#'/media/unknown/Data/PLP/fast_adv/defenses/weights/best/2AT_cifar10_ep_13_val_acc0.8770.pth'
#'/media/unknown/Data/PLP/fast_adv/defenses/weights/best/2_1Attention_cifar10_ep_33_val_acc0.8890.pth'
#'/media/unknown/Data/PLP/fast_adv/defenses/weights/best/2_2AT_cifar10_ep_29_val_acc0.8870.pth'
model_dict=model.state_dict()
save_model = torch.load(model_file,map_location=lambda storage, loc: storage)
state_dict = {k:v for k,v in save_model.items() if k in model_dict.keys()}
#print(state_dict.keys()) # dict_keys(['w', 'conv1.weight', 'conv1.bias', 'conv2.weight', 'conv2.bias'])
model_dict.update(state_dict)
model.load_state_dict(model_dict)
'''
#model_dict = torch.load('/media/unknown/Data/PLP/fast_adv/defenses/weights/best/2_2AT_cifar10_ep_29_val_acc0.8870.pth')
#model.load_state_dict(model_dict)
if torch.cuda.device_count() > 1:
model = torch.nn.DataParallel(model)
optimizer = SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
if args.adv == 0:
scheduler = lr_scheduler.StepLR(optimizer,
step_size=args.lr_step,
gamma=args.lr_decay)
else:
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=[60, 120, 160],
gamma=0.2)
attacker = DDN(steps=args.steps, device=DEVICE)
max_loss = torch.log(torch.tensor(10.)).item() # for callback
# print(len(pretext_model.keys()))
# print(len(model_dict.keys()))
# print(len(state_dict.keys()))
# model_dict.update(state_dict)
# model.load_state_dict(model_dict)
# model_dict = torch.load(weight_wsdan3)
# model.load_state_dict(model_dict)
# print("load wight:",model_file)
if torch.cuda.device_count() > 1:
model = torch.nn.DataParallel(model)
feature_center = torch.zeros(10,
args.num_attentions * m.num_features).to(DEVICE)
optimizer = torch.optim.SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
if args.adv == 0:
scheduler = lr_scheduler.StepLR(optimizer,
step_size=args.lr_step,
gamma=args.lr_decay)
else:
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=[60, 120, 160],
gamma=0.2)
attacker = DDN(steps=args.steps, device=DEVICE)
shuffle=False,
num_workers=args.workers,
pin_memory=True)
m = wide_resnet(num_classes=10, depth=28, widen_factor=10, dropRate=args.drop)
model = NormalizedModel(model=m, mean=image_mean, std=image_std).to(
DEVICE) # keep images in the [0, 1] range
weight_AT = './weights/best/2AT_cifar10_ep_13_val_acc0.8770.pth'
# model_file='/home/frankfeng/projects/researchData/AI_security/code/PLP/fast_adv/defenses/weights/cifar10_base/cifar10_valacc0.8339999794960022.pth'
model_dict = torch.load(weight_AT)
model.load_state_dict(model_dict)
if torch.cuda.device_count() > 1:
model = torch.nn.DataParallel(model)
optimizer = SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
if args.adv == 0:
scheduler = lr_scheduler.StepLR(optimizer,
step_size=args.lr_step,
gamma=args.lr_decay)
else:
scheduler = lr_scheduler.MultiStepLR(optimizer,
milestones=[60, 120, 160],
gamma=0.2)
attacker = DDN(steps=args.steps, device=DEVICE)
max_loss = torch.log(torch.tensor(10.)).item() # for callback
val_set = data.Subset(CIFAR10(args.data, train=True, transform=test_transform, download=True),
list(range(45000, 50000)))
test_set = CIFAR10(args.data, train=False, transform=test_transform, download=True)
train_loader = data.DataLoader(train_set, batch_size=args.batch_size, shuffle=True, num_workers=args.workers,
drop_last=True, pin_memory=True)
val_loader = data.DataLoader(val_set, batch_size=100, shuffle=True, num_workers=args.workers, pin_memory=True)
test_loader = data.DataLoader(test_set, batch_size=100, shuffle=True, num_workers=args.workers, pin_memory=True)
# m = wide_resnet(num_classes=10, depth=28, widen_factor=10, dropRate=args.drop)
m = resnet18(pretrained=False)
model = NormalizedModel(model=m, mean=image_mean, std=image_std).to(DEVICE) # keep images in the [0, 1] range
# if torch.cuda.device_count() > 1:
# model = torch.nn.DataParallel(model)
optimizer = SGD(model.parameters(), lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
if args.adv == 0:
scheduler = lr_scheduler.StepLR(optimizer, step_size=args.lr_step, gamma=args.lr_decay)
else:
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=[60, 120, 160], gamma=0.2)
attacker = DDN(steps=args.steps, device=DEVICE)
max_loss = torch.log(torch.tensor(10.)).item() # for callback
best_acc = 0
best_epoch = 0
for epoch in range(args.epochs):
scheduler.step()
cudnn.benchmark = True
model.train()