os.mkdir(opt.dataset)
if not os.path.exists(os.path.join("{}/train".format(opt.dataset))):
os.mkdir(os.path.join("{}/train".format(opt.dataset)))
os.mkdir(os.path.join("{}/train/A".format(opt.dataset)))
os.mkdir(os.path.join("{}/train/B".format(opt.dataset)))
if not os.path.exists(os.path.join("{}/test".format(opt.dataset))):
os.mkdir(os.path.join("{}/test".format(opt.dataset)))
os.mkdir(os.path.join("{}/test/A".format(opt.dataset)))
os.mkdir(os.path.join("{}/test/B".format(opt.dataset)))
train_set = get_training_set(opt.datasetPath)
train_data_loader = DataLoader(dataset=train_set,
num_workers=0,
batch_size=1,
shuffle=True)
test_set = get_test_set(opt.datasetPath)
testing_data_loader = DataLoader(dataset=test_set,
num_workers=0,
batch_size=1,
shuffle=False)
criterionMSE = nn.MSELoss()
criterionMSE = criterionMSE.cuda()
i = 0
'''
for x in range(10):
for batch in train_data_loader:
input, target, input_masked = Variable(batch[0], volatile=True), Variable(batch[1], volatile=True), Variable(
batch[2], volatile=True)
print(opt)
if opt.cuda and not torch.cuda.is_available():
raise Exception("No GPU found, please run without --cuda")
cudnn.benchmark = True
torch.manual_seed(opt.seed)
if opt.cuda:
torch.cuda.manual_seed(opt.seed)
print('===> Loading datasets')
train_set = get_training_set(opt.datasetPath, opt.image_size, opt.masked_size,
opt.resize_ratio)
test_set = get_test_set(opt.datasetPath, opt.image_size, opt.masked_size,
opt.resize_ratio)
training_data_loader = DataLoader(dataset=train_set,
num_workers=opt.threads,
batch_size=opt.batchSize,
shuffle=True,
pin_memory=True)
testing_data_loader = DataLoader(dataset=test_set,
num_workers=opt.threads,
batch_size=opt.testBatchSize,
shuffle=False)
print('===> Building model')
resume_epoch = 0
if opt.resume_epoch < 0:
net_g_model_out_path = "checkpoint/{}_{}/netG_model_latest.pth".format(
