class Batcher:
def __init__(self, batch_dim, train_percentage=90):
from Utilities.Sound import get_sound, sound_cut
from Utilities.Pretreatment import Normalize
data = sound_cut(get_sound("XqaJ2Ol5cC4").astype(np.float32))
cut = data.shape[0] * train_percentage // 100
self.pre = Normalize()
self.pre.fit(data)
self.train_data = self.pre.cmp(data[:cut])
self.valid_data = self.pre.cmp(data[cut:])
self.batch_dim = batch_dim
self.n_batch = 0
self.train_max = self.train_data.shape[0] - batch_dim[
0] - batch_dim[1] * batch_dim[2] - 1
self.starts = np.arange(0, self.train_max - batch_dim[2], batch_dim[0])
np.random.shuffle(self.starts)
def get_batch(self):
self.n_batch += 1
batch_dim = self.batch_dim
start = self.starts[self.n_batch % self.starts.shape[0]]
x_data = np.asarray([
self.train_data[start + i:start + i +
batch_dim[1] * batch_dim[2]].reshape(
(batch_dim[1], batch_dim[2]))
for i in range(batch_dim[0])
])
y_data = np.asarray([
self.train_data[start + i + batch_dim[2]:start + i +
(batch_dim[1] + 1) * batch_dim[2]].reshape(
(batch_dim[1], batch_dim[2]))
for i in range(batch_dim[0])
])
return x_data, y_data
def get_valid_batch(self):
batch_dim = self.batch_dim
x_data = np.asarray([
self.valid_data[i:i + batch_dim[1] * batch_dim[2]].reshape(
(batch_dim[1], batch_dim[2])) for i in range(batch_dim[0])
])
y_data = np.asarray([
self.valid_data[i + batch_dim[2]:i +
(batch_dim[1] + 1) * batch_dim[2]].reshape(
(batch_dim[1], batch_dim[2]))
for i in range(batch_dim[0])
])
return x_data, y_data
def get_percentage(self):
return 100 * self.n_batch * self.batch_dim[0] // self.train_max
def get_params(self):
return self.n_batch
def set_params(self, params):
self.n_batch = params
def __init__(self, batch_dim, train_percentage=90):
from Utilities.Sound import get_sound, sound_cut
from Utilities.Pretreatment import Normalize
data = sound_cut(get_sound("XqaJ2Ol5cC4").astype(np.float32))
cut = data.shape[0] * train_percentage // 100
self.pre = Normalize()
self.pre.fit(data)
self.train_data = self.pre.cmp(data[:cut])
self.valid_data = self.pre.cmp(data[cut:])
self.batch_dim = batch_dim
self.n_batch = 0
self.train_max = self.train_data.shape[0] - batch_dim[
0] - batch_dim[1] * batch_dim[2] - 1
self.starts = np.arange(0, self.train_max - batch_dim[2], batch_dim[0])
np.random.shuffle(self.starts)
class Batcher:
def __init__(self, batch_dim, train_percentage=90):
from Utilities.Sound import get_sound, sound_cut
from Utilities.Pretreatment import Normalize
data = sound_cut(get_sound("XqaJ2Ol5cC4").astype(np.float32))
cut = data.shape[0]*train_percentage//100
self.pre = Normalize()
self.pre.fit(data)
self.train_data = self.pre.cmp(data[:cut])
self.valid_data = self.pre.cmp(data[cut:])
self.batch_dim = batch_dim
self.n_batch = 0
self.train_max = self.train_data.shape[0]-batch_dim[0]-batch_dim[1]*batch_dim[2]-1
self.starts = np.arange(0, self.train_max-batch_dim[2], batch_dim[0])
np.random.shuffle(self.starts)
def get_batch(self):
self.n_batch += 1
batch_dim = self.batch_dim
start = self.starts[self.n_batch%self.starts.shape[0]]
x_data = np.asarray([self.train_data[start+i:start+i+batch_dim[1]*batch_dim[2]].reshape((batch_dim[1], batch_dim[2])) for i in range(batch_dim[0])])
y_data = np.asarray([self.train_data[start+i+batch_dim[2]:start+i+(batch_dim[1]+1)*batch_dim[2]].reshape((batch_dim[1], batch_dim[2])) for i in range(batch_dim[0])])
return x_data, y_data
def get_valid_batch(self):
batch_dim = self.batch_dim
x_data = np.asarray([self.valid_data[i:i+batch_dim[1]*batch_dim[2]].reshape((batch_dim[1], batch_dim[2])) for i in range(batch_dim[0])])
y_data = np.asarray([self.valid_data[i+batch_dim[2]:i+(batch_dim[1]+1)*batch_dim[2]].reshape((batch_dim[1], batch_dim[2])) for i in range(batch_dim[0])])
return x_data, y_data
def get_percentage(self):
return 100*self.n_batch*self.batch_dim[0]//self.train_max
def get_params(self):
return self.n_batch
def set_params(self, params):
self.n_batch = params
def __init__(self, batch_dim, train_percentage=90):
from Utilities.Sound import get_sound, sound_cut
from Utilities.Pretreatment import Normalize
data = sound_cut(get_sound("XqaJ2Ol5cC4").astype(np.float32))
cut = data.shape[0]*train_percentage//100
self.pre = Normalize()
self.pre.fit(data)
self.train_data = self.pre.cmp(data[:cut])
self.valid_data = self.pre.cmp(data[cut:])
self.batch_dim = batch_dim
self.n_batch = 0
self.train_max = self.train_data.shape[0]-batch_dim[0]-batch_dim[1]*batch_dim[2]-1
self.starts = np.arange(0, self.train_max-batch_dim[2], batch_dim[0])
np.random.shuffle(self.starts)
def __init__(self,
name,
batch_dim,
preprocess=Normalize(),
rate=16000,
n_valid=128):
self.name = name
self.batch_dim = batch_dim
self.preprocess = preprocess
self.rate = rate
self.n_valid = n_valid
self.valid_len = (batch_dim[0] + 1) * batch_dim[2] * n_valid
self.sound = sound_cut(get_sound(name).astype(config.floatX))
self.time = self.sound.shape[0] / float(rate)
self.preprocess.fit(self.sound[:-self.valid_len])
self.train = self.preprocess.cmp(self.sound[:-self.valid_len])
self.valid = self.preprocess.cmp(self.sound[-self.valid_len:])
self.n_batch = 0