Hao Song

Hi @akshitasingh0706, thanks for bringing this up. As projections for text datasets could vary a lot depending on the data structure and pre-processing, we don't have a specific text dataset...

Do you have a TensorFlow code/notebook running at the same time? It might be Tensorflow reserves all the GRAM so not much is left for Torch to use.

> Do we think users are ever going to have equal reference and test batch sizes in practice? I'd guess almost always the reference set is going to be much...

Now the linear-time estimator also uses Gaussian under null for the test threshold, so no permutation is required. It should be the fastest at the cost of lower test power...

> @Srceh final thing, were you planning on adding tests and updating the docs? Good question, haven't worked on anything specific, but happy to follow any suggestion.

> > Good question, haven't worked on anything specific, but happy to follow any suggestion. > > We'd usually aim to ensure any new functionality added to the library is...

> Left a number of comments related to the PyTorch implementation. Let's work through those first and then we can apply the desired changes to TensorFlow as well. TF version...

> @Srceh I've just merged the `score`/`predict` refactoring (#489). This will have introduced a few conflicts you need to resolve. It should simplify your life wrt to the implementation in...

> Are none of the other examples affected at all? They still work with the updated kernels producing the same results? Would be great if true, but it sounds almost...