Re:Outrageously Large Neural Networks: The Sparsely-Gated Mi...
by raverbashing on Monday January 30, 2017 @09:26AM
(#13521384)
I tried the Cats/Dogs exercise on Kaggle
Getting TS to work was hard. Ended up opting for Keras/Theano, TS would be slower for the same problems CPU only
Then getting all tensor shapes to "fit together", to run, then to converge, getting the right non-linearity for each layer, then finding out overfitting is a B! with a capital B
Getting TS to work was hard. Ended up opting for Keras/Theano, TS would be slower for the same problems CPU only
Then getting all tensor shapes to "fit together", to run, then to converge, getting the right non-linearity for each layer, then finding out overfitting is a B! with a capital B
It is hard