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:
cdgan = CrossDomainGAN(sess,
image_size=FLAGS.image_size,
batch_size=FLAGS.batch_size,
c_dim=FLAGS.c_dim,
dataset_name=FLAGS.dataset,
checkpoint_dir=FLAGS.checkpoint_dir,
sample_dir=FLAGS.sample_dir)
if FLAGS.is_train:
cdgan.train(FLAGS)
else:
cdgan.load(FLAGS.checkpoint_dir)
if FLAGS.visualize:
# to_json("./web/js/layers.js", [dcgan.h0_w, dcgan.h0_b, dcgan.g_bn0],
# [dcgan.h1_w, dcgan.h1_b, dcgan.g_bn1],
# [dcgan.h2_w, dcgan.h2_b, dcgan.g_bn2],
# [dcgan.h3_w, dcgan.h3_b, dcgan.g_bn3],
# [dcgan.h4_w, dcgan.h4_b, None])
# Below is codes for visualization
OPTION = 2
visualize(sess, dcgan, FLAGS, OPTION)
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(_):
pp.pprint(flags.FLAGS.__flags)
if not os.path.exists(FLAGS.checkpoint_dir):
os.makedirs(FLAGS.checkpoint_dir)
with tf.Session() as sess:
model = TinyVGG(sess, image_size=FLAGS.image_size, batch_size=FLAGS.batch_size, c_dim=FLAGS.c_dim,
y_dim=FLAGS.y_dim, dataset_name=FLAGS.dataset, checkpoint_dir=FLAGS.checkpoint_dir)
if FLAGS.is_train:
model.train(FLAGS)
else:
model.load(FLAGS.checkpoint_dir)
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)