def main():
# instantiate model and initialize weights
model = AutoNet(input_nc=args.input_nc, ndf=6, nonlinear='relu')
networks.print_network(model)
if args.cuda:
model.cuda()
print('using pretrained model')
checkpoint = torch.load(project_root + args.log_dir + '/checkpoint_60.pth')
model.load_state_dict(checkpoint['state_dict'])
args.lr = args.lr * 0.001
itr_start = 1
nature = test_nature(val_loader, model)
print(nature)
threshold = max(2, nature * 2)
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda()
optimizer = create_optimizer(model, args.lr)
new_samples = []
pn_num = []
nature_error_itr_global = []
for itr in np.arange(itr_start, 5):
args.dataroot = dst_dir
tmp = construct_negative_samples(model, new_samples, itr)
pn_num.append(tmp)
train_loader = myDataset.DataLoaderHalf(
myDataset.MyDataset(
args,
transforms.Compose([
transforms.Resize((256, 256), Image.BICUBIC),
transforms.ToTensor(), normalize
])),
batch_size=args.batch_size,
shuffle=True,
half_constraint=True,
sampler_type='RandomBalancedSampler',
**kwargs)
print('The number of train data:{}'.format(len(train_loader.dataset)))
args.epochs = 15 # after the new negative samples construct, the learning rate is constant, and epoch = 15
train_multi(train_loader, optimizer, model, criterion, val_loader, itr,
nature_error_itr_global)
print(pn_num)
model_selection(nature_error_itr_global, threshold)
data_root = '/home/wzquan/publicData/NIvsCG/RRVData/RRVNature-Corona'
project_root = '/home/wzquan/Project/NIvsCG/RRVNature-project/RRVNature-Corona/SrcCode'
LOG_DIR = project_root + args.log_dir
if not os.path.exists(LOG_DIR):
os.makedirs(LOG_DIR)
normalize = transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
args.dataroot = os.path.join(data_root, 'train')
train_loader = myDataset.DataLoaderHalf(myDataset.MyDataset(
args,
transforms.Compose([
transforms.RandomCrop(233),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), normalize
])),
batch_size=args.batch_size,
shuffle=True,
half_constraint=True,
sampler_type='RandomBalancedSampler',
**kwargs)
print('The number of train data:{}'.format(len(train_loader.dataset)))
def main():
# instantiate model and initialize weights
model = ENet()
networks.print_network(model)
networks.init_weights(model, init_type='normal')
model.init_convFilter(trainable=srm_trainable)
def main():
# instantiate model and initialize weights
model = ENet()
networks.print_network(model)
networks.init_weights(model, init_type='normal')
model.init_convFilter(trainable=srm_trainable)
if args.cuda:
model.cuda()
print('using pretrained model')
checkpoint = torch.load(project_root + args.log_dir +
'/checkpoint_300.pth')
model.load_state_dict(checkpoint['state_dict'])
args.lr = args.lr * 0.001
threshold = THRESHOLD_MAX
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda()
L1_criterion = nn.L1Loss(reduction='sum').cuda()
if not srm_trainable:
params = []
for name, param in model.named_parameters():
if name.find('convFilter1') == -1:
params += [param]
optimizer = create_optimizer(params, args.lr)
else:
optimizer = create_optimizer(model.parameters(), args.lr)
nature_error_itr_global = []
for itr in np.arange(1, 11):
args.dataroot = dst_dir
nature_error_itr_local = []
# adding negative samples into the original training dataset
construct_negative_samples(itr)
train_loader = myDataset.DataLoaderHalf(
myDataset.MyDataset(
args,
transforms.Compose([
transforms.RandomCrop(233),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(), normalize
])),
batch_size=args.batch_size,
shuffle=True,
half_constraint=True,
sampler_type='RandomBalancedSampler',
**kwargs)
print('The number of train data:{}'.format(len(train_loader.dataset)))
args.epochs = 15
train_multi(train_loader, optimizer, model, criterion, L1_criterion, val_loader, itr, \
nature_error_itr_local, nature_error_itr_global)
# start from itr = 1
if len(nature_error_itr_local) > 0:
adv_model_num, adv_model_idx = adv_model_selection(
nature_error_itr_local, threshold, itr)
if adv_model_num < 1:
break
print(nature_error_itr_global)
print(len(nature_error_itr_global) / (args.epochs - args.epochs // 2))
final_model_selection(nature_error_itr_global, threshold)
rmtree(dst_dir)
copytree(src_dir, dst_dir)
img_trans = transforms.Compose([
transforms.Resize((256, 256), Image.BICUBIC),
transforms.ToTensor(), normalize
])
args.dataroot = src_dir #here, use src_dir just for extracting the original info of training data
image_loader = myDataset.DataLoaderHalf(myDataset.MyDataset(
args,
transforms.Compose([
transforms.Resize((256, 256), Image.BICUBIC),
transforms.ToTensor(), normalize
])),
batch_size=args.batch_size,
shuffle=False,
half_constraint=False,
drop_last=False,
**kwargs)
print('The number of train data:{}'.format(len(image_loader.dataset)))
image_name = image_loader.dataset.images_txt
all_image_num = len(image_name)
print(all_image_num)
# store the name of colorized images
image_pn_add_flag = {}
for item in image_name[:all_image_num // 2]:
image_pn_add_flag[item] = True