[mlpack] GS0C 2020

[Gopi Manohar Tatiraju]

 Hey Marcus,
I agree that we should focus on one topic only, I am more interested in
Segmentation Models.

I started implementing SegNet(https://github.com/mlpack/models/issues/54)
but as UpSampling Layer is not implemented in mlpack I got stuck. As you
can see in the discussion said that they will implement of the layer is in
progress and I think soon we will know the status.

Also, I did some more reading regarding Segmentation Models, I think
reading survey papers on this topic would be a better option as by that we
can analyze the speed and requirements of the model and then can implement
those which provides better timings. What do you think?

I read this article(
https://medium.com/@arthur_ouaknine/review-of-deep-learning-algorithms-for-image-semantic-segmentation-509a600f7b57
)
[image: image.png]

I think it would be better to decide the models now, once decided we can
start focusing on Model Implementation & Visualization.

Regards.
Gopi M Tatiraju

On Sun, Mar 1, 2020 at 11:54 PM Marcus Edel <marcus.edel at fu-berlin.de>
wrote:

> Hello Gopi,
>
> Regarding the proposal are there any specific models you have in mind?
>
> As mentioned on the issue itself, I would start with a model that provides
> fast
> timings for the CPU and GPU as well, mobilenet or squeezenet are two
> examples.
> Personally, I would focus on a single topic, so either object detection or
> segmentation, rather have one polished model instead of two that are okay.
>
> About the visualize part, the cool thing about the models repo is, we
> don't have
> to care so much about dependencies, so if you think OpenCV is the best
> option,
> fine with me.
>
> Thanks,
> Marcus
>
> On 28. Feb 2020, at 15:25, Gopi Manohar Tatiraju <deathcoderx at gmail.com>
> wrote:
>
> Hey,
> Regarding adding more models in Mlpack, you are already familiar with my
> basic idea. I have already started working on it and by now I have a good
> idea about the functionality and architecture of Mlpack library.
>
> https://github.com/mlpack/models/issues/54
>
> Regarding the proposal are there any specific models you have in mind? I
> am thinking about models on Image Segmentation and Detection.
>
> Atleast two models which can be implemented directly without adding any
> new layer in Mlpack and remaining by adding new layers throughout the
> library so that they can be used for future implementations as well
> increasing the functionality of the library. This will also asure that we
> will be implementing atleast 2 models as creating the architecture only
> using Mlpack's already implemented functionality will be a bit easier than
> to implement models and layers.
>
> Also I think we need a separate module to visualize these algorithms, we
> can do that using OpenCV. This will be very helpful as image processing is
> only as useful if we can visualize it.
>
> What are your views?
>
> Project:
> https://github.com/mlpack/mlpack/wiki/SummerOfCodeIdeas#application-of-ann-algorithms-implemented-in-mlpack
> Mentors: Marcus Edel, Sumedh Ghaisas, Shikhar Jaiswal
> Reagrds
>
> Gopi M Tatiraju
> deathcoderx at gmail.com
> https://github.com/heisenbuug
> _______________________________________________
> mlpack mailing list
> mlpack at lists.mlpack.org
> http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20200302/e416da54/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 76558 bytes
Desc: not available
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20200302/e416da54/attachment-0001.png>