[mlpack] Regarding Implementation of SqeeuzeNet

[Marcus Edel]

Hello Gopi,

mlpack uses Armadillo: http://arma.sourceforge.net/ to handel matrix types, I
suggest to look at the  Matrix, Vector, Cube and Field Classes section:
http://arma.sourceforge.net/docs.html#part_classes.

Hopefully that is helpful, let me know if I should clarify anything.

Thanks,
Marcus

> On 4. Mar 2020, at 19:08, Gopi Manohar Tatiraju <deathcoderx at gmail.com> wrote:
> 
> Hey Marcus,
> 
> Regarding SqueezeNet, I read about the model and saw some implementation of the model in Python using Keras. There the model is implemented using Tensors. The input is taken as keras.engine.input_layer.Input() <https://keras.io/layers/core/> 
> 
> I was not able to find a way to instantiate tensors in mlpack itself. Shall I use some other library for that? Or do we need to add that functionality in the library? 
> 
> I want to list out all the requirements for the models so that I can add any if missing functionalities before the coding phase(GSoC) commences, so that in summer only building models and training and testing can be done.
> 
> Regards
> Gopi M Tatiraju
> 
> _______________________________________________
> 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/20200306/23ac8fbf/attachment.htm>