Hello Hassan, focusing on a single idea sounds like a good idea to me; and there are various ideas that could be tested for GAN's over the summer.
Thanks, Marcus > On 24. Mar 2018, at 22:45, Hassan Mahmood <[email protected]> wrote: > > Hello Marcus, > For GSOC, I was aiming to do Stacked GANs and Bidirectional RNNs in > "Essential Deep Learning Modules" project. > Besides these two, there is "Improved Techniques for Training GANs" part. So, > I was thinking of doing just these two: SGANs and Improved Techniques. > This will be better for me, because I will be working on GANs all the time. > Moreover, I will be able to focus more on the efficiency of the implemented > model rather than focusing on implementing more Deep Neural Networks. > > Can I do that for GSOC or should I implement BRNNs too? > Any advice or suggestion is appreciated. > > For API, > My implementation of SGANs will go under src/mlpack/methods/ann/sgan.hpp > The header files will also be referenced in CMakeLists file. > Then the tests for the module will go under src/mlpack/tests/gan_test.cpp. > Please correct me if I am wrong. > Thanks. > > Regards, > Hassan Mahmood > >
_______________________________________________ mlpack mailing list [email protected] http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
