search

danieldjohnson / biaxial-rnn-music-composition

A recurrent neural network designed to generate classical music.
BSD 2-Clause "Simplified" License
1.91k stars 380 forks source link

Question #27

Open Eumi opened 7 years ago

Eumi commented 7 years ago

I dont know anything about code writing..and this seems pretty complicated for me ...do i have to add code in the model? like create an output folder? idk how to do this ...i am sorry to bother but can no one put this in an easy out of the box executable code? or make a readme for dummies (like me)?
I tried 2 AI composers ..but one only generates same note length and the other one don´t lets me input own midis...while the results of this one seem outstanding! i really wanna have it =,O [sry to bother]

Eumi commented 7 years ago

I get this error on my linux =/ /home/eumi/biaxial-rnn-music-composition-master/model.py:370: UserWarning: Updating an OrderedUpdates with a non-ordered dictionary with 2+ elements could make your code non-deterministic self.walk_input: next_input /home/eumi/biaxial-rnn-music-composition-master/model.py:373: UserWarning: Updating an OrderedUpdates with a non-ordered dictionary with 2+ elements could make your code non-deterministic updates.update({hidden:newstate for hidden, newstate, layer in zip(self.walk_hiddens, new_states, self.time_model.layers) if has_hidden(layer)}) Killed

is it because i have to less memory? it takes a while till this error occurs, and it loads in midis before

chop0 commented 7 years ago

The "killed" thing is most likely because your CPU is not powerful enough. I would recommend launching a Amazon EC2 instance of t2.large (plenty of tutorials online) because using neural networks often requires a dedicated computer to do so. t2.large I think is about 2 cents / hour, and will give you 16 GB memory and a 3 GHZ processor. It also will have no crap running in the background to slow it down.

chop0 commented 7 years ago

The UserWarning errors you usually can ignore.