Alex Friedman

> > > 修改了学习率和系数之后明显好多了，目前就是loss收敛过程中呈上下跳动，且幅度挺大的，不过绘制了曲线发现走势是好的，现在已经把学习率调小并且把batch_size设为4，loss看起来正常多了。阿里嘎多！ @Amelia0911 I have been using google translate to read this page as I am having issues training. I was wondering if you could list what changes...

> > > I met the same problem, have you solve it? I have not solved it. 我还没有解决它。 > > > pytorch 版本不能太新。实测0.3.1能用，否则loss会很大 Is it working by using pytorch 0.3.1...

I'm having the same issue. I was wondering if you found a solution?

I'm having the same issue. Have you found a solution?

I'm not sure where to post this but I couldn't find a better place so I figured I'd ask here. In midi_utils.py, I noticed midi_to_samples has an option for encode_length....

I am using the same code and am able to get the network to train. When I forced encode_length to be True and re-ran preprocess_songs and then train.py, gt.mid still...

Thanks! Even if it just ends up putting a note every tick between the start and end of the actual note and then has to convert back to notes with...

For the generated songs during training, changing MAX_LENGTH in train.py (128 should be 3-4 mins) For the live editor, changing num_measures should increase the length of the song.

What did you change the variables to and how are you generating the files (during training from train.py, live_editor.py etc)?