msieg/deep-music-visualizer

The Deep Visualizer uses BigGAN (Brock et al., 2018) to visualize music.

deep-music-visualizer's Issues

StyleGAN integration

Hello,

Are there any limitations to this approach with other GAN models?

Update: No limitations, just an adaptation required.

Export Previously Used Classes

I know of the previous classes parameter but how can I save the classes to use whenever

Error code 12 (Cannot allocate memory)

python3 visualize.py --song ooo002.mp3 --resolution 512

VPS:

• 6 core
• 16 GB RAM
• 50 GB+ free SSD sapce
• Ubuntu 18.04

Generating frames

  0%|                                                                                                                                                                 | 0/14 [00:00<?, ?it/s]Traceback (most recent call last):
  File "visualize.py", line 382, in <module>
    output = model(noise_vector, class_vector, truncation)
  File "/home/user/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/user/.local/lib/python3.6/site-packages/pytorch_pretrained_biggan/model.py", line 295, in forward
    z = self.generator(cond_vector, truncation)
  File "/home/user/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/user/.local/lib/python3.6/site-packages/pytorch_pretrained_biggan/model.py", line 239, in forward
    z = layer(z, cond_vector, truncation)
  File "/home/user/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/user/.local/lib/python3.6/site-packages/pytorch_pretrained_biggan/model.py", line 190, in forward
    x = self.conv_3(x)
  File "/home/user/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/user/.local/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 345, in forward
    return self.conv2d_forward(input, self.weight)
  File "/home/user/.local/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 342, in conv2d_forward
    self.padding, self.dilation, self.groups)
RuntimeError: [enforce fail at CPUAllocator.cpp:64] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 4026531840 bytes. Error code 12 (Cannot allocate memory)

  0%|                                                                                                                                                                 | 0/14 [01:36<?, ?it/s]

Problem with torch

Ok so this time I installed everything for itself.
first git clone https://github.com/msieg/deep-music-visualizer.git
then cd deep-music-visualizer
then pip install tqdm
then pip install librosa
and so on, the full list of requirements.txt.

And it looks like the problem is torch. Maby this helps. Or maby the problem is somewhere else, i dont know

Help!!! RuntimeError: Numpy is not available

Generating frames

0%| | 0/16 [00:33<?, ?it/s]
Traceback (most recent call last):
File "D:\myproject\deep-music-visualizer-master\visualize.py", line 554, in
output_cpu = output.cpu().data.numpy()
RuntimeError: Numpy is not available

configure features error

It doesn't work. how to run this python?

OS Error when argument duration exceeds clip duration

The visualize process fails to output a file when the specified duration is longer than the duration of the song input.

Could most likely be resolved with a simple check of clip duration. ie,

duration = min(config.duration, clip.duration)

Please how do you set a Random Seed

Hi @msieg

I noticed that there there isn't a parameter setting for random seed for the noise because every time i run it, it creates a new video. Please how can i set the random seed or make it product the same video?

Thanks,
Babs

License?

What is license on this one?

errors with gcloud vm in tutorial --resolution 512

I followed the suggestion of the README and tried this out on the recommended gcloud VM, but I can't get a 512 size to generate. Is there a workaround (multiple GPUs?) I'm not familiar with pytorch so I don't know if this is a VM sizing issue or a problem with how this project batches data to CUDA memory or something. My audio is a little over 3 minutes.

Traceback (most recent call last):
  File "visualize.py", line 378, in <module>
    output = model(noise_vector, class_vector, truncation)
  File "/home/johnny/viz/venv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/johnny/viz/venv/lib/python3.7/site-packages/pytorch_pretrained_biggan/model.py", line 295, in forward
    z = self.generator(cond_vector, truncation)
  File "/home/johnny/viz/venv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/johnny/viz/venv/lib/python3.7/site-packages/pytorch_pretrained_biggan/model.py", line 239, in forward
    z = layer(z, cond_vector, truncation)
  File "/home/johnny/viz/venv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/johnny/viz/venv/lib/python3.7/site-packages/pytorch_pretrained_biggan/model.py", line 198, in forward
    out = x + x0
RuntimeError: CUDA out of memory. Tried to allocate 3.75 GiB (GPU 0; 11.17 GiB total capacity; 8.91 GiB already allocated; 365.44 MiB free; 10.37 GiB reserved in total by PyTorch)

audioread.exceptions.NoBackendError

Exit error code 1

Using legacy 'setup.py install' for scipy, since package 'wheel' is not installed.
Using legacy 'setup.py install' for librosa, since package 'wheel' is not installed.
Using legacy 'setup.py install' for audioread, since package 'wheel' is not installed.
Using legacy 'setup.py install' for resampy, since package 'wheel' is not installed.
Using legacy 'setup.py install' for moviepy, since package 'wheel' is not installed.
Using legacy 'setup.py install' for proglog, since package 'wheel' is not installed.
Using legacy 'setup.py install' for boto3, since package 'wheel' is not installed.
Installing collected packages: scipy, s3transfer, requests, pillow, packaging, numba, joblib, cffi, appdirs, torch, soundfile, scikit-learn, resampy, proglog, pooch, imageio-ffmpeg, imageio, decorator, boto3, audioread, pytorch-pretrained-biggan, moviepy, librosa
Running setup.py install for scipy ... error
ERROR: Command errored out with exit status 1:
command: 'c:\users\rossp\appdata\local\programs\python\python39\python.exe' -u -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py'"'"'; file='"'"'C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(file) if os.path.exists(file) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' install --record 'C:\Users\Rossp\AppData\Local\Temp\pip-record-es5qji36\install-record.txt' --single-version-externally-managed --compile --install-headers 'c:\users\rossp\appdata\local\programs\python\python39\Include\scipy'
cwd: C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082
Complete output (146 lines):
C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py:114: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
import imp

Note: if you need reliable uninstall behavior, then install
with pip instead of using `setup.py install`:

  - `pip install .`       (from a git repo or downloaded source
                           release)
  - `pip install scipy`   (last SciPy release on PyPI)


lapack_opt_info:
lapack_mkl_info:
No module named 'numpy.distutils._msvccompiler' in numpy.distutils; trying from distutils
customize MSVCCompiler
  libraries mkl_rt not found in ['c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\lib', 'C:\\', 'c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\libs']
  NOT AVAILABLE

openblas_lapack_info:
  libraries openblas not found in ['c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\lib', 'C:\\', 'c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\libs']
get_default_fcompiler: matching types: '['gnu', 'intelv', 'absoft', 'compaqv', 'intelev', 'gnu95', 'g95', 'intelvem', 'intelem', 'flang']'
customize GnuFCompiler
Could not locate executable g77
Could not locate executable f77
customize IntelVisualFCompiler
Could not locate executable ifort
Could not locate executable ifl
customize AbsoftFCompiler
Could not locate executable f90
customize CompaqVisualFCompiler
Could not locate executable DF
customize IntelItaniumVisualFCompiler
Could not locate executable efl
customize Gnu95FCompiler
Could not locate executable gfortran
Could not locate executable f95
customize G95FCompiler
Could not locate executable g95
customize IntelEM64VisualFCompiler
customize IntelEM64TFCompiler
Could not locate executable efort
Could not locate executable efc
customize PGroupFlangCompiler
Could not locate executable flang
don't know how to compile Fortran code on platform 'nt'
  NOT AVAILABLE

openblas_clapack_info:
  libraries openblas,lapack not found in ['c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\lib', 'C:\\', 'c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\libs']
  NOT AVAILABLE

flame_info:
  libraries flame not found in ['c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\lib', 'C:\\', 'c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\libs']
  NOT AVAILABLE

atlas_3_10_threads_info:
Setting PTATLAS=ATLAS
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries tatlas,tatlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries lapack_atlas not found in C:\
  libraries tatlas,tatlas not found in C:\
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
  libraries tatlas,tatlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
<class 'numpy.distutils.system_info.atlas_3_10_threads_info'>
  NOT AVAILABLE

atlas_3_10_info:
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries satlas,satlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries lapack_atlas not found in C:\
  libraries satlas,satlas not found in C:\
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
  libraries satlas,satlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
<class 'numpy.distutils.system_info.atlas_3_10_info'>
  NOT AVAILABLE

atlas_threads_info:
Setting PTATLAS=ATLAS
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries ptf77blas,ptcblas,atlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries lapack_atlas not found in C:\
  libraries ptf77blas,ptcblas,atlas not found in C:\
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
  libraries ptf77blas,ptcblas,atlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
<class 'numpy.distutils.system_info.atlas_threads_info'>
  NOT AVAILABLE

atlas_info:
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries f77blas,cblas,atlas not found in c:\users\rossp\appdata\local\programs\python\python39\lib
  libraries lapack_atlas not found in C:\
  libraries f77blas,cblas,atlas not found in C:\
  libraries lapack_atlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
  libraries f77blas,cblas,atlas not found in c:\users\rossp\appdata\local\programs\python\python39\libs
<class 'numpy.distutils.system_info.atlas_info'>
  NOT AVAILABLE

lapack_info:
  libraries lapack not found in ['c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\lib', 'C:\\', 'c:\\users\\rossp\\appdata\\local\\programs\\python\\python39\\libs']
  NOT AVAILABLE

c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\system_info.py:1849: UserWarning:
    Lapack (http://www.netlib.org/lapack/) libraries not found.
    Directories to search for the libraries can be specified in the
    numpy/distutils/site.cfg file (section [lapack]) or by setting
    the LAPACK environment variable.
  return getattr(self, '_calc_info_{}'.format(name))()
lapack_src_info:
  NOT AVAILABLE

c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\system_info.py:1849: UserWarning:
    Lapack (http://www.netlib.org/lapack/) sources not found.
    Directories to search for the sources can be specified in the
    numpy/distutils/site.cfg file (section [lapack_src]) or by setting
    the LAPACK_SRC environment variable.
  return getattr(self, '_calc_info_{}'.format(name))()
  NOT AVAILABLE

Running from scipy source directory.
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py", line 474, in <module>
    setup_package()
  File "C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py", line 470, in setup_package
    setup(**metadata)
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\core.py", line 135, in setup
    config = configuration()
  File "C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py", line 388, in configuration
    config.add_subpackage('scipy')
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\misc_util.py", line 1019, in add_subpackage
    config_list = self.get_subpackage(subpackage_name, subpackage_path,
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\misc_util.py", line 985, in get_subpackage
    config = self._get_configuration_from_setup_py(
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\misc_util.py", line 927, in _get_configuration_from_setup_py
    config = setup_module.configuration(*args)
  File "scipy\setup.py", line 15, in configuration
    config.add_subpackage('linalg')
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\misc_util.py", line 1019, in add_subpackage
    config_list = self.get_subpackage(subpackage_name, subpackage_path,
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\misc_util.py", line 985, in get_subpackage
    config = self._get_configuration_from_setup_py(
  File "c:\users\rossp\appdata\local\programs\python\python39\lib\site-packages\numpy\distutils\misc_util.py", line 927, in _get_configuration_from_setup_py
    config = setup_module.configuration(*args)
  File "scipy\linalg\setup.py", line 19, in configuration
    raise NotFoundError('no lapack/blas resources found')
numpy.distutils.system_info.NotFoundError: no lapack/blas resources found
----------------------------------------

ERROR: Command errored out with exit status 1: 'c:\users\rossp\appdata\local\programs\python\python39\python.exe' -u -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py'"'"'; file='"'"'C:\Users\Rossp\AppData\Local\Temp\pip-install-ci31gds8\scipy_7d706f3f907b40dfb23fcaa90915f082\setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(file) if os.path.exists(file) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' install --record 'C:\Users\Rossp\AppData\Local\Temp\pip-record-es5qji36\install-record.txt' --single-version-externally-managed --compile --install-headers 'c:\users\rossp\appdata\local\programs\python\python39\Include\scipy' Check the logs for full command output.

Has any one tried with audio with duration more than 4 minutes.

When I put an audio with duration more than 4 minutes the execution doesn't complete and stops at around 72-85% and nothing happens. Any solutions?

I cant seem to get the code to work

I'm brand new to all of this, but I'm very motivated to learn. I've downloaded the files, I have runwayml and Python3.0.1 but every time I enter the code it says syntax error. I've never done anything like this and it snot very intuitive, so any help is greatly appreciated!

HELP!!!

File "visualize.py", line 574, in
clip.write_videofile('my_movie.mp4',audio_codec='aac')
File "D:\Download\anaconda3\envs\tensorflow-gpu\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "D:\Download\anaconda3\envs\tensorflow-gpu\lib\site-packages\moviepy\decorators.py", line 54, in requires_duration
return f(clip, *a, **k)
File "D:\Download\anaconda3\envs\tensorflow-gpu\lib\site-packages\decorator.py", line 232, in fun
return caller(func, *(extras + args), **kw)
File "D:\Download\anaconda3\envs\tensorflow-gpu\lib\site-packages\moviepy\decorators.py", line 118, in use_clip_fps_by_default
names = inspect.getfullargspec(func).args[1:]
NameError: name 'func' is not defined

TypeError: must be real number, not NoneType when writing with moviepy

I receive the following error using the demo. I'll try to resolve myself, and update the issue if I find a fix.

python visualize.py --song beethoven.mp3 --duration 15 --resolution 128

Reading audio


Generating input vectors

100%|█████████████████████████████████████████████████████████| 2586/2586 [00:02<00:00, 1222.00it/s]


Generating frames

100%|███████████████████████████████████████████████████████████████| 21/21 [04:21<00:00, 12.45s/it]
Moviepy - Building video output.mp4.
MoviePy - Writing audio in outputTEMP_MPY_wvf_snd.mp4
MoviePy - Done.
Moviepy - Writing video output.mp4

Traceback (most recent call last):
  File "visualize.py", line 400, in <module>
    clip.write_videofile(outname,audio_codec='aac')
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/decorator.py", line 231, in fun
    return caller(func, *(extras + args), **kw)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/moviepy/decorators.py", line 54, in requires_duration
    return f(clip, *a, **k)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/decorator.py", line 231, in fun
    return caller(func, *(extras + args), **kw)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/moviepy/decorators.py", line 135, in use_clip_fps_by_default
    return f(clip, *new_a, **new_kw)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/decorator.py", line 231, in fun
    return caller(func, *(extras + args), **kw)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/moviepy/decorators.py", line 22, in convert_masks_to_RGB
    return f(clip, *a, **k)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/moviepy/video/VideoClip.py", line 307, in write_videofile
    logger=logger)
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/moviepy/video/io/ffmpeg_writer.py", line 216, in ffmpeg_write_video
    ffmpeg_params=ffmpeg_params) as writer:
  File "/Users/mark/miniconda3/envs/random/lib/python3.7/site-packages/moviepy/video/io/ffmpeg_writer.py", line 88, in __init__
    '-r', '%.02f' % fps,
TypeError: must be real number, not NoneType

scipy won't install on MacOS

I don't know if this is a Mac-only problem, but I can't get scipy 1.1 to install. The install script fails. (Error listed below)

But beyond that, is there any way to replace toimage(), the only function required from scipy? That function was deprecated and then removed from the package long ago. The code in question is:

output_cpu=output.cpu().data.numpy()

#convert to image array and add to frames
for out in output_cpu:    
    im=np.array(toimage(out))
    frames.append(im)

A rewrite of that, perhaps using the Image class, seems to be in order.

Anyway, here's the absurd error I'm getting from scipy's setup.py:
ERROR: Command errored out with exit status 1:
command: /Library/Frameworks/Python.framework/Versions/3.9/bin/python3.9 -u -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/private/var/folders/4n/58lgvxkx24d7q6y0pbkz7df00000gp/T/pip-install-c0krthbx/scipy_32ea160cb9384bc1976f352cc1c918b9/setup.py'"'"'; file='"'"'/private/var/folders/4n/58lgvxkx24d7q6y0pbkz7df00000gp/T/pip-install-c0krthbx/scipy_32ea160cb9384bc1976f352cc1c918b9/setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(file) if os.path.exists(file) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' install --record /private/var/folders/4n/58lgvxkx24d7q6y0pbkz7df00000gp/T/pip-record-ycegi919/install-record.txt --single-version-externally-managed --compile --install-headers /Library/Frameworks/Python.framework/Versions/3.9/include/python3.9/scipy
cwd: /private/var/folders/4n/58lgvxkx24d7q6y0pbkz7df00000gp/T/pip-install-c0krthbx/scipy_32ea160cb9384bc1976f352cc1c918b9/

IMPORTANT: Repository is not maintained

Dear all,

this repository is not maintained by @msieg since years.
Check out the forks for more up-to-date repos.

OSError: sndfile library not found

I got this message when I tried to run the visualizer. Anyone know what I should do? I am on a mac running macOS Monterey

`Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/soundfile.py", line 142, in
raise OSError('sndfile library not found')
OSError: sndfile library not found

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/kjzoosh/deep-music-visualizer/visualize.py", line 1, in
import librosa
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/librosa/init.py", line 209, in
from . import core
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/librosa/core/init.py", line 6, in
from .audio import * # pylint: disable=wildcard-import
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/librosa/core/audio.py", line 8, in
import soundfile as sf
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/soundfile.py", line 162, in
_snd = _ffi.dlopen(_os.path.join(
OSError: cannot load library '/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib': dlopen(/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib, 0x0002): tried: '/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file)`

Works fine on windows using 3.7 mini conda environment! -How to replace BigGan model with pkl file....???

Hey thanks for this, super wonderful. Works well on my windows machine in a 3.7 miniconda environment... just pip install the packages when you run the vizualize.py line...... super curious if anyone has had luck replacing the BIGgan model with a network pkl file? hoping to use my own model.... any success?

R

Syntax Error/invalid syntax

Every time I try to get this run I get an Syntax Error.
Im from germany and its so difficult to find a solution if you dont nativ speak english.

I tried it with different versions of python, I tried it with google colab, I tried it with internet sites where you can run python.
But every time Syntax Error/invalid syntax.

I tried with the whole code, with only one line each, with the linux lines (i have windows), tried the code from the read me but nothing works. Still syntax error.

Im new to AI and this things, so Im sure I make a mistake. But in the whole Internet I cant find one single video or article that explains exact what you have to do. Do I need anything else installed than python? Do I need another code?

I hope somebody can help me.

Cuda error with 3090

I can run the test just fine until it comes time for the rubber to hit the road.
Is anybody else experiencing this? and/or, how did you fix it?

Reading audio 


Generating input vectors 

100%|█████████████████████████████████████| 2586/2586 [00:01<00:00, 2400.27it/s]


Generating frames 

  0%|                                                    | 0/86 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/home/al/deep-music-visualizer/visualize.py", line 378, in <module>
    output = model(noise_vector, class_vector, truncation)
  File "/home/al/anaconda3/envs/ddvisualizer/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/al/anaconda3/envs/ddvisualizer/lib/python3.9/site-packages/pytorch_pretrained_biggan/model.py", line 293, in forward
    cond_vector = torch.cat((z, embed), dim=1)
RuntimeError: CUDA error: no kernel image is available for execution on the device
`

Running on GPU

I got this running and enjoy it, but I would like to run it on my GPU. Is this possible? I played around a bit with numba which is supposed to make it possible but I am not sure of which changes I would have to make in order to get this to work.

command not found: librosa

File "/Users/xxxxxxxxxxxxxx/deep-music-visualizer/visualize.py", line 1, in
import librosa
ModuleNotFoundError: No module named 'librosa'

Can't run because of deprecated scipy.misc functions

Love this project! Python noob, can't get it to work. Working on MacOS Catalina, Python 3.8.

Changed line 7. old: 'from scipy.misc import toimage'
new: 'from PIL import Image'

This affects line 384: 'im=np.array(toimage(out))'
and 398: 'clip = mpy.ImageSequenceClip(frames, fps=22050/frame_length)'

Despite a lot of attempted modification and some beginner Python tutorials, I cannot get this code to run.
Please help!!

How to add my own images and get the output?

Can't install the dependencies

none of the dependencies will even install, I've been troubleshooting for hours

Can't get it to work. And have little idea about python

I tried to run this on my win10 machine.
But something about my python is not right, somethings were not installed and so it all did not run.
What can I do in 2022 to run this?
Markus