def main(_):
print('Parsed arguments: ', FLAGS.__flags)
# make save path if it is required
if not os.path.exists(FLAGS.save_path):
os.makedirs(FLAGS.save_path)
if not os.path.exists(FLAGS.synthesis_path):
os.makedirs(FLAGS.synthesis_path)
np.random.seed(FLAGS.seed)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
udevices = []
for device in devices:
if len(devices) > 1 and 'CPU' in device.name:
# Use cpu only when we dont have gpus
# udevices.append(device.name)
continue
print('Using device: ', device.name)
udevices.append(device.name)
# execute the session
with tf.Session(config=config) as sess:
if FLAGS.model == 'gan':
print('Creating GAN model')
se_model = SEGAN(sess, FLAGS, udevices)
elif FLAGS.model == 'ae':
print('Creating AE model')
se_model = SEAE(sess, FLAGS, udevices)
else:
raise ValueError('{} model type not understood!'.format(
FLAGS.model))
if FLAGS.test_wav is None:
se_model.train(FLAGS, udevices)
else:
if FLAGS.weights is None:
raise ValueError('weights must be specified!')
print('Loading model weights...')
se_model.load(FLAGS.save_path, FLAGS.weights)
fm, wav_data = wavfile.read(FLAGS.test_wav)
print(fm)
wavname = FLAGS.test_wav.split('/')[-1]
if fm != 16000:
raise ValueError('16kHz required! Test file is different')
wave = (2. / 65535.) * (wav_data.astype(np.float32) - 32767) + 1.
if FLAGS.preemph > 0:
print('preemph test wave with {}'.format(FLAGS.preemph))
x_pholder, preemph_op = pre_emph_test(FLAGS.preemph,
wave.shape[0])
wave = sess.run(preemph_op, feed_dict={x_pholder: wave})
print('test wave shape: ', wave.shape)
print('test wave min:{} max:{}'.format(np.min(wave),
np.max(wave)))
c_wave = se_model.clean(wave)
print('c wave min:{} max:{}'.format(np.min(c_wave),
np.max(c_wave)))
wavfile.write(os.path.join(FLAGS.save_clean_path, wavname), 16000,
c_wave)
print('Done cleaning {} and saved '
'to {}'.format(FLAGS.test_wav,
os.path.join(FLAGS.save_clean_path, wavname)))
def main(_):
print('Parsed arguments: ', FLAGS.__flags)
# make save path if it is required
if not os.path.exists(FLAGS.save_path):
os.makedirs(FLAGS.save_path)
if not os.path.exists(FLAGS.synthesis_path):
os.makedirs(FLAGS.synthesis_path)
np.random.seed(FLAGS.seed)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement=True
udevices = []
for device in devices:
if len(devices) > 1 and 'cpu' in device.name:
# Use cpu only when we dont have gpus
continue
print('Using device: ', device.name)
udevices.append(device.name)
# execute the session
with tf.Session(config=config) as sess:
if FLAGS.model == 'gan':
print('Creating GAN model')
se_model = SEGAN(sess, FLAGS, udevices)
elif FLAGS.model == 'ae':
print('Creating AE model')
se_model = SEAE(sess, FLAGS, udevices)
else:
raise ValueError('{} model type not understood!'.format(FLAGS.model))
if FLAGS.test_wavs is None:
se_model.train(FLAGS, udevices)
else:
if FLAGS.weights is None:
raise ValueError('weights must be specified!')
print('Loading model weights...')
se_model.load(FLAGS.save_path, FLAGS.weights)
FLAGS.test_wavs = FLAGS.test_wavs.split(',')
for i in range(len(FLAGS.test_wavs)):
wav_data, fm = librosa.load(FLAGS.test_wavs[i], sr=16000)
wavname = FLAGS.test_wavs[i].split('/')[-1].split('.')[0] +'_segan.wav'
wave = (2./65535.) * (wav_data.astype(np.float32) - 32767) + 1.
if FLAGS.preemph > 0:
print('preemph test wave with {}'.format(FLAGS.preemph))
x_pholder, preemph_op = pre_emph_test(FLAGS.preemph, wav_data.shape[0])
wave = sess.run(preemph_op, feed_dict={x_pholder: wav_data})
print("【*】Clean start time ...", time.asctime(time.localtime(time.time())))
c_wave = se_model.clean(wave)
print("【*】Clean end time ...", time.asctime(time.localtime(time.time())))
print('c wave min:{} max:{}'.format(np.min(c_wave), np.max(c_wave)))
print(c_wave)
librosa.output.write_wav(os.path.join(FLAGS.save_clean_path, wavname), c_wave, sr=16000)
print('Done cleaning {} and saved '
'to {}'.format(FLAGS.test_wavs[i], os.path.join(FLAGS.save_clean_path, wavname)))
def main(_):
print('Parsed arguments: ', FLAGS.__flags)
# make save path if it is required
if not os.path.exists(FLAGS.save_path):
os.makedirs(FLAGS.save_path)
if not os.path.exists(FLAGS.synthesis_path):
os.makedirs(FLAGS.synthesis_path)
np.random.seed(FLAGS.seed)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement=True
udevices = []
for device in devices:
if len(devices) > 1 and 'cpu' in device.name:
# Use cpu only when we dont have gpus
continue
print('Using device: ', device.name)
udevices.append(device.name)
# execute the session
with tf.Session(config=config) as sess:
if FLAGS.model == 'gan':
print('Creating GAN model')
se_model = SEGAN(sess, FLAGS, udevices)
elif FLAGS.model == 'ae':
print('Creating AE model')
se_model = SEAE(sess, FLAGS, udevices)
else:
raise ValueError('{} model type not understood!'.format(FLAGS.model))
if FLAGS.test_wav is None:
se_model.train(FLAGS, udevices)
else:
if FLAGS.weights is None:
raise ValueError('weights must be specified!')
print('Loading model weights...')
se_model.load(FLAGS.save_path, FLAGS.weights)
fm, wav_data = wavfile.read(FLAGS.test_wav)
wavname = FLAGS.test_wav.split('/')[-1]
if fm != 16000:
raise ValueError('16kHz required! Test file is different')
wave = (2./65535.) * (wav_data.astype(np.float32) - 32767) + 1.
if FLAGS.preemph > 0:
print('preemph test wave with {}'.format(FLAGS.preemph))
x_pholder, preemph_op = pre_emph_test(FLAGS.preemph, wave.shape[0])
wave = sess.run(preemph_op, feed_dict={x_pholder:wave})
print('test wave shape: ', wave.shape)
print('test wave min:{} max:{}'.format(np.min(wave), np.max(wave)))
c_wave = se_model.clean(wave)
print('c wave min:{} max:{}'.format(np.min(c_wave), np.max(c_wave)))
wavfile.write(os.path.join(FLAGS.save_clean_path, wavname), 16e3, c_wave)
print('Done cleaning {} and saved '
'to {}'.format(FLAGS.test_wav,
os.path.join(FLAGS.save_clean_path, wavname)))
def main(_):
print('Parsed arguments: ', FLAGS.__flags)
# make save path if it is required
if not os.path.exists(FLAGS.save_path):
os.makedirs(FLAGS.save_path)
if not os.path.exists(FLAGS.synthesis_path):
os.makedirs(FLAGS.synthesis_path)
np.random.seed(FLAGS.seed)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
udevices = []
for device in devices:
if len(devices) > 1 and 'CPU' in device.name:
# Use cpu only when we dont have gpus
continue
print('Using device: ', device.name)
udevices.append(device.name)
print("!!!!!!", udevices)
# execute the session
with tf.Session(config=config) as sess:
if FLAGS.squeeze_generator:
print('Creating Classifier')
se_model = CLASSIFY(sess, FLAGS, udevices)
elif FLAGS.model == 'gan':
print('Creating GAN model')
se_model = SEGAN(sess, FLAGS, udevices)
elif FLAGS.model == 'ae':
print('Creating AE model')
se_model = SEAE(sess, FLAGS, udevices)
else:
raise ValueError('{} model type not understood!'.format(
FLAGS.model))
if FLAGS.test_wav is None:
se_model.train(FLAGS, udevices)
else:
if FLAGS.weights is None:
raise ValueError('weights must be specified!')
print('Loading model weights...')
se_model.load(FLAGS.save_path, FLAGS.weights)
if FLAGS.ref_wav is None:
wave = read_wave(sess, FLAGS.test_wav)
c_wave = se_model.clean(wave)
print('c wave min:{} max:{}'.format(np.min(c_wave),
np.max(c_wave)))
wavfile.write(os.path.join(FLAGS.save_clean_path, wavname),
16000, c_wave)
print('Done cleaning {} and saved '
'to {}'.format(
FLAGS.test_wav,
os.path.join(FLAGS.save_clean_path, wavname)))
else:
files = []
if os.path.isdir(FLAGS.test_wav):
for filename in os.listdir(FLAGS.test_wav):
if filename.endswith(".wav"):
files.append(os.path.join(FLAGS.test_wav,
filename))
else:
files.append(FLAGS.test_wav)
for f in files:
refs = []
if os.path.isdir(FLAGS.ref_wav):
m = s3re.search(f)
if m:
vid = m.group(1)
for filename in os.listdir(FLAGS.ref_wav):
if filename.endswith(".wav") and filename.find(
"s3_" + vid) != -1:
refs.append(
os.path.join(FLAGS.ref_wav, filename))
else:
refs.append(FLAGS.ref_wav)
score = []
wav_signals = read_signals(sess, f, FLAGS.canvas_size)
if wav_signals is not None:
for r in refs:
ref_signals = read_signals(sess, r,
FLAGS.canvas_size)
if ref_signals is not None:
logit = se_model.classify(
wav_signals, ref_signals)
score.append(str(logit))
print("RES\t", f, "\t".join(score))
def main(_):
print('Parsed arguments: ', FLAGS.__flags)
# make save path if it is required
if not os.path.exists(FLAGS.save_path):
os.makedirs(FLAGS.save_path)
if not os.path.exists(FLAGS.synthesis_path):
os.makedirs(FLAGS.synthesis_path)
np.random.seed(FLAGS.seed)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
udevices = []
for device in devices:
if len(devices) > 1 and 'cpu' in device.name:
# Use cpu only when we dont have gpus
continue
print('Using device: ', device.name)
udevices.append(device.name)
# execute the session
with tf.Session(config=config) as sess:
if FLAGS.model == 'gan':
print('Creating GAN model')
se_model = SEGAN(sess, FLAGS, udevices)
elif FLAGS.model == 'ae':
print('Creating AE model')
se_model = SEAE(sess, FLAGS, udevices)
else:
raise ValueError('{} model type not understood!'.format(
FLAGS.model))
folders = []
for depth in range(FLAGS.maxdepth):
path_str = '*' + os.sep
path_str = os.path.join(FLAGS.in_dir, path_str * depth)
folders += glob(path_str)
root_folder = os.path.basename(
os.path.dirname(os.path.join(FLAGS.in_dir, '')))
if FLAGS.weights is None:
raise ValueError('weights must be specified!')
print('Loading model weights...')
se_model.load(FLAGS.save_path, FLAGS.weights)
for fld in tqdm(folders):
files = sorted(glob(os.path.join(fld, '*.wav')))
for fle in files:
fm, wav_data = wavfile.read(fle)
wavname = fle.split('/')[-1]
if fm != 16000:
#raise ValueError('16kHz required! Test file is different')
number_of_samples = int(
round(len(wav_data) * float(16000) / fm))
wav_data = sps.resample(wav_data, number_of_samples)
wave = (2. / 65535.) * (wav_data.astype(np.float32) -
32767) + 1.
if FLAGS.preemph > 0:
print('preemph test wave with {}'.format(FLAGS.preemph))
x_pholder, preemph_op = pre_emph_test(
FLAGS.preemph, wave.shape[0])
try:
wave = sess.run(preemph_op,
feed_dict={x_pholder: wave})
except:
print('Error processing %s' % wavname)
continue
print('test wave shape: ', wave.shape)
print('test wave min:{} max:{}'.format(
np.min(wave), np.max(wave)))
c_wave = se_model.clean(wave)
print('c wave min:{} max:{}'.format(np.min(c_wave),
np.max(c_wave)))
save_path = os.path.join(
FLAGS.save_clean_path,
fle[fle.find(root_folder) + len(root_folder) + 1:])
save_dir = os.path.dirname(save_path)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
wavfile.write(save_path, 16e3, c_wave)
print('Done cleaning {} and saved '
'to {}'.format(wavname, save_path))
def main(_):
if FLAGS.feature_type == 'wavform':
from model import SEGAN, SEAE
elif FLAGS.feature_type == 'logspec':
from spec_model import SEGAN, SEAE
print('Parsed arguments: ', FLAGS.__flags)
# make save path if it is required
if not os.path.exists(FLAGS.save_path):
os.makedirs(FLAGS.save_path)
if not os.path.exists(FLAGS.synthesis_path):
os.makedirs(FLAGS.synthesis_path)
np.random.seed(FLAGS.seed)
#gpu_options = tf.GPUOptions(allow_growth=True)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
config.gpu_options.allocator_type = 'BFC'
udevices = []
for device in devices:
print("Device lists:{}".format(devices))
if len(devices) > 1 and 'cpu' in device.name:
# Use cpu only when we dont have gpus
continue
print('Using device: ', device.name)
udevices.append(device.name)
print("device:{}".format(udevices))
# execute the session
with tf.Session(config=config) as sess:
if FLAGS.model == 'gan':
print('Creating GAN model')
se_model = SEGAN(sess, FLAGS, udevices)
elif FLAGS.model == 'ae':
print('Creating AE model')
se_model = SEAE(sess, FLAGS, udevices)
else:
raise ValueError('{} model type not understood!'.format(
FLAGS.model))
if FLAGS.test_wav is None:
mode = 'stage2'
se_model.train(FLAGS, udevices, mode)
else:
if FLAGS.weights is None:
raise ValueError('weights must be specified!')
print('Loading model weights...')
se_model.load(FLAGS.save_path, FLAGS.weights)
noisy_test_filelist = []
for (dirpath, dirnames, filenames) in os.walk(FLAGS.test_wav):
# print('dirpath = ' + dirpath)
for filename in filenames:
file_path = os.path.join(dirpath, filename)
noisy_test_filelist.append(file_path)
nlist = noisy_test_filelist
for name in nlist:
t1 = time.time()
fm, wav_data = wavfile.read(name)
wavname = name.split('/')[-1]
if fm != 16000:
raise ValueError('16kHz required! Test file is different')
#import librosa
#print('16kHz is required: test file is {}kHz, have to resample to the required samplerate')
#wav_data = librosa.resample(wav_data, fm, 16000)
if FLAGS.feature_type == 'wavform':
wave = (2. / 65535.) * (wav_data.astype(np.float32) -
32767) + 1.
if FLAGS.preemph > 0:
print('preemph test wave with {}'.format(
FLAGS.preemph))
x_pholder, preemph_op = pre_emph_test(
FLAGS.preemph, wave.shape[0])
wave = sess.run(preemph_op,
feed_dict={x_pholder: wave})
print('test wave shape: ', wave.shape)
print('test wave min:{} max:{}'.format(
np.min(wave), np.max(wave)))
c_wave = se_model.clean(wave)
print('c wave min:{} max:{}'.format(
np.min(c_wave), np.max(c_wave)))
wavfile.write(
os.path.join(FLAGS.save_clean_path, wavname), 16e3,
np.int16(c_wave *
32767)) #(0.9*c_wave/max(abs(c_wave)))
t2 = time.time(
) #np.int16((1.0*c_wave/max(abs(c_wave)))*32767)
print('Done cleaning {}/{}s and saved '
'to {}'.format(
name, t2 - t1,
os.path.join(FLAGS.save_clean_path, wavname)))
if FLAGS.feature_type == 'logspec':
if wav_data.dtype != 'float32':
wave = np.float32(wav_data / 32767.)
#wave = (2./65535.) * (wav_data.astype(np.float32) - 32767) + 1.
if FLAGS.preemph > 0:
print('preemph test wave with {}'.format(
FLAGS.preemph))
x_pholder, preemph_op = pre_emph_test(
FLAGS.preemph, wave.shape[0])
wave = sess.run(preemph_op,
feed_dict={x_pholder: wave})
print('test wave shape: ', wave.shape)
print('test wave min:{} max:{}'.format(
np.min(wave), np.max(wave)))
c_wave = se_model.clean(wave)
print('c wave min:{} max:{}'.format(
np.min(c_wave), np.max(c_wave)))
wavfile.write(
os.path.join(FLAGS.save_clean_path, wavname), 16e3,
np.int16(c_wave *
32767)) #(0.9*c_wave/max(abs(c_wave)))
t2 = time.time()
print('Done cleaning {}/{}s and saved '
'to {}'.format(
name, t2 - t1,
os.path.join(FLAGS.save_clean_path, wavname)))
'''
def model_fn(features, labels, mode, params):
print('Creating GAN model')
print(features["wav_and_noisy"])
wavbatch = labels
input_var = None
# if mode == tf.estimator.ModeKeys.PREDICT:
# # var = tf.compat.v1.get_variable("wav_and_noisy", [FLAGS.batch_size, FLAGS.canvas_size], tf.float32, initializer=tf.zeros_initializer())
# # var_update_rows = tf.compat.v1.scatter_update(var, [0], features["wav_and_noisy"])
# var_update_rows = features["wav_and_noisy"]
# var_update_rows.set_shape([FLAGS.batch_size, FLAGS.canvas_size])
# input_var = {"wav_and_noisy":var_update_rows}
# else:
# input_var = features
input_var = tf.reshape(features["wav_and_noisy"], shape=[-1, FLAGS.canvas_size])
se_model = SEGAN(None, params, ['/gpu:0'], input_var, wavbatch)
if mode == tf.estimator.ModeKeys.PREDICT:
# var_update_rows = tf.compat.v1.scatter_update(var, [0], t[0])
G, _ = se_model.generator(input_var, is_ref=False, spk=None,
do_prelu=False)
# wavbatch = labels
# fake_feature = {'input_noise',tf.placeholder(dtype=tf.float32, shape=[None,], name='input_noise')}
# se_model = SEGAN(None, params, ['/GPU:0'], features, wavbatch)
# wav_data = features["input_noise"]
# wave = (2./65535.) * (wav_data.astype(np.float32) - 32767) + 1.
# if params.preemph > 0:
# print('preemph test wave with {}'.format(params.preemph))
# # x_pholder, preemph_op = pre_emph_test(FLAGS.preemph, wave.shape[0])
# # wave = sess.run(preemph_op, feed_dict={x_pholder: wave})
# wave = pre_emph(wave, params.preemph)
# print('test wave shape: ', wave.shape)
# print('test wave min:{} max:{}'.format(np.min(wave), np.max(wave)))
# c_wave = se_model.clean(wave)
# print('c wave min:{} max:{}'.format(np.min(c_wave), np.max(c_wave)))
# se_model.Gs[0](features['input_noise'],)
predictions = {"clean_wav": G}
export_outputs = {
tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: tf.estimator.export.PredictOutput(predictions)}
return tf.estimator.EstimatorSpec(
mode=mode,
predictions=predictions,
export_outputs=export_outputs
)
elif mode == tf.estimator.ModeKeys.TRAIN:
train_op = None
train_op = tf.group(se_model.d_opt, se_model.g_opt)
g_loss = se_model.g_losses[-1]
d_loss = se_model.d_losses[-1]
tf.summary.scalar('g_loss', g_loss)
tf.summary.scalar('d_loss', d_loss)
predictions = {"clean_wav": se_model.Gs[-1]}
return tf.estimator.EstimatorSpec(
mode=mode,
predictions=predictions,
loss=g_loss+d_loss,
train_op=train_op
)
else:
print("wrong!! invalid mode: {}".format(mode))