Pranav Shyam
Pranav Shyam
> but from my own experience with the LSTM benchmark it can be very difficult - you have to make sure literally every hyperparameter is identical, and you effectively can't...
@craffel, I thought you were saying something specific about LSTM, sorry, my bad.
I can help @f0k with Theano, but only after 23rd.
Thanks! I will try and see how it goes.
I have some experience with this - I started with this same goal for Keras that took many turns resulting in things like the `Graph` model, but this hasn't been...
I could complete code for keras/theano conversion [PR: #921 on keras repo]. Most of it can be reused here, though I would like to know what would be best. The...
Theano uses NCHW (bc01) layout. `np.swapaxes()` should help in conversion I think :) Thanks for the docs, things are making more sense now..
They are the exact same versions that I used (I don't think Lasagne has seen an API breaking update since). Can you please provide the error message that you are...
Hey, my code is in Python 2. You are running Python 3 and the division `B = input.shape[0] / 2` is returning a `float` instead of an `int`. It is...
hi, thanks for your interest! I am not currently working in any direction based on ARCs and I am not aware of anyone who is. Object detection is certainly an...