# argument parser
parser = argparse.ArgumentParser(description='Joint Adversarial Defense')
parser.add_argument('--lr', default=0.01, type=float, help='learning rate')
parser.add_argument('--steps', default=10, type=int, help='adv. steps')
parser.add_argument('--eps', required=True, type=float, help='max norm')
parser.add_argument('--dataset', required=True, type=str, help='dataset name')
parser.add_argument('--network', required=True, type=str, help='network name')
parser.add_argument('--data_root', required=True, type=str, help='path to dataset')
parser.add_argument('--epoch', default=60, type=int, help='epoch number')
parser.add_argument('--attack', default='pgd', type=str, help='attack type')
parser.add_argument('--save_dir', default='./experiment', type=str, help='save directory')
args = parser.parse_args()
# loading dataset, network, and attack
trainloader, testloader = dataset_loader(args)
net = network_loader(args, mean=args.mean, std=args.std).cuda()
attack = attack_loader(args, net)
# Adam Optimizer with KL divergence, and Scheduling Learning rate
optimizer = torch.optim.SGD(net.parameters(), lr=args.lr, momentum=0.9, weight_decay=1e-2)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=20, gamma=0.2)
# Setting checkpoint date time
date_time = datetime.today().strftime("%m%d%H%M")
# checkpoint_name
checkpoint_name = 'LP_'+args.network+'_'+args.dataset+'_'+date_time+'.pth'
# argument print
argument_print(args, checkpoint_name)
parser.add_argument('--eps', default=0.03, type=float, help='max norm')
parser.add_argument('--dataset', default='cifar10', type=str, help='dataset name')
parser.add_argument('--network', default='vgg', type=str, help='network name')
parser.add_argument('--data_root', default='./datasets', type=str, help='path to dataset')
parser.add_argument('--save_dir', default='./experiment', type=str, help='save directory')
parser.add_argument('--datetime', default=10, type=str, help='checkpoint datetime')
parser.add_argument('--baseline', default='LP', type=str, help='baseline')
# 0: plain, 1: AT, 2: RFM, 3: mAT, 4: LP, 5: trade
args = parser.parse_args()
checkpoint_name = args.baseline+'_'+args.network+'_'+args.dataset+'_'+args.datetime+'.pth'
# loading dataset, network, attack
_, testloader = dataset_loader(args)
if "OEM" in args.baseline:
args.isinitialize=True
net = OEM_network_loader(args, mean=args.mean, std=args.std).cuda()
net.load_state_dict(torch.load(os.path.join(args.save_dir, checkpoint_name))['model_state_dict'])
net.eval()
else:
if "Plain" in args.baseline:
args.attack="Plain"
else:
args.attack="AT"
net = network_loader(args, mean=args.mean, std=args.std).cuda()
net.load_state_dict(torch.load(os.path.join(args.save_dir, checkpoint_name))['model_state_dict'])
print('Total number of Model Parameters is: {}M\n'.format(sum(p.numel() for p in net.parameters() if p.requires_grad)/1000000))