Fit a model on data generated batch-by-batch by a Python generator. The generator is run in parallel to the model, for efficiency, and

Fit a model on data generated batch-by-batch by a Python generator. The generator is run in parallel to the model, for efficiency, and

Repeat the elements of a tensor along an axis, like np.repeat. If x has shape (s1, s2, s3) and axis=1, the output will have shape (s1, s2 * r

Save weights from all layers to a HDF5 files.

Function that loads the dataset into shared variables The reason we store our dataset in shared variables is to allow Theano to copy

Abstract method to loop over some data in batches.

All the recurrent layers share the same interface, so we can run through them with a single function.

Abstract method to loop over some data in batches.

modes: binary, count, tfidf, freq

prune: sequence of characters to filter out

Abstract fit function for f(ins). Assume that f returns a list, labelled by out_labels.

Return whether the session is set to run on GPU or not (i.e. on CPU).

Process a layer, adding its node to the graph and creating edges to its outputs. `connect_to` specify where the output of th

Data providing function: This function is separated from model() so that hyperopt won't reload data for each evaluation run.

Returns a dict mapping layer to their name in the model