When passing a two-dimensional input layer to LSTMLayer, it will break with an uninterpretable error message:

>>> lasagne.layers.LSTMLayer((10, 20), 30)
[...]
TypeError: 'numpy.float64' object cannot be interpreted as an index

The reason is that np.prod(()) returns 1.0 as a numpy.float64 instance when computing num_units: https://github.com/Lasagne/Lasagne/blob/master/lasagne

Hi,
How to write a C# generator for model.fit_generator()? Any example please.

Is your feature request related to a problem? Please describe.
Write a tutorial on using inception_v3 or vgg to classify imagenet images. This could help starters with image classificaton.

Describe the solution you'd like
An example like mnist that shows how to train vgg16 or inception_v3 on image net or a similar but smaller task. Ideally this would include transfer learning. Startin

Hey guys,

at first thanks a lot for your work on SPNs and this nice library!
I'm currently checking out your library's features and found some missing import in the ipython notebook for tutorial 1c:

"import tensorflow as tf"

should do the trick.

thanks for your fix,
Tobias

Documentation in form of Markdown is needed.

Due to the fact that Vortex is quite close to the initial release, a good and optimized documentation is due.

Requirements

The requirement for the documentation is that every class needs to have a unique page on which every function within the said class is explained in detail in addition to a C# Example code.