nlml / bpm2 Goto Github PK

DataGen.py did not generate any wav files. When I manually created "wavs" directory and placed some wav file myself there and ran wavs_to_features.py, I got the following:
[root@node2 bpm]# python wavs_to_features.py
wavs/120 AClassicEducation_NightOwl_RAW_02_03.wav
120 bpm
Traceback (most recent call last):
File "wavs_to_features.py", line 45, in
X, y, bpms, fnames = ns.get_spectogram_training_set(n_batch=len(tracks_subset))
File "/virtual_storage/kaustubh/june2017/bpm/ExtractFeatures.py", line 284, in get_spectogram_training_set
self.append_raw_wav_chunks_and_target_vectors(wav)
File "/virtual_storage/kaustubh/june2017/bpm/ExtractFeatures.py", line 196, in append_raw_wav_chunks_and_target_vectors
rng=self.rng)
File "/virtual_storage/kaustubh/june2017/bpm/ExtractFeatures.py", line 336, in get_target_vector
target_vec = np.random.rand(resolution) * 0.001
File "mtrand.pyx", line 1347, in mtrand.RandomState.rand (numpy/random/mtrand/mtrand.c:19701)
File "mtrand.pyx", line 856, in mtrand.RandomState.random_sample (numpy/random/mtrand/mtrand.c:15527)
File "mtrand.pyx", line 167, in mtrand.cont0_array (numpy/random/mtrand/mtrand.c:6127)
TypeError: 'float' object cannot be interpreted as an integer

I got this message when I ran 'python2 fit_nn.py'. Is there something I missed to do before running it?

Traceback (most recent call last):
  File "fit_nn.py", line 102, in <module>
    history, model = fit_model(model)
  File "fit_nn.py", line 89, in fit_model
    loss = history.history['val_loss'][0]
NameError: global name 'history' is not defined

plt.subplots(figsize=(15,7))

plt.plot(history.history['loss'],'b',label='Training loss')
plt.plot(history.history['val_loss'],'r',label='Validation loss')
plt.legend(loc='upper right')
plt.xlabel('Epochs')
plt.ylabel('Loss, [mse]')

plt.show()

Hi, im interested in the analysis of your code but i dont understand your outputs, can you give and example, or if you still have the dataset it's better for me. (the link that you provide dont work https://mega.nz/#!yZZWQJwK!eBAXyY2_Qxi6McaJ3Mnj-BdQ0zfVGdYFw0xmsv8Lc4o)

Hey, I'm trying to follow a link from this website: https://nlml.github.io/neural-networks/detecting-bpm-neural-networks-update/#howtorunthecode to download the training data:
https://mega.nz/#!yZZWQJwK!eBAXyY2_Qxi6McaJ3Mnj-BdQ0zfVGdYFw0xmsv8Lc4o
but it seems to be broken