russellizadi

import numpy as np 
import matplotlib.pylab as plt

f_sample = 22050.
signal = np.sin(2. * np.pi * 20. * np.arange(0, 2., 1/f_sample))
plt.plot(signal);

def frame(x, n_window, n_hop):
    n = x.shape[0]
    n_frames = 1 + int(np.floor((n - n_window) / n_hop))

russellizadi

import numpy as np 
import matplotlib.pylab as plt

f_sample = 22050.
signal = np.sin(2. * np.pi * 20. * np.arange(0, 2., 1/f_sample))
plt.plot(signal);

def frame(x, n_window, n_hop):
    n = x.shape[0]
    n_frames = 1 + int(np.floor((n - n_window) / n_hop))

russellizadi

russellizadi

# x^y mod p
def power(x, y, p):  
    res = 1 
    x = x % p 
    while (y > 0):  
        if (y & 1): 
            res = (res * x) % p
        y = y >> 1
        x = (x * x) % p
    return res

russellizadi

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.axes_grid1 import make_axes_locatable

ax = plt.subplot()
divider = make_axes_locatable(ax)
cax = divider.append_axes("right", size = "5%", pad = 0.05)
im = ax.imshow(x)
plt.colorbar(im, cax = cax)

russellizadi

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.axes_grid1 import make_axes_locatable

fig = plt.figure(1, figsize=(17, 17))

ax = fig.add_subplot(1, 2, 1)
divider = make_axes_locatable(ax)
cax = divider.append_axes("right", size = "5%", pad = 0.05)
im = ax.imshow(x1)

russellizadi

import os
from pydub import AudioSegment
from pydub.utils import mediainfo

path_flacs = '/home/russell/Documents/audiobooks/Educated_ A Memoir by Tara Westover-20190704T203807Z-001/Educated_ A Memoir by Tara Westover/FLAC'
path_mp3s = 'MP3'
path_cover = '/home/russell/Documents/audiobooks/Educated_ A Memoir by Tara Westover-20190704T203807Z-001/Educated_ A Memoir by Tara Westover/Educated_ A Memoir by Tara Westover.jpg'

def make_dir(path):
    if not os.path.exists(path):

russellizadi

import numpy as np

# n is batch size; d_in is input dimension;
# h is hidden dimension; d_out is output dimension.
n, d_in, d_h, d_out = 64, 1000, 100, 10

# Create random input and output data
x = np.random.randn(n, d_in)
y = np.random.randn(n, d_out)

russellizadi

import tensorflow as tf
import numpy as np
from datasets import mnist as dataset

tf.reset_default_graph() 

class Params:
    def __init__(self): 
        self.experiment = 'calssification'
    def model(self):

russellizadi

import tensorflow as tf
import numpy as np
from datasets import mnist as dataset

tf.reset_default_graph() 

class Params:
    def __init__(self): 
        self.dataset = 'dataset_fn1'
    def model(self):