN is that you do it once, takes a lot > of time, and never do it again. > If you look at the publications in this area, the concept of > reproducibility is not the usually expected "bit exact" ,as other > mathematical fields. > It is more like achieving similar results, given the model and dataset. I completely understand, having done some of that myself. > For anyone interested in the training process, Sergey provided the > repo [1] with scripts for downloading the dataset and training. That's great! What is the licensing of this? -- Jean-Baptiste Kempf - President +33 672 704 734 _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
