def __init__(self, args):
self.args = args
self.path = Path()
# Saver
self.saver = Saver(args, self.path.event) # Define Saver
# Define Dataloader
kwargs = {'num_workers': args.workers, 'pin_memory': True}
self.train_loader, self.val_loader = make_data_loader(args, **kwargs)
# Define network
self.model = mymodels.resnet152(pretrained=True)
# self.model = mymodels.resnet50(pretrained=True)
# if args.pretrained:
# self.model = mymodels.resnet101(pretrained=True)
# else:
# self.model = mymodels.resnet101()
# Binary classification
num_ftrs = self.model.fc.in_features
self.model.fc = nn.Linear(num_ftrs, 2) # len(class_names) = 2
del self.model.maxpool
# Resuming checkpoint
if args.resume is not None: # path to resuming file
if not os.path.isfile(args.resume):
raise RuntimeError("=> no checkpoint found at '{}'".format(
args.resume))
state_dict = torch.load(args.resume)
print('=>load pre-trained model from')
print(args.resume)
best_acc = state_dict['best_acc'] # accuracy
print('=>model top 1 accuracy: %0.3f' % best_acc)
self.model.load_state_dict(state_dict['state_dict'])
# Using cuda
if args.cuda:
self.model = self.model.cuda()
# define loss function (criterion) and optimizer
self.criterion = nn.CrossEntropyLoss().cuda() #交叉熵损失函数
self.optimizer = torch.optim.SGD(self.model.parameters(),
args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
# Define lr scheduler
self.scheduler = lr_scheduler.StepLR(self.optimizer,
step_size=10,
gamma=0.1)
# Record
self.best_acc = 0.0
def __init__(self, args):
super().__init__()
path = Path()
self._base_dir = path.detect
self.all_patch_list = []
self.image_ids = args.image_ids
for image_id in self.image_ids:
image = cv2.imread(os.path.join(self._base_dir, image_id))
image_pad = self.pad_image(image)
patch_list = self.image_to_patch(image_pad)
self.all_patch_list += patch_list
assert len(self.all_patch_list) == len(self.image_ids) * 16 * 12
def __init__(self, cfg, args, **kwargs):
self.cfg = cfg
self.distributed = dist.is_initialized()
# dataloader
dsval = CityscapesSegmentation(args,
root=Path().db_root_dir(args.dataset),
split='reval')
sampler = None
if self.distributed:
sampler = torch.utils.data.distributed.DistributedSampler(dsval)
self.dl = DataLoader(dsval,
batch_size=cfg.eval_batchsize,
sampler=sampler,
shuffle=False,
num_workers=cfg.eval_n_workers,
drop_last=False)
def __init__(self):
super().__init__()
with open('test_list.txt') as f:
test_list = f.readlines()
self.image_ids = [i.split(' ')[0] for i in test_list]
path = Path()
self._base_dir = path.harmo
self.all_patch_list = []
for image_id in self.image_ids:
image = cv2.imread(os.path.join(self._base_dir, image_id))
#print(os.path.join(self._base_dir, image_id))
#assert os.path.exists(os.path.join(self._base_dir, image_id))
image_pad = self.pad_image(image)
patch_list = self.image_to_patch(image_pad)
self.all_patch_list += patch_list
assert len(self.all_patch_list) == len(self.image_ids) * 16 * 12
def __init__(self, args):
self.args = args
path = Path()
# image to patch
n_patch = int(16*12) #192
eval_per = int(n_patch/args.batch_size) #
# path
self.event_dir = path.event
self.model_dir = os.path.join(self.event_dir, 'run', 'checkpoint.pth.tar')
test_list = args.test_list
with open(test_list) as f:
self.lines = f.readlines()
# range
self.ids = [i.split(' ')[0] for i in self.lines]
self.mins = [float(i.split(' ')[1]) for i in self.lines]
self.maxs = [float(i.split(' ')[2]) for i in self.lines]
# Define Dataloader
kwargs = {'num_workers': args.workers, 'pin_memory': True}
self.test_loader = make_data_loader(args, **kwargs)
# Define network
self.model = mymodels.resnet152()
# Binary classification
num_ftrs = self.model.fc.in_features
self.model.fc = nn.Linear(num_ftrs, 2) # len(class_names) = 2
del self.model.maxpool
# Resuming checkpoint
state_dict = torch.load(self.model_dir)
print('=>load pre-trained model')
best_acc = state_dict['best_acc'] # accuracy
print('=>model accuracy: %0.3f' % best_acc)
self.model.load_state_dict(state_dict['state_dict'])
# Using cuda
if args.cuda:
self.model = self.model.cuda()
def __init__(self, split='train'):
super().__init__()
assert split in ['train', 'val']
self.split = split
path = Path()
self._base_dir = path.patch
self.split_fn = os.path.join(self._base_dir, self.split + '.txt')
self.im_ids = []
self.im_lbs = [] # label:0/1
with open(self.split_fn, 'r') as f:
lines = f.read().splitlines()
for line in lines:
im_id, im_lb = line.split(' ')
self.im_ids.append(im_id)
self.im_lbs.append(im_lb)
assert len(self.im_ids) == len(self.im_lbs)