def main(_):
tfconfig = tf.ConfigProto(allow_soft_placement = True)
tfconfig.gpu_options.allow_growth = True
with tf.Session(config = tfconfig) as sess:
model = cycleGAN(sess,FLAGS)
if FLAGS.phase == 'train':
print("Training ...")
model.train(FLAGS)
def main():
args = get_args()
create_link(args.dataset_dir)
if args.training:
print("Training")
model = md.cycleGAN(args)
model.train(args)
if args.testing:
print("Testing")
tst.test(args)
def main():
args = get_args()
create_link(args.dataset_dir)
str_ids = args.gpu_ids.split(',')
args.gpu_ids = []
for str_id in str_ids:
id = int(str_id)
if id >= 0:
args.gpu_ids.append(id)
print(not args.no_dropout)
if args.training:
print("Training")
model = md.cycleGAN(args)
model.train(args)
if args.testing:
print("Testing")
model = md.cycleGAN(args)
model.test(args)
def main():
args = get_args()
create_link(args.dataset_dir)
str_ids = args.gpu_ids.split(',')
args.gpu_ids = []
for str_id in str_ids:
id = int(str_id)
if id >= 0:
args.gpu_ids.append(id)
print(not args.no_dropout)
md = model.cycleGAN(args)
md.train(args)
def main(args):
create_link(args.dataset_dir)
args.gpu_ids = []
for i in range(torch.cuda.device_count()):
args.gpu_ids.append(i)
if args.training:
print('Training')
model = md.cycleGAN(args)
model.train(args)
if args.gen_samples:
print('Generating samples')
gen_samples.gen_samples(args, 'last')
def main(_):
"""
global main method
"""
# input ('Main method will start , continue? press [Enter] to continue...')
tfconfig = tf.ConfigProto(allow_soft_placement=True)
tfconfig.gpu_options.allow_growth = True
# tfconfig.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.InteractiveSession(config=tfconfig)
gan = cycleGAN(sess, args)
if args.is_train:
gan.train(args)
else:
gan.test(args)
