[Scilab-users] Scilab + neural Networks (CNN / FCNN)

Tan Chin Luh chinluh at tritytech.com
Fri Aug 30 17:29:27 CEST 2019


Hi Philipp,

Currently the only module which could deal with the CNN directly is 
IPCV, but it is just for inferencing, means we load the pre-trained 
model into Scilab thought IPCV and use it for forward pass (prediction). 
Currently the module could import models from caffe, tensorflow, and 
onnx (some bugs detected on important ONNX, will fix it).

The link you sent was our initial approach to try using the caffe-python 
binding and use the scilab-python (PIMS) module to import the model for 
inferencing as well. While PIMS is good for importing the python modules 
and use in Scilab, however, the syntax would be very similar to the 
Python, and some datatype are not compatible between 2. In this case, 
might as well we just use the python for training?

We also used caffe framework for CNN training before (using the binary) 
and using the Scilab to control the setting, since their binary is 
reading some external files for hyperparameters, and the google prototxt 
to design the CNN, which make the design much easier. This went quite 
well but the I could not see the future of caffe and seems that the 
attention was shifted to caffe2 which is now merge into pytorch.

This, infact is a good news, as pytorch does have a C++ interface, 
libtorch, which could be much easier to be integrated into Scilab, and 
we have done some testing on the integration and it seems working well, 
but to make this happened, I would call upon more developers for Scilab 
to contribute ideas and their experiences especially in C++ so the 
project could move fast.

In a few weeks time, I will create a git project, if any Scilab + C++ 
experts are interested, please continue this conversation, I believe we 
could make something up.

Thanks.

Regards,
Chin Luh



On 23/8/2019 4:24 PM, P M wrote:
> Dear experts,
>
> I am investigating if Scilab is capable to build a CNN or FCNN.
>
> So far I understood the ANN-Toolbox is not able to build these neural 
> network types.
> Also the Neural-Network-Module does not seem to support CNN's or FCNN's.
>
> However it seems to be possible by using caffee together with scilab's 
> python toolbox.
> see: 
> http://scilabipcv.tritytech.com/2017/08/21/deep-learning-cnn-with-scilab-using-caffe-model/
>
>
> Question:
> Is there work ongoing to implement CNN's and / or FCNN's into the 
> Scilab modules mentioned above?
>
> Best regards,
> Philipp
>
> _______________________________________________
> users mailing list
> users at lists.scilab.org
> http://lists.scilab.org/mailman/listinfo/users


-- 
Tan Chin Luh
Trity Technologies Sdn Bhd
Tel : +603 80637737
HP : +6013 3691728

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.scilab.org/pipermail/users/attachments/20190830/67477c0f/attachment.htm>


More information about the users mailing list