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
