def create_from_image_folders(datadir, jpg=False, shuffle=True, size=None):
assert os.path.isdir(datadir)
imgs = []
labels = []
for root, subdirs, files in os.walk(datadir):
for i, subdir in enumerate(subdirs):
tmp_list = img_list(os.path.join(root, subdir))
imgs = imgs + tmp_list
labels = labels + [i] * len(tmp_list)
labels = np.array(labels)
onehot = np.zeros((labels.size, np.max(labels) + 1), dtype=np.float32)
onehot[np.arange(labels.size), labels] = 1.
assert len(imgs) > 0, ' No input images found!'
sample_img = np.asarray(PIL.Image.open(imgs[0]))
sample_shape = sample_img.shape
channels = sample_shape[2] if sample_img.ndim == 3 else 1
assert channels in [1, 3, 4], ' Weird color dim: %d' % channels
print(' Making dataset ..', datadir, sample_shape,
'%d labels' % (np.max(labels) + 1))
if jpg is True: print(' Loading JPG as is!')
with TFRecordExporter(datadir, len(imgs)) as tfr:
order = tfr.choose_shuffled_order() if shuffle else np.arange(
len(imgs))
pbar = ProgressBar(order.size)
for idx in range(order.size):
img_path = imgs[order[idx]]
tfr.add_image(img_path, jpg=jpg, size=size)
pbar.upd()
tfr.add_labels(onehot[order])
return tfr.tfr_file, len(imgs)
def make_transit(lat1, lat2, fcount, start_frame=0):
pbar = ProgressBar(fcount)
for i in range(fcount):
img = render_latent_mix(lat1, lat2, i/fcount)
fname = os.path.join(a.out_dir, 'ttt', "%05d.jpg" % (i+start_frame))
if i%2==0:
cv2.imshow('latent', img[:,:,::-1])
cv2.waitKey(10)
imsave(fname, img)
pbar.upd()
def make_loop(base_latent, direction, lrange, fcount, start_frame=0):
coeffs = get_coeffs_dir(lrange, fcount//2)
pbar = ProgressBar(fcount)
for i in range(fcount):
img = render_latent_dir(base_latent, direction, coeffs[i])
fname1 = os.path.join(a.out_dir, 'ttt', "%05d.jpg" % (i+start_frame))
if i%2==0:
cv2.imshow('latent', img[:,:,::-1])
cv2.waitKey(10)
imsave(fname1, img)
pbar.upd()
def create_from_images(dataset, jpg=False, shuffle=True, size=None):
assert os.path.isdir(dataset)
image_filenames = sorted(img_list(dataset))
assert len(image_filenames) > 0, ' No input images found!'
sample_img = np.asarray(PIL.Image.open(image_filenames[0]))
sample_shape = sample_img.shape
channels = sample_shape[2] if sample_img.ndim == 3 else 1
assert channels in [1,3,4], ' Weird color dim: %d' % channels
print(' Making dataset', dataset, sample_shape)
if jpg is True: print(' Loading JPG as is!')
with TFRecordExporter(dataset, len(image_filenames)) as tfr:
order = tfr.choose_shuffled_order() if shuffle else np.arange(len(image_filenames))
pbar = ProgressBar(order.size)
for idx in range(order.size):
img_path = image_filenames[order[idx]]
tfr.add_image(img_path, jpg=jpg, size=size)
pbar.upd()
return tfr.tfr_file, len(image_filenames)
def project_image(proj, targets, work_dir, resolution, num_snapshots):
filename = osp.join(work_dir, basename(work_dir))
video_out = cv2.VideoWriter(filename + '.avi',
cv2.VideoWriter_fourcc('M', 'J', 'P', 'G'), 24,
resolution)
snapshot_steps = set(proj.num_steps - np.linspace(
0, proj.num_steps, num_snapshots, endpoint=False, dtype=int))
misc.save_image_grid(targets, filename + '.jpg', drange=[-1, 1])
proj.start(targets)
pbar = ProgressBar(proj.num_steps)
while proj.get_cur_step() < proj.num_steps:
proj.step()
write_video_frame(proj, video_out)
if proj.get_cur_step() in snapshot_steps:
misc.save_image_grid(proj.get_images(),
filename + '-%04d.jpg' % proj.get_cur_step(),
drange=[-1, 1])
pbar.upd()
dlats = proj.get_dlatents()
np.save(filename + '-%04d.npy' % proj.get_cur_step(), dlats)
video_out.release()
def main():
os.makedirs(a.out_dir, exist_ok=True)
# setup generator
fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
Gs_kwargs = dnnlib.EasyDict()
Gs_kwargs.func_name = 'training.stylegan2_multi.G_main'
Gs_kwargs.verbose = a.verbose
Gs_kwargs.size = a.size
Gs_kwargs.scale_type = a.scale_type
Gs_kwargs.impl = a.ops
# load model with arguments
sess = tflib.init_tf({'allow_soft_placement': True})
pkl_name = osp.splitext(a.model)[0]
with open(pkl_name + '.pkl', 'rb') as file:
network = pickle.load(file, encoding='latin1')
try:
_, _, network = network
except:
pass
for k in list(network.static_kwargs.keys()):
Gs_kwargs[k] = network.static_kwargs[k]
# reload custom network, if needed
if '.pkl' in a.model.lower():
print(' .. Gs from pkl ..', basename(a.model))
Gs = network
else: # reconstruct network
print(' .. Gs custom ..', basename(a.model))
Gs = tflib.Network('Gs', **Gs_kwargs)
Gs.copy_vars_from(network)
z_dim = Gs.input_shape[1]
dz_dim = 512 # dlatent_size
try:
dl_dim = 2 * (int(np.floor(np.log2(Gs_kwargs.resolution))) - 1)
except:
print(' Resave model, no resolution kwarg found!')
exit(1)
dlat_shape = (1, dl_dim, dz_dim) # [1,18,512]
# read saved latents
if a.dlatents is not None and osp.isfile(a.dlatents):
key_dlatents = load_latents(a.dlatents)
if len(key_dlatents.shape) == 2:
key_dlatents = np.expand_dims(key_dlatents, 0)
elif a.dlatents is not None and osp.isdir(a.dlatents):
# if a.dlatents.endswith('/') or a.dlatents.endswith('\\'): a.dlatents = a.dlatents[:-1]
key_dlatents = []
npy_list = file_list(a.dlatents, 'npy')
for npy in npy_list:
key_dlatent = load_latents(npy)
if len(key_dlatent.shape) == 2:
key_dlatent = np.expand_dims(key_dlatent, 0)
key_dlatents.append(key_dlatent)
key_dlatents = np.concatenate(key_dlatents) # [frm,18,512]
else:
print(' No input dlatents found')
exit()
key_dlatents = key_dlatents[:, np.newaxis] # [frm,1,18,512]
print(' key dlatents', key_dlatents.shape)
# replace higher layers with single (style) latent
if a.style_npy_file is not None:
print(' styling with latent', a.style_npy_file)
style_dlatent = load_latents(a.style_npy_file)
while len(style_dlatent.shape) < 4:
style_dlatent = np.expand_dims(style_dlatent, 0)
# try replacing 5 by other value, less than dl_dim
key_dlatents[:, :,
range(5, dl_dim), :] = style_dlatent[:, :,
range(5, dl_dim), :]
frames = key_dlatents.shape[0] * a.fstep
dlatents = latent_anima(dlat_shape,
frames,
a.fstep,
key_latents=key_dlatents,
cubic=a.cubic,
verbose=True) # [frm,1,512]
print(' dlatents', dlatents.shape)
frame_count = dlatents.shape[0]
# truncation trick
dlatent_avg = Gs.get_var('dlatent_avg') # (512,)
tr_range = range(0, 8)
dlatents[:, :, tr_range, :] = dlatent_avg + (dlatents[:, :, tr_range, :] -
dlatent_avg) * a.trunc
# distort image by tweaking initial const layer
if a.digress > 0:
try:
latent_size = Gs.static_kwargs['latent_size']
except:
latent_size = 512 # default latent size
try:
init_res = Gs.static_kwargs['init_res']
except:
init_res = (4, 4) # default initial layer size
dconst = a.digress * latent_anima([1, latent_size, *init_res],
frames,
a.fstep,
cubic=True,
verbose=False)
else:
dconst = np.zeros([frame_count, 1, 1, 1, 1])
# generate images from latent timeline
pbar = ProgressBar(frame_count)
for i in range(frame_count):
if a.digress is True:
tf.get_default_session().run(tf.assign(wvars[0], wts[i]))
# generate multi-latent result
if Gs.num_inputs == 2:
output = Gs.components.synthesis.run(dlatents[i],
randomize_noise=False,
output_transform=fmt,
minibatch_size=1)
else:
output = Gs.components.synthesis.run(dlatents[i], [None],
dconst[i],
randomize_noise=False,
output_transform=fmt,
minibatch_size=1)
ext = 'png' if output.shape[3] == 4 else 'jpg'
filename = osp.join(a.out_dir, "%06d.%s" % (i, ext))
imsave(filename, output[0])
pbar.upd()
def main():
os.makedirs(a.out_dir, exist_ok=True)
np.random.seed(seed=696)
# parse filename to model parameters
mparams = basename(a.model).split('-')
res = int(mparams[1])
cfg = mparams[2]
# setup generator
fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
Gs_kwargs = dnnlib.EasyDict()
Gs_kwargs.func_name = 'training.stylegan2_custom.G_main'
Gs_kwargs.verbose = False
Gs_kwargs.resolution = res
Gs_kwargs.size = a.size
Gs_kwargs.scale_type = a.scale_type
Gs_kwargs.latent_size = a.latent_size
Gs_kwargs.impl = a.ops
if cfg.lower() == 'f':
Gs_kwargs.synthesis_func = 'G_synthesis_stylegan2'
elif cfg.lower() == 'e':
Gs_kwargs.synthesis_func = 'G_synthesis_stylegan2'
Gs_kwargs.fmap_base = 8 << 10
else:
print(' old modes [A-D] not implemented'); exit()
# check initial model resolution
if len(mparams) > 3:
if 'x' in mparams[3].lower():
init_res = [int(x) for x in mparams[3].lower().split('x')]
Gs_kwargs.init_res = list(reversed(init_res)) # [H,W]
# load model, check channels
sess = tflib.init_tf({'allow_soft_placement':True})
pkl_name = osp.splitext(a.model)[0]
with open(pkl_name + '.pkl', 'rb') as file:
network = pickle.load(file, encoding='latin1')
try: _, _, Gs = network
except: Gs = network
Gs_kwargs.num_channels = Gs.output_shape[1]
# reload custom network, if needed
if '.pkl' in a.model.lower():
print(' .. Gs from pkl ..')
else:
print(' .. Gs custom ..')
Gs = tflib.Network('Gs', **Gs_kwargs)
Gs.copy_vars_from(network)
# Gs.print_layers()
print(' out shape', Gs.output_shape[1:])
if a.size is None: a.size = Gs.output_shape[2:]
z_dim = Gs.input_shape[1]
shape = (1, z_dim)
print(' making timeline..')
latents = latent_anima(shape, a.frames, a.fstep, cubic=a.cubic, gauss=a.gauss, verbose=True) # [frm,1,512]
print(' latents', latents.shape)
# generate images from latent timeline
frame_count = latents.shape[0]
pbar = ProgressBar(frame_count)
for i in range(frame_count):
output = Gs.run(latents[i], [None], truncation_psi=a.trunc, randomize_noise=False, output_transform=fmt)
ext = 'png' if output.shape[3]==4 else 'jpg'
filename = osp.join(a.out_dir, "%05d.%s" % (i,ext))
imsave(filename, output[0])
pbar.upd()
# convert latents to dlatents, save them
latents = latents.squeeze(1) # [frm,512]
dlatents = Gs.components.mapping.run(latents, None, latent_size=z_dim, dtype='float16') # [frm,18,512]
filename = '{}-{}-{}.npy'.format(basename(a.model), a.size[1], a.size[0])
filename = osp.join(osp.dirname(a.out_dir), filename)
np.save(filename, dlatents)
print('saved dlatents', dlatents.shape, 'to', filename)
def main():
os.makedirs(a.out_dir, exist_ok=True)
# parse filename to model parameters
mparams = basename(a.model).split('-')
res = int(mparams[1])
cfg = mparams[2]
# setup generator
fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
Gs_kwargs = dnnlib.EasyDict()
Gs_kwargs.func_name = 'training.stylegan2_custom.G_main'
Gs_kwargs.verbose = False
Gs_kwargs.resolution = res
Gs_kwargs.size = a.size
Gs_kwargs.scale_type = a.scale_type
Gs_kwargs.latent_size = a.latent_size
if cfg.lower() == 'f':
Gs_kwargs.synthesis_func = 'G_synthesis_stylegan2'
elif cfg.lower() == 'e':
Gs_kwargs.synthesis_func = 'G_synthesis_stylegan2'
Gs_kwargs.fmap_base = 8 << 10
else:
print(' old modes [A-D] not implemented')
exit()
# check initial model resolution
if len(mparams) > 3:
if 'x' in mparams[3].lower():
init_res = [int(x) for x in mparams[3].lower().split('x')]
Gs_kwargs.init_res = list(reversed(init_res)) # [H,W]
# load model, check channels
sess = tflib.init_tf({'allow_soft_placement': True})
pkl_name = osp.splitext(a.model)[0]
with open(pkl_name + '.pkl', 'rb') as file:
network = pickle.load(file, encoding='latin1')
try:
_, _, Gs = network
except:
Gs = network
Gs_kwargs.num_channels = Gs.output_shape[1]
# reload custom network, if needed
if '.pkl' in a.model.lower():
print(' .. Gs from pkl ..')
else:
print(' .. Gs custom ..')
Gs = tflib.Network('Gs', **Gs_kwargs)
Gs.copy_vars_from(network)
z_dim = Gs.input_shape[1]
dz_dim = a.dlatent_size # 512
dl_dim = 2 * (int(np.floor(np.log2(res))) - 1)
dlat_shape = (1, dl_dim, dz_dim) # [1,18,512]
# read saved latents
if a.dlatents is not None and osp.isfile(a.dlatents):
key_dlatents = load_latents(a.dlatents)
if len(key_dlatents.shape) == 2:
key_dlatents = np.expand_dims(key_dlatents, 0)
elif a.dlatents is not None and osp.isdir(a.dlatents):
# if a.dlatents.endswith('/') or a.dlatents.endswith('\\'): a.dlatents = a.dlatents[:-1]
key_dlatents = []
npy_list = file_list(a.dlatents, 'npy')
for npy in npy_list:
key_dlatent = load_latents(npy)
if len(key_dlatent.shape) == 2:
key_dlatent = np.expand_dims(key_dlatent, 0)
key_dlatents.append(key_dlatent)
key_dlatents = np.concatenate(key_dlatents) # [frm,18,512]
else:
print(' No input dlatents found')
exit()
key_dlatents = key_dlatents[:, np.newaxis] # [frm,1,18,512]
print(' key dlatents', key_dlatents.shape)
# replace higher layers with single (style) latent
if a.style_npy_file is not None:
print(' styling with latent', a.style_npy_file)
style_dlatent = load_latents(a.style_npy_file)
while len(style_dlatent.shape) < 4:
style_dlatent = np.expand_dims(style_dlatent, 0)
# try other values < dl_dim besides 5
key_dlatents[:, :,
range(5, dl_dim), :] = style_dlatent[:, :,
range(5, dl_dim), :]
frames = key_dlatents.shape[0] * a.fstep
dlatents = latent_anima(dlat_shape,
frames,
a.fstep,
key_latents=key_dlatents,
cubic=a.cubic,
verbose=True) # [frm,1,512]
print(' dlatents', dlatents.shape)
# truncation trick
dlatent_avg = Gs.get_var('dlatent_avg') # (512,)
tr_range = range(0, 8)
dlatents[:, :, tr_range, :] = dlatent_avg + (dlatents[:, :, tr_range, :] -
dlatent_avg) * a.trunc
# loop for graph frame by frame
frame_count = dlatents.shape[0]
pbar = ProgressBar(frame_count)
for i in range(frame_count):
dlatent = dlatents[i]
output = Gs.components.synthesis.run(dlatent,
randomize_noise=False,
output_transform=fmt,
minibatch_size=1)
ext = 'png' if output.shape[3] == 4 else 'jpg'
filename = osp.join(a.out_dir, "%05d.%s" % (i, ext))
imsave(filename, output[0])
pbar.upd()
def main():
os.makedirs(a.out_dir, exist_ok=True)
np.random.seed(seed=696)
# setup generator
fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
Gs_kwargs = dnnlib.EasyDict()
Gs_kwargs.func_name = 'training.stylegan2_multi.G_main'
Gs_kwargs.verbose = a.verbose
Gs_kwargs.size = a.size
Gs_kwargs.scale_type = a.scale_type
Gs_kwargs.impl = a.ops
# mask/blend latents with external latmask or by splitting the frame
if a.latmask is None:
if a.verbose is True:
print(' Latent blending w/split frame %d x %d' % (a.nX, a.nY))
n_mult = a.nX * a.nY
lmask = np.tile(np.asarray([[[[None]]]]), (1, n_mult, 1, 1))
Gs_kwargs.countW = a.nX
Gs_kwargs.countH = a.nY
Gs_kwargs.splitfine = a.splitfine
else:
if a.verbose is True: print(' Latent blending with mask', a.latmask)
n_mult = 2
if os.path.isfile(a.latmask): # single file
lmask = np.asarray([[imread(a.latmask)[:, :, 0] / 255.]]) # [h,w]
elif os.path.isdir(a.latmask): # directory with frame sequence
lmask = np.asarray([[
imread(f)[:, :, 0] / 255. for f in img_list(a.latmask)
]]) # [h,w]
else:
print(' !! Blending mask not found:', a.latmask)
exit(1)
lmask = np.concatenate((lmask, 1 - lmask), 1) # [frm,2,h,w]
Gs_kwargs.latmask_res = lmask.shape[2:]
# load model with arguments
sess = tflib.init_tf({'allow_soft_placement': True})
pkl_name = osp.splitext(a.model)[0]
with open(pkl_name + '.pkl', 'rb') as file:
network = pickle.load(file, encoding='latin1')
try:
_, _, network = network
except:
pass
for k in list(network.static_kwargs.keys()):
Gs_kwargs[k] = network.static_kwargs[k]
# reload custom network, if needed
if '.pkl' in a.model.lower():
print(' .. Gs from pkl ..', basename(a.model))
Gs = network
else: # reconstruct network
print(' .. Gs custom ..', basename(a.model))
# print(Gs_kwargs)
Gs = tflib.Network('Gs', **Gs_kwargs)
Gs.copy_vars_from(network)
if a.verbose is True:
print('kwargs:', [
'%s: %s' % (kv[0], kv[1])
for kv in sorted(Gs.static_kwargs.items())
])
if a.verbose is True: print(' out shape', Gs.output_shape[1:])
if a.size is None: a.size = Gs.output_shape[2:]
if a.verbose is True: print(' making timeline..')
lats = [] # list of [frm,1,512]
for i in range(n_mult):
lat_tmp = latent_anima((1, Gs.input_shape[1]),
a.frames,
a.fstep,
cubic=a.cubic,
gauss=a.gauss,
verbose=False) # [frm,1,512]
lats.append(lat_tmp) # list of [frm,1,512]
latents = np.concatenate(lats, 1) # [frm,X,512]
print(' latents', latents.shape)
frame_count = latents.shape[0]
# distort image by tweaking initial const layer
if a.digress > 0:
try:
latent_size = Gs.static_kwargs['latent_size']
except:
latent_size = 512 # default latent size
try:
init_res = Gs.static_kwargs['init_res']
except:
init_res = (4, 4) # default initial layer size
dconst = []
for i in range(n_mult):
dc_tmp = a.digress * latent_anima([1, latent_size, *init_res],
a.frames,
a.fstep,
cubic=True,
verbose=False)
dconst.append(dc_tmp)
dconst = np.concatenate(dconst, 1)
else:
dconst = np.zeros([frame_count, 1, 1, 1, 1])
# generate images from latent timeline
pbar = ProgressBar(frame_count)
for i in range(frame_count):
latent = latents[i] # [X,512]
latmask = lmask[i %
len(lmask)] if lmask is not None else [None] # [X,h,w]
dc = dconst[i % len(dconst)] # [X,512,4,4]
# generate multi-latent result
if Gs.num_inputs == 2:
output = Gs.run(latent, [None],
truncation_psi=a.trunc,
randomize_noise=False,
output_transform=fmt)
else:
output = Gs.run(latent, [None],
latmask,
dc,
truncation_psi=a.trunc,
randomize_noise=False,
output_transform=fmt)
# save image
ext = 'png' if output.shape[3] == 4 else 'jpg'
filename = osp.join(a.out_dir, "%06d.%s" % (i, ext))
imsave(filename, output[0])
pbar.upd()
# convert latents to dlatents, save them
if a.save_lat is True:
latents = latents.squeeze(1) # [frm,512]
dlatents = Gs.components.mapping.run(latents, None,
dtype='float16') # [frm,18,512]
filename = '{}-{}-{}.npy'.format(basename(a.model), a.size[1],
a.size[0])
filename = osp.join(osp.dirname(a.out_dir), filename)
np.save(filename, dlatents)
print('saved dlatents', dlatents.shape, 'to', filename)