jazdev / genrexpose Goto Github PK

what are the assumptions you took in this project

I just want to know what machine learning algorithm did you use?
Did you use any type of neural network?

I run genreXpose on WIndows 10, with Python 2.7.13 | Anaconda 4.3.0 (64-bit), sklern version = '0.18.1', but it seems have a problem.

Traceback (most recent call last):
File "classifier.py", line 95, in
train_avg, test_avg, cms = train_model(X, y, "ceps", plot=True)
File "classifier.py", line 25, in train_model
cv = ShuffleSplit(n=len(X), n_iterations=1, test_fraction=0.3, indices=True, random_state=0)
TypeError: init() got an unexpected keyword argument 'indices'

It seems the sklern has updated all codes to python 3, one part of the file:

class ShuffleSplit(BaseShuffleSplit):
......
Examples
--------
>>> from sklearn import cross_validation
>>> rs = cross_validation.ShuffleSplit(4, n_iter=3, test_size=.25, random_state=0)

The post on your blog which shows underlying technologies of genreXpose isn't there anymore. Can you please re-post it?

Thanks

Hello,

I have installed and tried to predict the genre of a rock song. It predicted it as 'country'. Then I tried to predict the song from the data set. I tried to predict country.00011.au.wav song from the data folder. It predicted it as 'hiphop'.

Please let me know if I am doing anything wrong. Please suggest.

Thanks,
Sateesh

Would you like to provide the Python 3 version? Thanks.