def main(_):
args = parser.parse_args()
with tf.Session() as sess:
model = Face(sess, args)
if args.phase == "train":
model.train(args)
print('train mode')
def load(parsr,website,args):
from parse import parser
deflt={key:None for key in vars(parsr)}
parser.set_defaults(**deflt)
par=parser.parse_args(args[1:])
number=parsr.number[0]
lines,nb=loadlines()
if lines==0: return
if number<0: number=nb-number
if number>nb or number<0: print "This history line doesn't exist"
line=lines[number].split('\t')
model=save_patern[1:-2].split('}\t{')
for i in xrange(len(line)):
try:val=save_type[i](line[i])
except: pass
if getattr(par,model[i],None)==None: setattr(par,model[i],val)
par.nb_pages=[par.stop-par.start+1]
print par
return par
def main(_):
args = parser.parse_args()
tfconfig = tf.ConfigProto(allow_soft_placement=False)
tfconfig.gpu_options.allow_growth = True
with tf.Session(config=tfconfig) as sess:
model = Artgan(sess, args)
if args.phase == 'train':
print("Train.")
model.train(args, ckpt_nmbr=args.ckpt_nmbr)
if args.phase == 'inference' or args.phase == 'test':
print("Inference.")
model.inference(args,
args.inference_images_dir,
resize_to_original=False,
to_save_dir=args.save_dir,
ckpt_nmbr=args.ckpt_nmbr)
if args.phase == 'inference_on_frames' or args.phase == 'test_on_frames':
print("Inference on frames sequence.")
model.inference_video(args,
path_to_folder=args.inference_images_dir[0],
resize_to_original=False,
to_save_dir=args.save_dir,
ckpt_nmbr=args.ckpt_nmbr)
if args.phase == "export_layers":
print("export_layers.")
model.export_layers(args.inference_images_dir,
to_save_dir=args.save_dir,
ckpt_nmbr=args.ckpt_nmbr)
if args.phase == "export_arg":
print("export_arg.")
model.export_arg(args.ckpt_name)
sess.close()
def main(_):
args = parser.parse_args()
log.init("FaceNeural", logging.DEBUG, log_path="output/log.txt")
with tf.Session() as sess:
if args.phase == "train":
model = Face(sess, args)
model.train(args)
log.info('train mode')
elif args.phase == "inference":
log.info("inference")
model = Face(sess, args)
model.inference(args)
elif args.phase == "lightcnn":
log.info("light cnn test")
elif args.phase == "faceparsing":
log.info("faceparsing")
elif args.phase == "net":
log.info("net start with ports (%d, %d)", 5010, 5011)
net = Net(5010, 5011)
while True:
r_input = raw_input("command: \n")
if r_input == "s":
msg = raw_input("input: ")
net.only_send(msg)
elif r_input == 'r':
msg = raw_input("input: ")
net.send_recv(msg)
elif r_input == "q":
net.only_send("quit")
net.close()
break
else:
log.error("unknown code, quit")
net.close()
break
and arguments.use_gpu)
if support_gpu and arguments.use_gpu:
if not arguments.gpuid:
arguments.gpuid = 0
dev = torch.device("cuda:%d" % arguments.gpuid)
return True, dev
else:
dev = torch.device("cpu")
return False, dev
if __name__ == '__main__':
"""
程序入口函数
"""
args = parser.parse_args()
log.init("FaceNeural", logging.INFO, log_path="./output/neural_log.txt")
cuda, device = init_device(args)
if args.phase == "train_imitator":
log.info('imitator train mode')
imitator = Imitator("neural imitator", args)
if cuda:
imitator.cuda()
imitator.batch_train(cuda)
elif args.phase == "train_extractor":
log.info('feature extractor train mode')
extractor = Extractor("neural extractor", args)
if cuda:
extractor.cuda()
extractor.batch_train(cuda)
