def __call__(self, sample, wav_file, name_set):
feature, label = sample['feature'], sample['label']
save = self.save
config_file = self.config_file
out_dir = self.out_dir
feats_gmm_dir = self.feats_gmm_dir
# Reading params/config
params = utils.read_conf_file(file_name=config_file,
conf_section='DEFAULTS')
3,
reuse=True,
training=False),
feed_dict={net.input_z: sample_z})
samples.append(gen_samples)
_ = utils.view_samples(-1,
samples,
6,
12,
figsize=(FLAGS.h_figsize,
FLAGS.v_figsize))
plt.show()
saver.save(sess, './checkpoints/generator.ckpt')
with open('samples.pkl', 'wb') as f:
pkl.dump(samples, f)
fig, ax = plt.subplot()
losses = np.array(losses)
plt.plot(losses.T[0], label='Discriminator', alpha=0.5)
plt.plot(losses.T[1], label='Generator', alpha=0.5)
plt.title('Training Losses')
plt.legend()
plt.show()
if __name__ == '__main__':
args = parse_args()
FLAGS = utils.read_conf_file(args.conf)
main(FLAGS)
(step, loss_t, elapsed))
# summary
if step % _SUMMARY_EPS == 0:
tf.logging.info('adding summary...')
summary_str = sess.run(summary)
writer.add_summary(summary_str, step)
writer.flush()
# checkpoint
if step % _SAVE_EPS == 0:
saver.save(sess,
os.path.join(training_path,
'fast-style-model.ckpt'),
global_step=step)
except tf.errors.OutOfRangeError:
saver.save(
sess,
os.path.join(training_path, 'fast-style-model.ckpt-done'))
tf.logging.info('Done training -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
def main(flag):
training(flag)
if __name__ == '__main__':
FLAGS = read_conf_file(_YML_PATH + _DEFAULT_YML)
main(FLAGS)
def __call__(self, sample, wav_file, name_set):
waveform, label = sample['wave'], sample['label']
save = self.save
config_file = self.config_file
deltas = self.deltas
out_dir = self.out_dir
# frame-level feats params/config
params = utils.read_conf_file(file_name=config_file,
conf_section='DEFAULTS')
# check if features are already computed if features do not exist, then compute them
wav_name = os.path.splitext(os.path.basename(wav_file))[0]
file_name = '/{0}_{1}'.format(self.feat_type, wav_name)
feat_file_path = out_dir + '/' + file_name
if not os.path.isfile(feat_file_path):
# Compute without derivatives
if deltas == 0:
# Compute features
feat = execute_extraction_function(feat_type=self.feat_type,
waveform=waveform,
**params)
# Save features if asked for
out_dir = out_dir + '/{0}/{1}/'.format(self.feat_type,
name_set)
if save:
utils.save_features(out_dir, self.feat_type, wav_file,
feat)
utils.copy_conf(config_file, out_dir, self.feat_type)
feature = {'feature': feat, 'label': label}
return feature
# Compute derivatives if asked for
if deltas == 1:
# Compute features
feat = execute_extraction_function(feat_type=self.feat_type,
waveform=waveform,
**params)
delta1 = torchaudio.functional.compute_deltas(
feat) # compute 1st order
feat = torch.cat((feat, delta1), 1)
# Save features if asked for
out_dir = out_dir + '/{0}/{1}/'.format(self.feat_type,
name_set)
if save:
utils.save_features(out_dir, self.feat_type,
'{0}_{1}del'.format(wav_file,
deltas), feat)
utils.copy_conf(config_file, out_dir, self.feat_type)
feature = {'feature': feat, 'label': label}
return feature
if deltas == 2:
# Compute features
feat = execute_extraction_function(feat_type=self.feat_type,
waveform=waveform,
**params)
delta1 = torchaudio.functional.compute_deltas(
feat) # compute 1st order
delta2 = torchaudio.functional.compute_deltas(
delta1) # compute 2nd order
feat = torch.cat((feat, delta1, delta2), 1)
# Save features if asked for
out_dir = out_dir + '/{0}/{1}/'.format(self.feat_type,
name_set)
if save:
utils.save_features(out_dir, self.feat_type,
'{0}_{1}del'.format(wav_file,
deltas), feat)
utils.copy_conf(config_file, out_dir, self.feat_type)
feature = {'feature': feat, 'label': label}
return feature
# if features exist, then LOAD them
else:
feat = np.load(feat_file_path)
feature = {'feature': feat, 'label': label}
return feature
def compute_flfeats_offline(source_path,
out_dir,
feat_type,
deltas=None,
config_file=None):
"""Function to calculate the frame-level features and save them to files.
The function saves one file (containing features) per utterance
Args:
source_path (string): Path to the wavs.
out_dir (string): Type of the frame-level feature to extract from the utterances.
Choose from: 'mfcc', 'fbanks', 'melspec'. Default is: 'fbanks'.
feat_type (string): Type of the frame-level feature to extract from the utterances.
Choose from: 'mfcc', 'fbanks', 'melspec'. Default is: 'fbanks'.
deltas (int, optional): Compute delta coefficients of a tensor. '1' for first order derivative,
'2' for second order. None for not using deltas. Default: None.
config_file (string): Path to the configuration file (ini).
"""
list_wavs = utils.get_files_abspaths(path=source_path, file_type='.wav')
# frame-level feats params/config from the config file
params = utils.read_conf_file(file_name=config_file,
conf_section='DEFAULTS')
print("Computing {} for {} utterances in {}...".format(
feat_type, len(list_wavs), source_path))
for wav_file in list_wavs:
# Load wav
waveform = utils.load_wav_torch(wav_file,
max_length_in_seconds=5,
pad_and_truncate=True)
# Compute without derivatives
if deltas == 0:
# Compute features
feat = execute_extraction_function(feat_type=feat_type,
waveform=waveform,
**params)
final_dir = out_dir + '/{0}/{1}/'.format(
feat_type, os.path.basename(source_path))
utils.save_features(final_dir, feat_type, wav_file, feat)
utils.copy_conf(config_file, final_dir, feat_type)
# Compute derivatives if asked for
if deltas == 1:
# Compute features
feat = execute_extraction_function(feat_type=feat_type,
waveform=waveform,
**params)
delta1 = torchaudio.functional.compute_deltas(
feat) # compute 1st order
feat = torch.cat((feat, delta1), 1)
final_dir = out_dir + '/{0}/{1}/'.format(
feat_type, os.path.basename(source_path))
utils.save_features(final_dir, feat_type, wav_file, feat)
utils.copy_conf(config_file, final_dir, feat_type)
if deltas == 2:
# Compute features
feat = execute_extraction_function(feat_type=feat_type,
waveform=waveform,
**params)
delta1 = torchaudio.functional.compute_deltas(
feat) # compute 1st order
delta2 = torchaudio.functional.compute_deltas(delta1)
feat = torch.cat((feat, delta1, delta2), 1)
final_dir = out_dir + '/{0}/{1}/'.format(
feat_type, os.path.basename(source_path))
utils.save_features(final_dir, feat_type, wav_file, feat)
utils.copy_conf(config_file, final_dir, feat_type)
writer.flush()
"""checkpoint"""
if step % 1000 == 0:
saver.save(sess,os.path.join(training_path,'fast-style-model.ckpt'),global_step=step)#保存variable_to_restore中的参数值
except tf.errors.OutOfRangeError:
saver.save(sess,os.path.join(training_path,'fast-style-model.ckpt-done'))
tf.logging.info('Done training -- epoch limit reached')
finally:
coord.request_stop()#要求停止所有线程
coord.join(threads)#将线程并入主线程，删除
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO) #将INFO及其以上的警告信息显示在屏幕上
args = parse_args() #设定命令行参数，主要是configure document 存储位置
FLAGS = utils.read_conf_file(args.conf) #读取configure
main(FLAGS)
#注意一个区别，tf.app.run()一般会与tf.app.flags.DEFINE_string()（定义命令行，同argparse.add_argument() ; FLAGS = tf.app.FLASG(读取命令行参数，如FLAGS.conf) 联用
#而argparse设定命令行参数，返回args=parse_args()，将命令行参数args作为main()的形参；
#总结一下train.py的思路
#step1：取出loss_model，not train
#step2:将origin image进行input前的预处理
#step2:将preprocessed origin输入“图像生成网络”，形成generated，“图像生成网络”需要train
#step3:将generated进行input loss model前的预处理
#step4:将preprocessed origin和preprocessed generated送入loss model，得到各层的输出endpoints_dict
#step5:计算内容损失，和，风格损失，得到total_loss
#step5:建立需要训练的参数的list，以及需要restore and save的参数list
#step6:利用Adam梯度下降来优化total_loss，需要训练的参数放在variable_to_train list中
#step6:将全局变量和局部变量初始化
"""开始训练"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
start_time = time.time()
try:
while not coord.should_stop():
_, loss_t, step = sess.run([train_op, loss, global_step])
elapsed_time = time.time() - start_time
start_time = time.time()
if step % 10 == 0:
tf.logging.info(
'step: %d, total Loss %f, secs/step: %f,%s' % (step, loss_t, elapsed_time, time.asctime()))
"""checkpoint"""
if step % 50 == 0:
tf.logging.info('saving check point...')
saver.save(sess, os.path.join(training_path, FLAGS.naming + '.ckpt'), global_step=step)
except tf.errors.OutOfRangeError:
saver.save(sess, os.path.join(training_path, 'fast-style-model.ckpt-done'))
tf.logging.info('Done training -- epoch limit reached')
finally:
coord.request_stop()
tf.logging.info('coordinator stop')
coord.join(threads)
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
args = parse_args()
FLAGS = utils.read_conf_file(args.conf)
main(FLAGS)
