def test_sequence_keyframes_linear_random_batch(self):
n_keyframes = 10
n_vector = 100
n_label = 1000
num_frames = 100
batch_size = 7 # pick something that doesn't divide num_frames
batch_div = int(num_frames // batch_size)
batch_rem = 1 if int(num_frames % batch_size) > 0 else 0
batch_count = batch_div + batch_rem
keyframes = np.asarray([
create_random_keyframe(n_vector, n_label)
for i in range(n_keyframes)
])
z, label, trunc = latent_space.sequence_keyframes(
keyframes,
num_frames,
batch_size=batch_size,
interp_method='linear')
assert (num_frames == z.shape[0]),\
'z sequence: target frame count: %s; actual shape: %s' % (num_frames, z.shape)
assert (num_frames == label.shape[0]),\
'label sequence: target frame count: %s; actual shape: %s' % (num_frames, label.shape)
assert (batch_count == trunc.shape[0]),\
'trunc sequence: target frame count: %s; actual shape: %s' % (batch_count, trunc.shape)
def main():
args = handle_args()
# get animation keyframes from ganbreeder
print('Downloading keyframe info from ganbreeder...')
keyframes = ganbreeder.get_info_batch(args.username, args.password, args.keys)
# interpolate path through input space
print('Interpolating path through input space...')
try:
z_seq, label_seq, truncation_seq = latent_space.sequence_keyframes(
keyframes,
args.nframes,
batch_size=args.nbatch,
interp_method=args.interp,
loop=args.loop)
except ValueError as e:
print(e)
print('ERROR: Interpolation failed. Make sure you are using at least 3 keys (4 if --no-loop is enabled)')
print('If you would like to use fewer keys, try using the --interp linear argument')
return 1
# sample the GAN
print('Loading bigGAN...')
gan = biggan.BigGAN()
path = '' if args.output_dir == None else str(args.output_dir)
prefix = '' if args.prefix == None else str(args.prefix)
saver = image_utils.ImageSaver(output_dir=path, prefix=prefix)
print('Image files will be saved to: '+path + prefix)
print('Sampling from bigGAN...')
gan.sample(z_seq, label_seq, truncation=truncation_seq, batch_size=args.nbatch, save_callback=saver.save)
print('Done.')
return 0
def test_sequence_keyframes_linear_random_basic(self):
n_keyframes = 10
n_vector = 100
n_label = 1000
num_frames = 100
keyframes = np.asarray([
create_random_keyframe(n_vector, n_label)
for i in range(n_keyframes)
])
z, label, trunc = latent_space.sequence_keyframes(
keyframes, num_frames, batch_size=1, interp_method='linear')
assert (num_frames == z.shape[0]),\
'z sequence: target frame count: %s; actual shape: %s' % (num_frames, z.shape)
assert (num_frames == label.shape[0]),\
'label sequence: target frame count: %s; actual shape: %s' % (num_frames, label.shape)
assert (num_frames == trunc.shape[0]),\
'trunc sequence: target frame count: %s; actual shape: %s' % (num_frames, trunc.shape)
def test_sequence_keyframes_cubic_random_batch_oob(self):
n_keyframes = 10
n_vector = 100
n_label = 1000
num_frames = 100
batch_size = 150 # pick something that doesn't divide num_frames
batch_div = int(num_frames // batch_size)
batch_rem = 1 if int(num_frames % batch_size) > 0 else 0
batch_count = batch_div + batch_rem
keyframes = np.asarray([
create_random_keyframe(n_vector, n_label)
for i in range(n_keyframes)
])
z, label, trunc = latent_space.sequence_keyframes(
keyframes,
num_frames,
batch_size=batch_size,
interp_method='cubic')