I cannot find a definitive answer to the question of whether keras scipy supports sparse matrices as training / testing vectors. I read this link, which apparently implies that it is not https://www.kaggle.com/c/walmart-recruiting-trip-type-classification/forums/t/18154/training-neural-network- with-scipy-sparse-matrix . This PR seems to imply what it does, although https://github.com/fchollet/keras/pull/1886 . Documents are not indicated explicitly - can someone shed light?
thank
No one has answered this question yet.
: