initial_epoch = findLastCheckpoint(
save_dir=save_dir) # load the last model in matconvnet style
initial_epoch = 11
if initial_epoch > 0:
print('resuming by loading epoch %03d' % initial_epoch)
decompose_model.load_state_dict(
torch.load(os.path.join(save_dir,
'model_%03d.pth' % initial_epoch)))
# model = torch.load(os.path.join(save_dir, 'model_%03d.pth' % initial_epoch))
# criterion = nn.MSELoss(reduction = 'sum') # PyTorch 0.4.1
# criterion = sum_squared_error()
criterion = nn.MSELoss()
if cuda:
decompose_model = decompose_model.cuda()
# compose_model = compose_model.cuda()
# device_ids = [0]
# model = nn.DataParallel(model, device_ids=device_ids).cuda()
# criterion = criterion.cuda()
optimizer_decompose = optim.Adam(decompose_model.parameters(), lr=args.lr)
scheduler_decompose = MultiStepLR(optimizer_decompose,
milestones=[30, 60, 90],
gamma=0.2) # learning rates
# optimizer_compose = optim.Adam(compose_model.parameters(), lr=args.lr)
# scheduler_compose = MultiStepLR(optimizer_compose, milestones=[30, 60, 90], gamma=0.2) # learning rates
for epoch in range(initial_epoch, n_epoch):
decompose_model.train()
# compose_model.train()
criterion = nn.L1Loss()
chk = nn.MSELoss()
transform = transforms.Compose(
[transforms.RandomCrop(100),
transforms.ToTensor()])
trainset = datasets.ImageFolder(root=args.train_data, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset,
batch_size=args.batch_size,
shuffle=True,
num_workers=0)
if cuda:
model = model.cuda()
pre_model = pre_model.cuda()
# device_ids = [0]
# model = nn.DataParallel(model, device_ids=device_ids).cuda()
# criterion = criterion.cuda()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
scheduler = MultiStepLR(optimizer, milestones=[700, 1400, 2100],
gamma=0.2) # learning rates
for epoch in range(initial_epoch, n_epoch):
scheduler.step(epoch) # step to the learning rate in this epcoh
# xs = dg.datagenerator(data_dir=args.train_data)
# xs = xs.astype('float32') / 255.0
# xs = torch.from_numpy(xs.transpose((0, 3, 1, 2))) # tensor of the clean patches, NXCXHXW
#
# DDataset = DenoisingDataset(xs, sigma)
log('load trained model')
# params = model.state_dict()
# print(params.values())
# print(params.keys())
#
# for key, value in params.items():
# print(key) # parameter name
# print(params['dncnn.12.running_mean'])
# print(model.state_dict())
model.eval() # evaluation mode
# model.train()
if torch.cuda.is_available():
model = model.cuda()
if not os.path.exists(args.result_dir):
os.mkdir(args.result_dir)
for set_cur in args.set_names:
if not os.path.exists(os.path.join(args.result_dir, set_cur)):
os.mkdir(os.path.join(args.result_dir, set_cur))
psnrs = []
ssims = []
for im in os.listdir(os.path.join(args.set_dir, set_cur)):
if im.endswith(".jpg") or im.endswith(".bmp") or im.endswith(".png"):
x = np.array(imread(os.path.join(args.set_dir, set_cur, im)), dtype=np.float32)/255.0
low_model = DnCNN()
low_model.load_state_dict(torch.load(os.path.join(args.low_model_dir, args.low_model_name)))
initial_epoch = findLastCheckpoint(save_dir=save_dir) # load the last model in matconvnet style
if initial_epoch > 0:
print('resuming by loading epoch %03d' % initial_epoch)
# model.load_state_dict(torch.load(os.path.join(save_dir, 'model_%03d.pth' % initial_epoch)))
# model = torch.load(os.path.join(save_dir, 'model_%03d.pth' % initial_epoch))
model.train()
low_model.eval()
# criterion = nn.MSELoss(reduction = 'sum') # PyTorch 0.4.1
# criterion = sum_squared_error()
criterion = nn.MSELoss()
Edge_enhance = torch.FloatTensor(args.batch_size, 1, 40, 40)
if cuda:
model = model.cuda()
low_model = low_model.cuda()
# device_ids = [0]
# model = nn.DataParallel(model, device_ids=device_ids).cuda()
criterion = criterion.cuda()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
scheduler = MultiStepLR(optimizer, milestones=[30, 60, 90], gamma=0.2) # learning rates
for epoch in range(initial_epoch, n_epoch):
scheduler.step(epoch) # step to the learning rate in this epcoh
xs = dg.datagenerator(data_dir=args.train_data)
xs = xs.astype('float32') / 255.0
xs = torch.from_numpy(xs.transpose((0, 3, 1, 2))) # tensor of the clean patches, NXCXHXW
DDataset = DenoisingDataset(xs, sigma)
# params = model.state_dict()
# print(params.values())
# print(params.keys())
#
# for key, value in params.items():
# print(key) # parameter name
# print(params['dncnn.12.running_mean'])
# print(model.state_dict())
model_dncnn.eval() # evaluation mode
model_lowfreq.eval()
# model.train()
if torch.cuda.is_available():
model_dncnn = model_dncnn.cuda()
model_lowfreq = model_lowfreq.cuda()
if not os.path.exists(args.result_dir):
os.mkdir(args.result_dir)
for set_cur in args.set_names:
if not os.path.exists(os.path.join(args.result_dir, set_cur)):
os.mkdir(os.path.join(args.result_dir, set_cur))
psnrs = []
ssims = []
for im in os.listdir(os.path.join(args.set_dir, set_cur)):
if im.endswith(".jpg") or im.endswith(".bmp") or im.endswith(".png"):
# params = model.state_dict()
# print(params.values())
# print(params.keys())
#
# for key, value in params.items():
# print(key) # parameter name
# print(params['dncnn.12.running_mean'])
# print(model.state_dict())
high_model.eval() # evaluation mode
low_model.eval()
# model.train()
if torch.cuda.is_available():
high_model = high_model.cuda()
low_model = low_model.cuda()
if not os.path.exists(args.result_dir):
os.mkdir(args.result_dir)
for set_cur in args.set_names:
if not os.path.exists(os.path.join(args.result_dir, set_cur)):
os.mkdir(os.path.join(args.result_dir, set_cur))
psnrs = []
ssims = []
for im in os.listdir(os.path.join(args.set_dir, set_cur)):
if im.endswith(".jpg") or im.endswith(".bmp") or im.endswith(
".png"):
# params = model.state_dict()
# print(params.values())
# print(params.keys())
#
# for key, value in params.items():
# print(key) # parameter name
# print(params['dncnn.12.running_mean'])
# print(model.state_dict())
low_model.eval() # evaluation mode
res_model.eval()
model.eval()
if torch.cuda.is_available():
low_model = low_model.cuda()
res_model = res_model.cuda()
model = model.cuda()
# evaluation mode
if not os.path.exists(args.result_dir):
os.mkdir(args.result_dir)
for set_cur in args.set_names:
if not os.path.exists(os.path.join(args.result_dir, set_cur)):
os.mkdir(os.path.join(args.result_dir, set_cur))
psnrs = []
ssims = []
for im in os.listdir(os.path.join(args.set_dir, set_cur)):