This comment has been minimized.
This comment has been minimized.
GTZAN dataset: |
This comment has been minimized.
This comment has been minimized.
can you send us loaction of your path. i am not getting the logic |
This comment has been minimized.
This comment has been minimized.
header = 'filename chroma_stft spectral_centroid spectral_bandwidth rolloff zero_crossing_rate' i have got syntax errror how to fix the pblm??help me File "", line 3 |
This comment has been minimized.
This comment has been minimized.
In case any one having error with the rmse just include |
This comment has been minimized.
This comment has been minimized.
@gjnehruceg33 are you using Python 3.6+? If not, you'll be seeing that syntax error. |
This comment has been minimized.
This comment has been minimized.
Notice that after 0.6.3 version change |
This comment has been minimized.
This comment has been minimized.
Nice work |
This comment has been minimized.
This comment has been minimized.
How to make gui for this? |
This comment has been minimized.
This comment has been minimized.
librosa.feature.rms <= |
This comment has been minimized.
This comment has been minimized.
Where did you use those images, I just wanted to know are they just for visualization? |
This comment has been minimized.
This comment has been minimized.
You extracted all spectrograms and saved them as figs, but you don't need them for training? Then, what was the point there? |
This comment has been minimized.
This comment has been minimized.
Hi @basriciftci, good question. Like I have mentioned in the article accompanying the code(https://towardsdatascience.com/music-genre-classification-with-python-c714d032f0d8), the purpose of this whole exercise was to help beginners understand the concept of working and understanding the audio files. Once the data has been extracted, they can use any algorithm of their choice to train it. |
This comment has been minimized.
This comment has been minimized.
hello, |
This comment has been minimized.
This comment has been minimized.
Hi @parulnith. I am wondering have you any example where you used the Spectogram images for training the Neural network and classifying? |
This comment has been minimized.
This comment has been minimized.
Hi @DylanCarey94, did you manage to create a neural network using the spectogram images? |
This comment has been minimized.
This comment has been minimized.
Hi,
So I have a music dataset which I used Librosa to extract features from and then classify using multiple different algorithms. My last algorithm is a Neural Network so the original features are not sufficient because the Neural Network I classifies images more accurately than normal features. So because of this I have been able to convert the music dataset in to a dataset of spectrogram images. My problem is extracting features from the images, so no unfortunately not.
Sent from Mail<https://go.microsoft.com/fwlink/?LinkId=550986> for Windows 10
From: michellemul<mailto:notifications@github.com>
Sent: Monday 9 March 2020 16:42
To: parulnith<mailto:parulnith@noreply.github.com>
Cc: Dylan Carey<mailto:dylancarey2010@hotmail.com>; Mention<mailto:mention@noreply.github.com>
Subject: Re: parulnith/Music_genre_classification.ipynb
Hi @parulnith<https://github.com/parulnith>. I am wondering have you any example where you used the Spectogram images for training the Neural network and classifying?
Hi @DylanCarey94<https://github.com/DylanCarey94>, did you manage to create a neural network using the spectogram images?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub<https://gist.github.com/7f8c174e6ac099e86f0495d3d9a4c01e?email_source=notifications&email_token=AFNBAT3WFMSTFXMY53TQFETRGV5HZA5CNFSM4HPVJB6KYY3PNVWWK3TUL52HS4DFVNDWS43UINXW23LFNZ2KUY3PNVWWK3TUL5UWJTQAGDV2G#gistcomment-3206051>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AFNBAT6MLPU6FAJWQXE5CHLRGV5HZANCNFSM4HPVJB6A>.
|
This comment has been minimized.
This comment has been minimized.
Hi there, I ran through the code and for the code block: np.argmax(predictions[0]) My result was 3. I noticed in the example that it is 8. Does this mean something is wrong with my model? How can we start using this to pass it new songs to predict? |
This comment has been minimized.
This comment has been minimized.
Hi @specpro30, Just put replace the data in X_test with whatever features you extract from your new songs and you are good to go :) |
This comment has been minimized.
This comment has been minimized.
For this code, I am getting problem of "keras scratch graph"
InvalidArgumentError: Received a label value of 996 which is outside the valid range of [0, 10). Label values: 807 996 153 945 283 178 816 976 923 648 129 22 944 439 34 979 288 994 321 483 810 830 215 736 324 138 308 796 473 824 206 627 Function call stack: CAN SOMEONE HELP ME TO SORT OUT THIS PROBLEM |
This comment has been minimized.
This comment has been minimized.
Hi @SonamSangpoLama, I think you want to check the contents of your y_train vector. There is too many classes in it. It can only be a number between 0 and 10:
|
This comment has been minimized.
This comment has been minimized.
Thank you for your kind response.. Can you explain me further. I cannot get it..How can I check y_train content..? |
This comment has been minimized.
This comment has been minimized.
Hi @SonamSangpoLama, |
This comment has been minimized.
This comment has been minimized.
I have just been trying to use the same code of above but I am getting error. I have just made tiny changes on file directory. Extracting spec from audios extracting features from spect
writing to csv
reading csv
standard scaler
|
This comment has been minimized.
This comment has been minimized.
What was the use of spectrogram images??? |
This comment has been minimized.
This comment has been minimized.
I wrote a easy to understand notebook based on FE ideas in this one: Take a look if this seems too complicated |
This comment has been minimized.
Hi
Do you have dataset available with you ?? seems author removed GTZAN datasets..
Thanks in advance