# Chromagrams from MATLAB
chrom = sio.loadmat(fold + "/chrom.mat")['chroma']
chromas = []
names = []
for i in range(0, chrom[0].shape[0]):
try:
names.append(float(chrom[0][i][0][0].replace('-', '.').replace('.mp3', '')))
chromas.append(chrom[0][i][1][0][0][:, 0:514])
except ValueError:
y = chrom[0][i][1][0][0][:, 0:514]
names_arr = np.asarray(names)
x = np.argsort(names_arr)
names = names_arr[x]
chromas = [chromas[x1] for x1 in x]
chrom_shape = chromas[0].shape
lap_chrom = lap_pyramid(6, chrom_shape)
yr = np.reshape(y, (1, chrom_shape[0], chrom_shape[1], 1))
chrom_lap_temp, chrom_eucl_temp = [], []
for c in chromas:
cr = np.reshape(c, (1, chrom_shape[0], chrom_shape[1], 1))
chrom_lap_temp.append(lap_chrom.compare(yr, cr))
chrom_eucl_temp.append(np.sqrt(np.mean((y-c) ** 2)))
for f in (glob.glob(fold + "*.wav")):
y, sr = librosa.load(f, duration=12.0)
c1s = librosa.core.stft(y=y)
c1c = librosa.feature.chroma_stft(y=y, sr=sr, n_chroma=88)
c1s = np.vstack((c1s.real, c1s.imag))
stft_shape = c1s.shape
c1sr = np.reshape(c1s, (1, stft_shape[0], stft_shape[1], 1))
chrom_shape = c1c.shape
import matplotlib.pyplot as plt
import glob
from mutagen.mp3 import MP3
from pydub import AudioSegment
from pydub.utils import mediainfo
files = (glob.glob("./Audio Files/*.mp3"))
y, sr = librosa.load('nonoise.wav', duration=10.0) # bitrate = 706k
#c1 = librosa.feature.chroma_cqt(y=y, sr=sr, n_chroma=88)[:, 0:430]
c1 = librosa.core.stft(y=y)
chrom_shape = c1.shape
c1r = np.reshape(c1, (1, chrom_shape[0], chrom_shape[1], 1))
lap = lap_pyramid(6, chrom_shape)
scores = []
eucl = []
bitrates = []
for f in tqdm(files):
y2, sr2 = librosa.load(f, duration=10.0)
m = MP3(f)
bitrates.append(m.info.bitrate/1000)
#chrom = librosa.feature.chroma_cqt(y=y2, sr=sr2, n_chroma=88)[:, 0:430]
chrom = librosa.core.stft(y=y2)
chromr = np.reshape(chrom, (1, chrom_shape[0], chrom_shape[1], 1))
scores.append(lap.compare(c1r, chromr))
from scipy.spatial import distance
from tqdm import tqdm
y, sr = librosa.load(librosa.util.example_audio_file(), duration=10.0)
sigmas = np.linspace(0.01, 0.1, 10)
c1 = librosa.feature.chroma_cqt(y=y, sr=sr, n_chroma=88)[:, 0:430]
chrom_shape = c1.shape
c1r = np.reshape(c1, (1, chrom_shape[0], chrom_shape[1], 1))
kern = [[0.0025, 0.0125, 0.0200, 0.0125, 0.0025],
[0.0125, 0.0625, 0.1000, 0.0625, 0.0125],
[0.0200, 0.1000, 0.1600, 0.1000, 0.0200],
[0.0125, 0.0625, 0.1000, 0.0625, 0.0125],
[0.0025, 0.0125, 0.0200, 0.0125, 0.0025]]
kern = np.reshape(kern, (5, 5, 1, 1))
lap = lap_pyramid(6, chrom_shape, kernel=kern)
scores = []
eucl = []
for sig in tqdm(sigmas):
noise = np.random.normal(0, sig, y.shape[0])
chrom = librosa.feature.chroma_cqt(y=(y + noise), sr=sr,
n_chroma=88)[:, 0:430]
chromr = np.reshape(chrom, (1, chrom_shape[0], chrom_shape[1], 1))
scores.append(lap.compare(c1r, chromr))
eucl.append(np.sqrt(np.mean((c1 - chrom)**2)))
plt.figure()
plt.subplot(2, 1, 1)
plt.scatter(sigmas, scores, marker='x')
plt.title('Normalised Laplacian Pyramid')
plt.xlabel('Additive Gaussian Noise standard deviation')
import numpy as np
from tqdm import tqdm
from lap_pyramid import *
from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras.datasets import mnist
import matplotlib.pyplot as plt
import tensorflow as tf
lap = lap_pyramid(6, [28, 28], loss=True)
def custom_loss(real, pred):
s = lap.loss_function(real, pred)
print(s)
return s
input_img = Input(shape=(28, 28, 1))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
'Song': splt[-1],
'Album': splt[-2],
'Pyramid': pyr
},
ignore_index=True)
album = pd.Series(df['Album']).astype('category')
album_number = album.cat.codes
df['Album Number'] = album_number
return df
if __name__ == "__main__":
start_time = time.time()
flac_path = '/Users/ah13558/Documents/flac/'
base_y, base_sr = librosa.load(flac_path + "base.flac", duration=12.0)
lap = lap_pyramid(6, [2050, 513])
df = create_pyramid_dataframe(flac_path, lap)
scores = distance.cdist(list(df['Pyramid']),
list(df['Pyramid']),
metric=calc_rmse)
# Create graph
colors = [set3[x] for x in list(df['Album Number'])]
plot = figure(title="LAPD Songs",
x_range=(-1.1, 1.1),
y_range=(-1.1, 1.1),
plot_width=800,
plot_height=800)
G = nx.from_numpy_matrix(scores)
graph_renderer = from_networkx(G, nx.spring_layout)
graph_renderer.node_renderer.data_source.add(colors, 'fillcolor')