You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm trying to port a simple of project of silence (little noise) detection in audio files to sklearn from TensorFlow. Data is attached here.
train.npy, shape = (250, 20)
test.npy, shape = (120, 20)
The training data consists of 250 samples of Mel Frequency Cepstrum Coefficient (MFCC) with 20 floats in each and testing consists
120 samples of MFCC with 20 floats in each. In tensorflow, the generated model has an accuracy of 1.0 with loss = 0.04.
Here is my code using sklearn:
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello,
I'm trying to port a simple of project of silence (little noise) detection in audio files to sklearn from TensorFlow. Data is attached here.
train.npy, shape = (250, 20)
test.npy, shape = (120, 20)
The training data consists of 250 samples of Mel Frequency Cepstrum Coefficient (MFCC) with 20 floats in each and testing consists
120 samples of MFCC with 20 floats in each. In tensorflow, the generated model has an accuracy of 1.0 with loss = 0.04.
Here is my code using sklearn:
The score is quite low, 0.46153846153846156 and prediction probabilities look random to me. Am I missing something here?
data.zip
Beta Was this translation helpful? Give feedback.
All reactions