msm1089

@csurfer Thanks for creating this extension. I am wondering if you ever found anything that might allow the variables in previous cells to be used?

UPDATE In the end I solved it by changing the last else block: ``` else: start_mask = (1

@ianni67 Did you ever give learning form multiple examples a go? Sounds interesting...like you could style a piece of audio as a genre, by learning from a bunch of tracks...

@ianni67 @lkoz If you use longer inputs, you can change the value in the 4th cell, below line: `S = np.log1p(np.abs(S[:,:430]))` So for 30s, use 430 x 3 = 1290...

@piteight Did you fix your blank screen error? It is unrelated to gpu, but if you did want to try running on gpu, all you need to do is change...

Fixing issue https://github.com/DmitryUlyanov/neural-style-audio-tf/issues/5

It only works for some methods of running notebooks unfortunately. Normal jupyter is fine and jupyter lab (up to v3.0.2 at least). How are you running it, and what versions?...

I just tried this and get a different result:  I created a new blank notebook in VS Code, with default server, i.e. local. Were you connecting to some remote,...

The problem appears to be at the point it tries to get the sessions. It manages to construct the url to query, e.g. http://localhost:8888/api/sessions?token=8b3cbe84593547819ed5e78c97a6cadda392f2ce7469bcdb, but connection to this is refused...

I also get this issue. Thanks for peoples suggestions above to resolve it, but none of them worked for me. I used an ecosystem.config.js and saw identical behaviour to running...