Giter Site home page Giter Site logo

bregmantoolkit's People

Contributors

andrewbeaubien avatar martinthoma avatar pkmital avatar soundspotter avatar victor-shepardson avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

bregmantoolkit's Issues

Type issue when initializing features

I am using the Toolkit in a clustering algorithm with Tensorflow (see https://github.com/BinRoot/TensorFlow-Book/blob/master/ch05_clustering/Concept01_clustering.ipynb).
When the last cell runs, I get this error :

Loading ./audio_dataset/cough_1.wav
INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.CancelledError'>, Enqueue operation was cancelled
[[Node: input_producer/input_producer_EnqueueMany = QueueEnqueueManyV2[Tcomponents=[DT_STRING], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input_producer, input_producer/RandomShuffle)]]


TypeError Traceback (most recent call last)
in ()
1 with tf.Session() as sess:
2 sess.run((tf.global_variables_initializer(),tf.local_variables_initializer()))
----> 3 X, names = get_dataset(sess)
4 centroids = initial_cluster_centroids(X, k)
5 i, converged = 0, False

in get_dataset(sess)
8 for _ in range(num_files):
9 plt.figure()
---> 10 chromo_data, filename = get_next_chromogram(sess)
11
12 plt.subplot(1, 2, 1)

in get_next_chromogram(sess)
2 audio_file = sess.run(filename)
3 print('Loading {}'.format(audio_file))
----> 4 F = Chromagram(audio_file, nfft=16384, wfft=8192, nhop=2205)
5 return F.X, audio_file

/usr/local/lib/python2.7/dist-packages/bregman/features.pyc in init(self, arg, **feature_params)
141 def init(self, arg=None, **feature_params):
142 feature_params['feature']='chroma'
--> 143 Features.init(self, arg, feature_params)
144
145 class HighQuefrencyChromagram(Features):

/usr/local/lib/python2.7/dist-packages/bregman/features_base.pyc in init(self, arg, feature_params)
68 if arg:
69 self.load_audio(arg) # open file as MONO signal
---> 70 self.extract()
71
72 def _initialize(self, feature_params):

/usr/local/lib/python2.7/dist-packages/bregman/features_base.pyc in extract(self, feature_params)
211 """
212 f = self._check_feature_params(feature_params)['feature']
--> 213 self.extract_funs.get(f, self._extract_error)()
214 if self.onsets: self._extract_onsets()
215

/usr/local/lib/python2.7/dist-packages/bregman/features_base.pyc in _chroma(self)
709 lo = self.lo
710 self.lo = 63.5444 # set to quarter tone below C
--> 711 if not self._cqft():
712 return False
713 self.lo = lo # restore original lo edge

/usr/local/lib/python2.7/dist-packages/bregman/features_base.pyc in _cqft(self)
586 self._cqft_intensified()
587 else:
--> 588 self._make_log_freq_map()
589 self.CQFT=P.sqrt(P.array(P.mat(self.Q)*P.mat(P.absolute(self.STFT)**2)))
590 self._is_intensified=False

/usr/local/lib/python2.7/dist-packages/bregman/features_base.pyc in _make_log_freq_map(self)
351 self._outN = float(self.nfft/2+1)
352 if self._cqtN<1: print "warning: cqtN not positive definite"
--> 353 mxnorm = P.empty(self._cqtN) # Normalization coefficients
354 fftfrqs = self._fftfrqs #P.array([i * self.sample_rate / float(self._fftN) for i in P.arange(self._outN)])
355 logfrqs=P.array([lo_edge * P.exp(P.log(2.0)*i/bpo) for i in P.arange(self._cqtN)])

TypeError: 'float' object cannot be interpreted as an index

<matplotlib.figure.Figure at 0x7fc25ed7dfd0>

I've checked and I am using the last update of the BregmanToolkit. Does anybody know how to fix that ?

Documentation needs updating

The tutorials need some updating. Keyword arguments for features are now expanded python dicts, using the **kwargs syntax.

E.g. the following feature instances are equivalent:
LinearFrequencySpectrum(audio_dir+'fastcar.wav', nfft=2048, wfft=1024, nhop=512)
LinearFrequencySpectrum(audio_dir+'fastcar.wav', **{'nfft':2048, 'wfft':1024,'nhop':512})

Python 3 support needed

Any chance support for python3 is in the works? When I try to install I get the following:

sudo python3 setup.py install
Password:
running install
running build
running build_py
running install_lib
byte-compiling /usr/local/lib/python3.6/site-packages/bregman/audiodb.py to audiodb.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/audiodb.py", line 47
    print "IOError: Cannot open %s for reading." %(fname)
                                               ^
SyntaxError: invalid syntax

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/classifier.py to classifier.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/classifier.py", line 180
    print "sse = ", sse
                 ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/error.py to error.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/error.py", line 12
    print "Bregman error:", msg
                         ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/features.py to features.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/features.py", line 419
    print num_frames, num_hop
                   ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/features_base.py to features_base.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/features_base.py", line 240
    print "Error: must extract STFT first"
                                         ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/features_mmap.py to features_mmap.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/features_mmap.py", line 22
    print fp[m:m+mem_rows,:]
           ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/segment.py to segment.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/segment.py", line 149
    print self.segmentation[seg]
             ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/sound.py to sound.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/sound.py", line 49
    print 'sample_rate=%i' %self.sample_rate
                         ^
SyntaxError: Missing parentheses in call to 'print'

byte-compiling /usr/local/lib/python3.6/site-packages/bregman/testsignal.py to testsignal.cpython-36.pyc
  File "/usr/local/lib/python3.6/site-packages/bregman/testsignal.py", line 29
    print "TestSignal: " + msg
                       ^
SyntaxError: Missing parentheses in call to 'print'

running install_data
running install_egg_info
Removing /usr/local/lib/python3.6/site-packages/Bregman-0.11_11.14-py3.6.egg-info
Writing /usr/local/lib/python3.6/site-packages/Bregman-0.11_11.14-py3.6.egg-info

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.