print('{} training images'.format(len(train_HRimages)))
print('{} testing images'.format(len(test_HRimages)))
HR_loader = torch.utils.data.DataLoader(
train_HRimages, shuffle=False, batch_size=batch_size) #, pin_memory=cuda)
LR_loader = torch.utils.data.DataLoader(
train_LRimages, shuffle=False, batch_size=batch_size) #, pin_memory=cuda)
lossfunc = torch.nn.SmoothL1Loss()
#lossfunc = torch.nn.MSELoss()
TV_weight = 0 #1.e-4
SL_weight = 0 #1.e-4
num_epochs = 50
tvloss = lf.TVLoss(TV_weight)
styleloss = lf.StyleLoss(SL_weight)
def train(model):
model.train()
if cuda:
model = model.cuda()
epoch_loss = []
epoch_psnr = []
all_loss = []
optimizer_name = torch.optim.Adam
#lr = 0.001
w_decay = 0 #1.0e-4
optimizer = optimizer_name(model.parameters(), lr=lr, weight_decay=w_decay)
gamma = 0.97
train_HRimages = HRimages[0:Ntrain]
test_HRimages = HRimages[Ntrain:Ntrain + Ntest]
train_LRimages = LRimages[0:Ntrain]
test_LRimages = LRimages[Ntrain:Ntrain + Ntest]
print('{} training images'.format(len(train_HRimages)))
print('{} testing images'.format(len(test_HRimages)))
HR_loader = torch.utils.data.DataLoader(
train_HRimages, shuffle=False, batch_size=batch_size) #, pin_memory=cuda)
LR_loader = torch.utils.data.DataLoader(
train_LRimages, shuffle=False, batch_size=batch_size) #, pin_memory=cuda)
lossfunc = torch.nn.SmoothL1Loss()
#lossfunc = torch.nn.MSELoss()
TV_weight = 5.e-5
styleloss = lf.StyleLoss(1.0e-14)
num_epochs = 100
def train(model):
model.train()
if cuda:
model = model.cuda()
epoch_loss = []
all_loss = []
optimizer_name = torch.optim.Adam
lr = 0.001
w_decay = 1.0e-5
optimizer = optimizer_name(model.parameters(), lr=lr, weight_decay=w_decay)