Thomas Fel
Thomas Fel
When dealing with tabular data of shape `(Nb_samples, Features)` and apply batch to tf.dataset. We may not be able to deal correctly with this kind of data, but in that...
Each model has its own input range, actually we only handle `[0, 1]` : the output of the sigmoid or clip. We could investigate what solution should be adopted: -...
as discussed by @lucashervier, it would be good to have a way to properly benchmark our inverse hessian vector product calculator on different parameter dimensions -- mnist, cifar, imagenet convolution...