def generate_latent_walk(checkpoint_dir, dataset_name, output_size, n_epochs,
jump_length, output_file_name):
n_jumps = n_epochs * 64
boundary = 1.3
z = np.zeros((n_jumps, 100))
walk = np.zeros((n_jumps, output_size, output_size, 3))
for t in range(1, n_jumps):
jumps = mixture_pareto(mu=0.04, alpha=1.6, size=[1, 100])
# keep walk confined within hypercube with reflective boundaries
new_z = z[t - 1, :] + jumps
outside_domain_left = new_z < -boundary
outside_domain_right = new_z > boundary
new_z_2 = new_z[:]
new_z_2[outside_domain_left] = -boundary - (
new_z[outside_domain_left] + boundary)
new_z_2[outside_domain_right] = boundary - (
new_z[outside_domain_right] - boundary)
new_z[outside_domain_left] = new_z_2[outside_domain_left]
new_z[outside_domain_right] = new_z_2[outside_domain_right]
z[t, :] = new_z
with tf.Session() as sess:
dcgan = DCGAN(sess,
checkpoint_dir=checkpoint_dir,
dataset_name=dataset_name,
output_size=output_size,
is_train=False)
for e in range(n_epochs):
this_start = e * 64
this_end = (e + 1) * 64
walk[this_start:this_end, :, :, :] = dcgan.sample(
z[this_start:this_end, :])
save_latent_walk(walk, output_file_name)
return walk
def main(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
if not os.path.exists(FLAGS.sample_dir):
os.makedirs(FLAGS.sample_dir)
with tf.Session() as sess:
dcgan = DCGAN(sess,
phase=FLAGS.phase,
image_size=FLAGS.image_size,
batch_size=FLAGS.batch_size,
output_size=FLAGS.output_size,
c_dim=FLAGS.c_dim,
is_crop=FLAGS.is_crop,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
if FLAGS.is_train:
dcgan.train(FLAGS)
else:
dcgan.sample(64)
dcgan = DCGAN(sess,
wav_size=wav_size,
batch_size=batch_size,
dataset_name=dataset,
is_crop=is_crop,
checkpoint_dir=checkpoint_dir)
dcgan.load(checkpoint_dir)
data = glob(os.path.join("./training", "*.wav"))
sample_file = data[0]
sample = tensorflow_wav.get_wav(sample_file)
print(sample)
full_audio = []
for i in range(1):
audio = dcgan.sample()
audio = np.reshape(audio, [-1])
print("Audio shape", np.shape(audio))
full_audio += audio[:bitrate * batch_size].tolist()
print("Full audio shape", np.shape(full_audio))
samplewav = sample.copy()
samplewav
print("Generated stats 'min', 'max', 'mean', 'stddev'",
np.min(full_audio), np.max(full_audio), np.mean(full_audio),
np.std(full_audio))
samplewav['data'] = np.reshape(np.array(full_audio), [-1, 64])
print("samplewav shape", np.shape(samplewav['data']))
filename = "./compositions/song.wav.stft"
