kahst / acousticeventdetection Goto Github PK

Good afternoon.

Can you specify the different dependencies that you used for this code? The CUDA version, CuDNN, python libraries, theano, etc?

I'm having a lot of problems using your code.

Thanks.

Theano - v1.0.1
Lasagne - v0.2.dev1

Command:
python AED_test.py --filenames 'dataset/schreien_scream.wav' --modelname 'AED_Example_Run_model.pkl' --overlap 4 --results 5 --confidence 0.01

HANDLING IMPORTS...
Using cuDNN version 7103 on context None
Mapped name None to device cuda: GeForce GT 650M (0000:01:00.0)
...DONE!
IMPORTING MODEL... DONE!
Traceback (most recent call last):
  File "AED_test.py", line 159, in <module>
    TEST_NET = getPredictionFuntion(NET)
  File "AED_test.py", line 71, in getPredictionFuntion
    net_output = l.get_output(net, deterministic=True)
  File "/home/enniya/miniconda2/lib/python2.7/site-packages/lasagne/layers/helper.py", line 197, in get_output
    all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)
  File "/home/enniya/miniconda2/lib/python2.7/site-packages/lasagne/layers/conv.py", line 352, in get_output_for
    conved = self.convolve(input, **kwargs)
  File "/home/enniya/miniconda2/lib/python2.7/site-packages/lasagne/layers/conv.py", line 643, in convolve
    if self.num_groups > 1:  # pragma: no cover
AttributeError: 'Conv2DLayer' object has no attribute 'num_groups'

Hello, @kahst
Thank you for your package though I am still not able to use it.
I followed you installation instruction and downloaded pre-trained model:"sh model/fetch_model.sh". When I executed script:"python AED_test.py --filenames 'dataset/schreien_scream.wav' --modelname 'AED_Example_Run_model.pkl' --overlap 4 --results 5 --confidence 0.01", the following error occurred:

scu@scu-desktop:~/AcousticEventDetection$ python AED_test.py --filenames 'dataset/schreien_scream.wav' --modelname 'AED_Example_Run_model.pkl'
HANDLING IMPORTS...
Using gpu device 0: GeForce GTX 960 (CNMeM is disabled, CuDNN 7004)
/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/init.py:600: UserWarning: Your CuDNN version is more recent then Theano. If you see problems, try updating Theano or downgrading CuDNN to version 4.
warnings.warn(warn)
...DONE!
IMPORTING MODEL...
Traceback (most recent call last):
File "AED_test.py", line 156, in
NET, CLASSES, IM_SIZE, IM_DIM = loadModel(TRAINED_MODEL)
File "AED_test.py", line 57, in loadModel
data = pickle.load(f)
File "/usr/lib/python2.7/pickle.py", line 1378, in load
return Unpickler(file).load()
File "/usr/lib/python2.7/pickle.py", line 858, in load
dispatchkey
File "/usr/lib/python2.7/pickle.py", line 1090, in load_global
klass = self.find_class(module, name)
File "/usr/lib/python2.7/pickle.py", line 1124, in find_class
import(module)
ImportError: No module named gpuarray.type

I have installed Python 2.7,python-opencv,numpy,scipy,scikit-learn,python_speech_features,pydub,matplotlib,cuda8.0,cuDNN7,Thenao 0.8,Lasagne on Ubuntu 14.04.

As a beginner,I'm sorry to trouble you.Can you help me?Thanks!

Hello kahst,
Thanks for sharing the model!
I got some trouble while using your model.
I followed your instruction and download the public data set "UrbanSound8K", when I use AED_spec.py to extract the spectrograms of wav files, python shell reports:

NUMBER OF EVENTS: 10
dataset/UrbanSound8K/audio/fold1/event0_air_conditioner/134717-0-0-0.wav
SAMPLE RATE: 44100
0 ERROR
Traceback (most recent call last):
File "E:\python\python364\project\AcousticEventDetection-master\AED_spec_new.py", line 137, in
for spec in getMultiSpec(wav):
File "E:\python\python364\project\AcousticEventDetection-master\AED_spec_new.py", line 111, in getMultiSpec
magspec = getSpecFromSignal(sig, rate, seconds)
File "E:\python\python364\project\AcousticEventDetection-master\AED_spec_new.py", line 58, in getSpecFromSignal
frames = psf.sigproc.framesig(sig, winlenrate, winsteprate, winfunc)
File "E:\python\python364\lib\site-packages\python_speech_features\sigproc.py", line 33, in framesig
padsignal = numpy.concatenate((sig,zeros))
ValueError: all the input arrays must have same number of dimensions
dataset/UrbanSound8K/audio/fold1/event0_air_conditioner/134717-0-0-1.wav
SAMPLE RATE: 44100
0 ERROR
Traceback (most recent call last):
File "E:\python\python364\project\AcousticEventDetection-master\AED_spec_new.py", line 137, in
for spec in getMultiSpec(wav):
File "E:\python\python364\project\AcousticEventDetection-master\AED_spec_new.py", line 111, in getMultiSpec
magspec = getSpecFromSignal(sig, rate, seconds)
File "E:\python\python364\project\AcousticEventDetection-master\AED_spec_new.py", line 58, in getSpecFromSignal
frames = psf.sigproc.framesig(sig, winlenrate, winsteprate, winfunc)
File "E:\python\python364\lib\site-packages\python_speech_features\sigproc.py", line 33, in framesig
padsignal = numpy.concatenate((sig,zeros))
ValueError: all the input arrays must have same number of dimensions
...

I can only extract a few files.
So do you know where is wrong? Could you help me with this problem? I'm really sorry to bother you. Thanks！
Best regards!