def train_net(config):
# enable cudnn
cudnn.benchmark = True
data_loader = get_loader(config)
solver = Solver(config, data_loader=data_loader, device="cuda")
solver.train()
def train_net():
# enable cudnn
cudnn.benchmark = True
data_loader = get_loader(dataset_config, config, mode="train")
solver = Solver_makeupGAN(config, data_loader=data_loader, device="cuda")
solver.train()
def train_net(config):
# enable cudnn https://zhuanlan.zhihu.com/p/73711222
cudnn.benchmark = True
data_loader = get_loader(config)
#solver = Solver(config, data_loader=data_loader, device="cuda")
solver = Solver(config, data_loader=data_loader, device=config.device)
solver.train()
def train_net():
# enable cudnn
cudnn.benchmark = True
data_loaders = get_loader(config, mode="train") # return train&test
#get the solver
if args.model == 'cycleGAN':
solver = Solver_cycleGAN(data_loaders, config, dataset_config)
elif args.model == 'makeupGAN':
solver = Solver_makeupGAN(data_loaders, config, dataset_config)
else:
print("model that not support")
exit()
solver.train()
def tes_net():
# enable cudnn
cudnn.benchmark = True
# get the DataLoader
data_loaders = get_loader(dataset_config, config, mode="test")
#get the solver
if args.model == 'cycleGAN':
solver = Solver_cycleGAN(data_loaders, config, dataset_config)
elif args.model =='makeupGAN':
solver = Solver_makeupGAN(data_loaders, config, dataset_config)
else:
print("model that not support")
exit()
solver.test()
def train_net():
# enable cudnn
cudnn.benchmark = True
data_loaders = get_loader(dataset_config, config, mode="train")
solver = Solver_PSGAN(data_loaders, config, dataset_config)
solver.train()
from config import config, dataset_config
from dataloder import get_loader
from psgan.inference import Inference
from setup import setup_config, setup_argparser
import numpy as np
import neupeak.utils.webcv2 as cv2
args = setup_argparser().parse_args()
config = setup_config(args)
loader = get_loader(config)
inference = Inference(config)
for source_input, reference_input in loader:
ret = inference.solver.test(*source_input, *reference_input)
source = (source_input[0].squeeze(0).squeeze(0).numpy().transpose(1, 2, 0)
+ 1) / 2
reference = (reference_input[0].squeeze(0).squeeze(0).numpy().transpose(
1, 2, 0) + 1) / 2
mask_s = (source_input[1][0, :, 0].numpy().transpose(1, 2, 0) * 255 +
0.5).astype(np.uint8)
mask_r = (
reference_input[1][0, :, 0].squeeze(2).numpy().transpose(1, 2, 0) * 255
+ 0.5).astype(np.uint8)
cv2.imshow("source", source[..., ::-1])
cv2.imshow("reference", reference[..., ::-1])
cv2.imshow("mask_s", mask_s)
cv2.imshow("mask_r", mask_r)
cv2.imshow("ret", np.asarray(ret)[..., ::-1])
cv2.waitKey()