Code for “Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation”
Home Page: https://salu133445.github.io/bmusegan/
License: MIT License
I tried to train bmusegan model by the source code in musegan github , it always stop in the 'initializing variables' step and jump out . So I check the source program and find the problem maybe happen in the main.py , when we choose second_stage training phase , the program still jump into first_stage's class GAN and cause the initial wrong .
If musegan/bmusegan is need two stages train and each stage need change some config parameters (like stage_phase)?
I try use the recommend data source --lastfm_alternative_5b_phrase.npy for train musegan/bmusegan , but it give a error feed :
It's seem the dataset is have wrong form, do you know what the problem in detail.
Hi, I downloaded the data 'lastfm_alternative_8b_phrase.npy' and I tried this command: python store_to_sa.py lastfm_alternative_8b_phrase.npy --name=lastfm_alternative_8b_phrase
And it said that: Failed to interpret file 'lastfm_alternative_8b_phrase.npy' as a pickle
Traceback (most recent call last):
File "main.py", line 61, in
train_end2end()
File "main.py", line 52, in train_end2end
end2end_gan = End2EndGAN(sess, MODEL_CONFIG)
File "/mnt/d/Constantine/BinaryMuseGAN/musegan/bmusegan/models.py", line 629, in init
self.build()
File "/mnt/d/Constantine/BinaryMuseGAN/musegan/bmusegan/models.py", line 651, in build
slope_tensor=self.slope_tensor, name='G')
File "/mnt/d/Constantine/BinaryMuseGAN/musegan/bmusegan/components.py", line 199, in init
self.tensor_out, self.nets, self.preactivated = self.build(config)
File "/mnt/d/Constantine/BinaryMuseGAN/musegan/bmusegan/components.py", line 241, in build
return (tf.compat.v1.concat([nn.tensor_out for nn in nets['private']], -1), nets,
KeyError: 'private'
Hi sir, I had this bug when I try to run this code, could you help with this bug please? Thank you!
I'm trying to recreate your results but cannot seem to find a relevant requirements.txt or Pipfile to install dependencies from.
Do you have this repository and it's dependencies local to your machine? If so, could you commit that lockfile?
File "/usr/local/lib/python3.6/dist-packages/pypianoroll/outputs.py", line 139, in to_pretty_midi
f"Expect BinaryTrack or StandardTrack, but got {type(track)}."
ValueError: Expect BinaryTrack or StandardTrack, but got <class 'pypianoroll.track.Track'>.
### How do I debug this error?
When I run the train stage (the second stage) of musegan/bmusegan , it would jump out and remind me the OOM problem
But at same time , my GPU memory >10G for free, it is weird. Do you know what is problem?
How can Inference be done? after traiining
I got an error while training using the default params and config and training data. Does this have to do with my machine? I'm using a 1080ti
--------------------------------------------------------------------------------
[*] Initializing variables...
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1130 thread 1 bound to OS proc set 1
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1131 thread 2 bound to OS proc set 2
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1132 thread 3 bound to OS proc set 3
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1133 thread 4 bound to OS proc set 4
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1134 thread 5 bound to OS proc set 5
================================ Training Start ================================
-------------------------------- Epoch 0 Start ---------------------------------
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1097 thread 6 bound to OS proc set 6
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1158 thread 10 bound to OS proc set 10
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1156 thread 8 bound to OS proc set 8
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1155 thread 7 bound to OS proc set 7
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1159 thread 11 bound to OS proc set 11
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1157 thread 9 bound to OS proc set 9
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1160 thread 12 bound to OS proc set 0
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1162 thread 13 bound to OS proc set 1
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1164 thread 14 bound to OS proc set 2
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1165 thread 15 bound to OS proc set 3
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1166 thread 16 bound to OS proc set 4
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1167 thread 17 bound to OS proc set 5
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1099 thread 18 bound to OS proc set 6
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1168 thread 19 bound to OS proc set 7
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1169 thread 20 bound to OS proc set 8
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1170 thread 21 bound to OS proc set 9
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1171 thread 22 bound to OS proc set 10
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1172 thread 23 bound to OS proc set 11
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1173 thread 24 bound to OS proc set 0
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1174 thread 25 bound to OS proc set 1
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1175 thread 26 bound to OS proc set 2
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1176 thread 27 bound to OS proc set 3
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1177 thread 28 bound to OS proc set 4
OMP: Info #250: KMP_AFFINITY: pid 1048 tid 1178 thread 29 bound to OS proc set 5
2019-05-30 04:57:58.837415: F ./tensorflow/core/util/mkl_util.h:607] Check failed: dims == sizes.size() (5 vs. 4)
Aborted (core dumped)
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.