def main(_):
pp.pprint(flags.FLAGS.__flags)
if FLAGS.input_width is None:
FLAGS.input_width = FLAGS.input_height
if FLAGS.output_width is None:
FLAGS.output_width = FLAGS.output_height
if not os.path.exists(LOGDIR):
os.makedirs(LOGDIR)
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
run_config = tf.ConfigProto()
run_config.gpu_options.allow_growth=True
print("FLAGs " + str(FLAGS.dataset))
with tf.Session(config=run_config) as sess:
model = BlockGAN(
sess,
input_width=FLAGS.input_width,
input_height=FLAGS.input_height,
output_width=FLAGS.output_width,
output_height=FLAGS.output_height,
dataset_name=FLAGS.dataset,
input_fname_pattern=FLAGS.input_fname_pattern)
model.build(cfg['build_func'])
show_all_variables()
if FLAGS.train:
train_func = eval("model." + (cfg['train_func']))
train_func(FLAGS)
else:
if not model.load(LOGDIR)[0]:
raise Exception("[!] Train a model first, then run test mode")
model.sample_HoloGAN(FLAGS)
def main(_):
if not os.path.exists(LOGDIR):
os.makedirs(LOGDIR)
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
run_config = tf.ConfigProto()
run_config.gpu_options.allow_growth = True
emb_graph = None
if ADD_EMBEDDING:
emb_graph = load_pb(str(cfg.emb_tf_model))
with tf.Session(config=run_config, graph=emb_graph) as sess:
model = HoloGAN(
sess,
emb_graph,
input_width=cfg.input_width,
input_height=cfg.input_height,
output_width=cfg.output_width,
output_height=cfg.output_height,
dataset_name=cfg.dataset,
input_fname_pattern=cfg.input_fname_pattern,
crop=cfg.crop)
model.build(cfg.build_func)
show_all_variables()
if cfg.train:
train_func = eval("model." + cfg.train_func)
train_func()
else:
if not model.load(LOGDIR)[0]:
raise Exception("[!] Train a model first, then run test mode")
model.sample_HoloGAN()
def main(_):
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
pp.pprint(flags.FLAGS.__flags)
if FLAGS.input_width is None:
FLAGS.input_width = FLAGS.input_height
if FLAGS.output_width is None:
FLAGS.output_width = FLAGS.output_height
if not os.path.exists(LOGDIR):
os.makedirs(LOGDIR)
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
run_config = tf.ConfigProto()
run_config.gpu_options.allow_growth=True
print("FLAGs " + str(FLAGS.dataset))
with tf.Session(config=run_config) as sess:
model = HoloGAN(
sess,
input_width=FLAGS.input_width,
input_height=FLAGS.input_height,
output_width=FLAGS.output_width,
output_height=FLAGS.output_height,
dataset_name=FLAGS.dataset,
input_fname_pattern=FLAGS.input_fname_pattern,
crop=FLAGS.crop)
model.build(cfg['build_func'])
show_all_variables()
if FLAGS.train:
print("FLAGS.train: ", FLAGS.train)
print("FLAGS.rotate_azimuth: ", FLAGS.rotate_azimuth)
train_func = eval("model." + (cfg['train_func']))
train_func(FLAGS)
else:
print("FLAGS.train: ", FLAGS.train)
print("FLAGS.rotate_azimuth: ", FLAGS.rotate_azimuth)
if not model.load(LOGDIR)[0]:
raise Exception("[!] Train a model first, then run test mode")
# here are eight ways to sample images for different purposes
#model.sample_HoloGAN(FLAGS)
#model.sample_HoloGAN_target_image_tuple(FLAGS)
#model.sample_HoloGAN_target_image_divided(FLAGS)
#model.sample_HoloGAN_target_image_update_tuple(FLAGS)
#model.sample_HoloGAN_target_image_update_divided(FLAGS)
#model.sample_HoloGAN_many(FLAGS, amount=10000)
#model.sample_HoloGAN_many_target_image(FLAGS, amount=10000)
model.sample_HoloGAN_many_target_image_update(FLAGS, start_idx=9000, over_idx=10000, update_num=3)
def main(_):
# pp.pprint(flags.FLAGS.__flags)
if FLAGS.input_width is None:
FLAGS.input_width = FLAGS.input_height
if FLAGS.output_width is None:
FLAGS.output_width = FLAGS.output_height
if not os.path.exists(OUTPUT_DIR):
os.makedirs(OUTPUT_DIR)
run_config = tf.compat.v1.ConfigProto()
run_config.gpu_options.allow_growth = True
with tf.compat.v1.Session(config=run_config) as sess:
model = HoloGAN(sess,
input_width=FLAGS.input_width,
input_height=FLAGS.input_height,
output_width=FLAGS.output_width,
output_height=FLAGS.output_height,
dataset_name=FLAGS.dataset,
input_fname_pattern=FLAGS.input_fname_pattern,
crop=FLAGS.crop)
model.build(cfg['build_func'])
show_all_variables()
if FLAGS.train:
train_func = eval("model." + (cfg['train_func']))
train_func(FLAGS)
else:
if not model.load()[0]:
raise Exception("[!] Train a model first, then run test mode")
if str.lower(str(cfg["z_map"])) == "true":
model.train_z_map(FLAGS)
elif str.lower(str(cfg["sample"])) == "true":
model.sample_HoloGAN(FLAGS)
elif str.lower(str(cfg["generate"])) == "true":
model.generate_images(FLAGS)