Hello Marcus,
Thanks for the suggestions.
As you've suggested I would focus on only one of the ideas, that will be
Neural Style Transfer.
The main goal will be to add Neural Style Transfer to MLPack in a
well-designed and documented way such that users who wish to expand upon it
by coding further and those who wish to just use it by using CLI can both
use it.
Since GSOC is divided into three phases I will divide my work into three
phases.
Phase 1:
1) Adding the VGG model.
2) Getting it trained on the ImageNet dataset, or successfully transferring
pre-trained weights to it. A little image recognition testing will be done
to make sure the model has learned good enough parameters.
Since there is already a PR open for VGG and Kartik Dutt is already working
on restructuring the models' repository, this should be easier than other
tasks. I'll probably have exams around this time so it'll work out well.
Phase 2:
1)Implementing Neural Style Transfer. I would like to implement it like a
neatly defined API which is easy to use. Adding it as a CLI program and an
importable library is what I'll aim for.
After VGG will be added MLPack has almost everything required to implement
this algorithm. I will need to define some custom loss but MLPack has is
already covered.
Phase 3:
1) In this phase I will document the API created in the parts it's lacking.
I will also do some more testing and add tutorials for it.
Testing will include using other models like inception and AlexNet to give
outputs and compare the visual quality of different models and visualizing
"content" and "style" of images as per the NN.
I think I'll have enough time to complete all of this, so any other small
details that are required to make this as refined as possible will be
worked upon within the GSOC period itself.
Any suggestions are highly appreciated.
Thanks,
Prince Gupta
On Fri, Mar 13, 2020 at 2:18 AM Marcus Edel
wrote:
> Hello Prince,
>
> thanks for reaching out, and thanks for all the contributions over the last
> weeks.
>
> Personally, I would focus on one project, you can always implement another
> method if there is time left at the end, but since the models behind both
> ideas
> a somewhat different it makes sense to focus on a single one. Also, I
> think I
> said this before, but testing takes time, sometimes more time than the
> actual
> method implementation. Besides, documentation and writing a tutorial
> shouldn't
> be underestimated as well. That said I think each project is interesting
> and
> definitely enough work for a GSoC project.
>
> Thanks,
> Marcus
>
> > On 8. Mar 2020, at 09:49, Prince Gupta wrote:
> >
> > Hello everyone
> > I am Prince Gupta, currently a 1st year Engineering student from India.
> I've been getting familiar with MLPack codebase, especially ANN and made
> some PRs since February 2020. I wanted to get some opinions on the GSOC
> project I've decided on.
> > I apologize in advance if this email gets too long.
> >
> > Earlier I discussed with @zoq about implementing YOLO for GSOC project
> but @kartikdutt18 was already working on it, so I decided to change my
> project idea as two people working on same thing will be redundant.
> >
> > For GSOC I would like to implement the following two applications of ANN:
> > 1) Neural Style Transfer
> > 2) Face Recognition
> >
> > To work on them I would also need to implement the following
> prerequisites which I hope to implement before the GSOC period starts:
> > 1) VGG-19 Model for Neural Style Transfer
> > 2) Triplet Margin Loss for Face Recognition(I've opened a PR on it
> already #2208)
> > 3) Inception Network for Face Recognition
> > If training is out of scope I'll try to use pre-trained weights.
> >
> > I would love to hear opinions on my project idea, is this sufficient? is
> this too much? other things I should consider or anything else.
> >
> > Project: Application of ANN Algorithms Implemented in mlpack
> > Mentors: Marcus Edel, Sumedh Ghaisas, Shikhar Jaiswal, Saksham Bansal
> >
> > Thanks
> > Prince Gupta
> > Github ID: prince776
> > ___
> > mlpack mailing list
> > mlpack@lists.mlpack.org
> > http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
>
>
___
mlpack mailing list
mlpack@lists.mlpack.org
http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
