kunalvaidya99/music-genre-classification

Music Genre Recognition App With Accuracy of 89%.

Music-Genre-Classification

Music Genre Classification using GTZAN Dataset.Here is the Link to Dataset GTZAN Dataset

I Made a Web App using Streamlit For the Convolutional Neural Network (CNN) Model and Deployed it on Amazon EC2

The Dataset contains 10 Genres of music :

Genres

• Blues
• Classical
• Country
• Disco
• Hip-Hop
• Jazz
• Metal
• Pop
• Reggae
• Rock

Dataset

• Each Genre contains 100 audio files each of duration 30s.
• Divided 30s audio files into 10 files of 3s each.
• This Data Augmentation really helps model learn better and it performes better on the test set.

Models

I have explored the problem using two approaches

1. Using Deep Neural Network (DNN) Model which made use of features such as MFCC's,spectral centroids, extracted features are in features_3sec.csv
2. Using Convolutional Neural Network (CNN) Model which made use of Mel Spectrogram of the Audio Files.

Results

So this the training and test accuracy obtained after 250 epochs. A simple DNN model is also showing quite good test accuracy due to data augmentation

music-genre-classification's Issues

Epoch 1/70 12/22 [===============>..............] - ETA: 8s - loss: 0.4481 - accuracy: 0.8300 - get_f1: 0.8416 --------------------------------------------------------------------------- UnidentifiedImageError Traceback (most recent call last) <ipython-input-39-b2a011903e5a> in <module>() ----> 1 model.fit_generator(train_generator,epochs=70,validation_data=vali_generator) 12 frames /usr/local/lib/python3.6/dist-packages/PIL/Image.py in open(fp, mode) 2860 warnings.warn(message) 2861 raise UnidentifiedImageError( -> 2862 "cannot identify image file %r" % (filename if filename else fp) 2863 ) 2864 UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7ff9217a4af0>

Music Genre classification using cnn

Error in
y,sr = librosa.load('/content/gdrive/My Drive/kunal/genres/blues/blues.00020.wav')

RuntimeError: Error opening '/content/gdrive/My Drive/kunal/genres/blues/blues.00020.wav': System error.

NameError: name 'X_test' is not defined

preds = model.evaluate(x=X_test,y=Y_test)
print(preds[1])
print(preds[2])
when i ran this code it showed
NameError: name 'X_test' is not defined
how to solve it

issue with data generator

train_dir = "/content/gdrive/My Drive/spectrograms3sec/train/"
train_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(train_dir,target_size=(288,432),color_mode="rgba",class_mode='categorical',batch_size=128)

validation_dir = "/content/gdrive/My Drive/spectrograms3sec/test/"
vali_datagen = ImageDataGenerator(rescale=1./255)
vali_generator = vali_datagen.flow_from_directory(validation_dir,target_size=(288,432),color_mode='rgba',class_mode='categorical',batch_size=128)
output: Found 0 images belonging to 3 classes.
Found 0 images belonging to 3 classes.
why is so?