def train_VAE(
gpu=GPU,
dataset_fileName=f'{DATASET_SAVE_PATH}/wsj0_normalize_{N_FFT}_{HOP_LENGTH}.pic'
):
file_suffix = f"normal-scale=gamma-D={N_LATENT}"
if os.path.isfile(MODEL_SAVE_PATH +
'/model-best-{0}.npz'.format(file_suffix)):
print(f"{MODEL_SAVE_PATH}model-best-{file_suffix}.npz already exist")
exit
cuda.get_device_from_id(gpu).use()
# Load dataset
with open(dataset_fileName, 'rb') as f:
dataset = pic.load(f)
n_data = dataset.shape[1]
# Prepare VAE model
model = network_VAE.VAE(n_freq=int(N_FFT / 2 + 1), n_latent=N_LATENT)
model.to_gpu()
# Setup Optimizer
optimizer = optimizers.Adam(LEARNING_RATE)
optimizer.setup(model)
# Learning loop
min_loss = np.inf
loss_list = []
for epoch in range(N_EPOCH):
print('Epoch:', epoch + 1)
sum_loss = 0
perm = np.random.permutation(n_data)
for ii in progressbar(range(0, n_data, BATCH_SIZE)):
minibatch = dataset[:, perm[ii:ii + BATCH_SIZE]].T
scales = np.random.gamma(2, 0.5, (len(minibatch)))
minibatch = minibatch * scales[:, None]
x = chainer.Variable(cp.asarray(minibatch, dtype=cp.float32))
optimizer.update(model.get_loss_func(), x)
sum_loss += float(model.loss.data) * BATCH_SIZE
loss_list.append(float(model.loss.data))
sum_loss /= n_data
print("Loss:", sum_loss)
print('save the model and optimizer')
serializers.save_npz(
MODEL_SAVE_PATH + 'model-{0}.npz'.format(file_suffix), model)
with open(MODEL_SAVE_PATH + 'loss-{0}.pic'.format(file_suffix),
'wb') as f:
pic.dump(loss_list, f)
if sum_loss < min_loss:
shutil.copyfile(
MODEL_SAVE_PATH + 'model-{0}.npz'.format(file_suffix),
MODEL_SAVE_PATH + 'model-best-{0}.npz'.format(file_suffix))
min_loss = sum_loss
sum_loss = 0
parser.add_argument( '--n_fft', type= int, default= 1024, help='number of frequencies')
parser.add_argument( '--n_noise', type= int, default= 1, help='number of noise')
parser.add_argument( '--n_latent', type= int, default= 16, help='dimention of encoded vector')
parser.add_argument( '--n_basis_noise', type= int, default= 64, help='number of basis of noise (MODE_noise=NMF)')
parser.add_argument( '--init_SCM', type= str, default="obs", help='unit, obs, ILRMA')
parser.add_argument( '--n_iteration', type= int, default= 30, help='number of iteration')
parser.add_argument( '--n_Z_iteration', type= int, default= 30, help='number of update Z iteration')
parser.add_argument( '--mode_update_Z', type= str, default="sampling", help='sampling, sampling2, backprop, backprop2, hybrid, hybrid2')
parser.add_argument('--mode_update_parameter', type= str, default= "all", help='all, one_by_one')
args = parser.parse_args()
sys.path.append("../DeepSpeechPrior")
import network_VAE
model_fileName = "../DeepSpeechPrior/model-VAE-best-scale=gamma-D={}.npz".format(args.n_latent)
speech_VAE = network_VAE.VAE(n_latent=args.n_latent)
serializers.load_npz(model_fileName, speech_VAE)
name_DNN = "VAE"
if args.gpu < 0:
import numpy as xp
else:
import cupy as xp
print("Use GPU " + str(args.gpu))
cuda.get_device_from_id(args.gpu).use()
speech_VAE.to_gpu()
wav, fs = sf.read(args.input_fileName)
wav = wav.T
M = len(wav)
for m in range(M):
