[mlpack] GS0C 2020

Thu Mar 12 02:10:35 EDT 2020

Hey Marcus,
Sorry for late reply, I was busy with my exams but they are over now and I
can give my complete attention here.

I want to implement Image Segmentation Models for sure. I want to go with
two models:

   1. SegNet
   2. SqueezeNet

   - Main attraction of SegNet is it's Encoder-Decoder Layer. Here the
   fully connected layers are discarded which makes our model much smaller.
   - I am planning to add this layer not specifically for SegNet but into
   the library so that it can be used for other implementation in the future
   as well. Doing this will ensure the code re usability and will increase the
   productivity and will make our library network rich!!!
   - SqueezeNet again has a Fire Module which is its main feature to
   decrease the number of input channel.
   - This will also be implemented library wide so that it can be used in
   future implementation as well.
   - Any more layers or functions required for these models will also we
   implemented library wide

Phase 1

Add all the pre-required layers and functions library wide and perform
extensive testing on them.
Testing parameters can be decided hand in hand while implementing these
layers and functions.

Phase 2

This phase will be completely dedicated to implement the architecture of
both the models.
This should not take much time as by now we will have all the required
layers and function.
We will just need to dictate the flow and build the architecture. Also
testing will be started.

Phase 3

Here we can make final tweaks as per our requirements and testing results.
Once the models are finally done we can start training them.
I am also planning to write more extensive tutorial on how to use these
models.
Also based on the results virtualisation will be created to display it in
more
understandable ways.
I am also planning to apply Segmentation Models on the video, it will be a
great way to
show off the model repo.

Both models have less training time and more efficiency when considered
against complexity of the models. Also once trained both can run on mobile
devices.
What are your thoughts about this plan?
Do I need to add more detailing?

Regards
Gopi M Tatiraju

On Sat, Mar 7, 2020 at 4:00 AM Marcus Edel <marcus.edel at fu-berlin.de> wrote:

> Hello Gopi,
>
> 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?
>
>
> Yes, sounds totally reasonable to me.
>
> I think it would be better to decide the models now, once decided we can
> start
> focusing on Model Implementation & Visualization.
>
>
> Do you already have a preference, I don't really want to dictate what
> model has
> to be implemented, but I can take a closer look at the models you find
> interesting and then we can discuss from that point?
>
> Let me know what you think.
>
> Thanks,
> Marcus
>
> On 5. Mar 2020, at 17:25, Gopi Manohar Tatiraju <deathcoderx at gmail.com>
> wrote:
>
> Hey Mentors,
>
> I just went through the idea page for GSoC 2020 Mlpack and found that this
> project was added
> https://github.com/mlpack/mlpack/wiki/SummerOfCodeIdeas#visualization-tool
>
> In my previous mail I mentioned that I was planning to do this as a part
> of
> https://github.com/mlpack/mlpack/wiki/SummerOfCodeIdeas#application-of-ann-algorithms-implemented-in-mlpack
> And also a new project regarding Improvisation of ANN module was added(
> https://github.com/mlpack/mlpack/wiki/SummerOfCodeIdeas#improvisation-and-implementation-of-ann-modules
> ).
>
> I was also planning to add the required functionalities by myself in the
> pre-coding phase but now as these are assigned to different projects I
> think we can try and implement more than 2-3 models over the course of
> summer and perform testing. Also if nobody takes up the visualisation
> project I still would like to perform that under the  Application of ANN
> Algorithms Implemented in mlpack.
>
> Regards.
> Gopi M Tatiraju
>
> On Mon, Mar 2, 2020 at 12:07 PM Gopi Manohar Tatiraju <
> deathcoderx at gmail.com> wrote:
>
>> 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.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
>>>
>>>
>>> _______________________________________________
> 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/20200312/e7981741/attachment-0001.htm>