def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.485, 0.456, 0.406)
std = (0.229, 0.224, 0.225)
normalize = transforms.Normalize(mean=mean, std=std)
# [0.485, 0.456, 0.406], [0.229, 0.224, 0.225] for Dogs vs Cats
# TODO write train_dataset for cvd --check utils
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=256, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([
transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)
], p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize])
train_dir= opt.data_dir
train_files= os.listdir(train_dir)
cat_files = [tf for tf in train_files if 'cat' in tf]
dog_files = [tf for tf in train_files if 'dog' in tf]
cats = CatDogDataset(cat_files, train_dir, transform = TwoCropTransform(train_transform))
dogs = CatDogDataset(train_files, train_dir, transform = TwoCropTransform(train_transform))
train_dataset = ConcatDataset([cats, dogs])
train_sampler = None
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=opt.batch_size, shuffle=(train_sampler is None),
num_workers=opt.num_workers, pin_memory=True, sampler=train_sampler)
return train_loader
def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
elif opt.dataset == 'SD198-20':
mean = (0.485, 0.456, 0.406)
std = (0.229, 0.224, 0.225)
elif opt.dataset == 'path':
mean = eval(opt.mean)
std = eval(opt.std)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
# ['RandomResizedCrop', 'ImageJitter', 'RandomRotation', 'RandomHorizontalFlip', 'ToTensor', 'Normalize']
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=opt.size, scale=(0.8, 1.2)),
transforms.RandomRotation(degrees=30),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
if opt.dataset == 'cifar10':
train_dataset = datasets.CIFAR10(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = datasets.CIFAR100(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'SD198-20':
## opt.data_folder = '/home/slidm/SkinLesionData/SD-198-20/base.json'
train_dataset = SimpleDataset(
data_file=opt.data_folder,
transform=TwoCropTransform(train_transform))
elif opt.dataset == 'path':
train_dataset = datasets.ImageFolder(
root=opt.data_folder, transform=TwoCropTransform(train_transform))
else:
raise ValueError(opt.dataset)
train_sampler = None
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=(train_sampler is None),
num_workers=opt.num_workers,
pin_memory=True,
sampler=train_sampler)
return train_loader
def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
elif opt.dataset == 'path':
mean = eval(opt.mean)
std = eval(opt.std)
elif opt.dataset == 'cardio':
mean = (0.485, 0.456, 0.406)
std = (0.229, 0.224, 0.225)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
#transforms.RandomResizedCrop(size=opt.size, scale=(0.2, 1.)),
transforms.Resize(size=opt.size),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
if opt.dataset == 'cifar10':
train_dataset = datasets.CIFAR10(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = datasets.CIFAR100(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'path':
train_dataset = datasets.ImageFolder(
root=opt.data_folder, transform=TwoCropTransform(train_transform))
elif opt.dataset == 'cardio':
train_dataset = get_cardio_smclr(opt.data_folder)
print('cardio dataset')
else:
raise ValueError(opt.dataset)
train_sampler = None
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=(train_sampler is None),
num_workers=opt.num_workers,
pin_memory=True,
sampler=train_sampler)
return train_loader
def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
elif opt.dataset == 'shapenet':
mean = (0.1575, 0.1497, 0.1429)
std = (0.2985, 0.2891, 0.2827)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=32, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
if opt.dataset == 'cifar10':
train_dataset = datasets.CIFAR10(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = datasets.CIFAR100(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'shapenet':
train_dataset = ImageFolder(root=os.path.join(opt.data_folder,
'train'),
transform=train_transform,
views=opt.views,
drop_objects_ratio=opt.drop_objects_ratio)
else:
raise ValueError(opt.dataset)
train_sampler = None
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=(train_sampler is None),
num_workers=opt.num_workers,
pin_memory=True,
sampler=train_sampler)
return train_loader
def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
elif opt.dataset == 'path':
mean = eval(opt.mean)
std = eval(opt.std)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=32, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(), normalize
])
if opt.dataset == 'cifar10':
train_dataset = CIFAR10Instance(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = CIFAR100Instance(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'path':
train_dataset = datasets.ImageFolder(
root=opt.data_folder, transform=TwoCropTransform(train_transform))
else:
raise ValueError(opt.dataset)
n_data = len(train_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=opt.batch_size,
num_workers=opt.num_workers,
pin_memory=True)
return train_loader, n_data
def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=32, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
if opt.dataset == 'cifar10':
train_dataset = datasets.CIFAR10(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = datasets.CIFAR100(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
else:
raise ValueError(opt.dataset)
from util import InfiniteSampler
train_sampler = InfiniteSampler(train_dataset, shuffle=True)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=(train_sampler is None),
num_workers=opt.num_workers,
pin_memory=True,
sampler=train_sampler)
return iter(train_loader)
def set_dataset(opt):
# construct dataset
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
elif opt.dataset == 'path':
mean = eval(opt.mean)
std = eval(opt.mean)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=opt.size, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
if opt.dataset == 'cifar10':
train_dataset = datasets.CIFAR10(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = datasets.CIFAR100(
root=opt.data_folder,
transform=TwoCropTransform(train_transform),
download=True)
elif opt.dataset == 'path':
train_dataset = datasets.ImageFolder(
root=opt.data_folder, transform=TwoCropTransform(train_transform))
else:
raise ValueError(opt.dataset)
return train_dataset
def set_loader(opt, train=True):
if opt.dataset == 'cifar10':
dataset = datasets.CIFAR10(root=opt.data_folder,
train=train,
transform=TwoCropTransform(transforms.ToTensor()),
download=True)
elif opt.dataset == 'cifar100':
dataset = datasets.CIFAR100(root=opt.data_folder,
train=train,
transform=TwoCropTransform(transforms.ToTensor()),
download=True)
elif opt.dataset == 'shapenet':
dataset = ImageFolder(root=opt.data_folder, transform=transforms.ToTensor())
else:
raise ValueError(opt.dataset)
data_loader = torch.utils.data.DataLoader(
dataset, batch_size=opt.batch_size, shuffle=False,
num_workers=opt.num_workers, pin_memory=True)
return data_loader
def set_loader(opt):
# construct data loader
# if opt.dataset == 'cifar10':
# mean = (0.4914, 0.4822, 0.4465)
# std = (0.2023, 0.1994, 0.2010)
# elif opt.dataset == 'cifar100':
# mean = (0.5071, 0.4867, 0.4408)
# std = (0.2675, 0.2565, 0.2761)
# # else:
# # raise ValueError('dataset not supported: {}'.format(opt.dataset))
mean = [0.485, 0.456, 0.406] # imagenet mean
std = [0.229, 0.224, 0.225] # imagenet std
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=192, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)],
p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
train_transform = TwoCropTransform(train_transform)
#
# if opt.dataset == 'cifar10':
# train_dataset = datasets.CIFAR10(root=opt.data_folder,
# transform=TwoCropTransform(train_transform),
# download=True)
# elif opt.dataset == 'cifar100':
# train_dataset = datasets.CIFAR100(root=opt.data_folder,
# transform=TwoCropTransform(train_transform),
# download=True)
if opt.dataset == 'ali':
train_dataset = Ali(train_transform)
else:
raise ValueError(opt.dataset)
train_sampler = None
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=opt.batch_size,
shuffle=(train_sampler is None),
num_workers=opt.num_workers,
pin_memory=True,
sampler=train_sampler)
return train_loader
def set_loader(opt):
# construct data loader
# mean and std of imagenet dataset
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225]
operations = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.RandomResizedCrop(size=224, scale=(0.2, 1)),
transforms.ToTensor(),
transforms.Normalize(mean=mean, std=std)
])
transformed_dataset = PascalVOCDataset(
csv_file='objects.csv', transform=TwoCropTransform(operations))
train_loader = torch.utils.data.DataLoader(transformed_dataset,
batch_size=4,
shuffle=True,
num_workers=2)
return train_loader
def set_loader(opt):
# construct data loader
if opt.dataset == 'cifar10':
mean = (0.4914, 0.4822, 0.4465)
std = (0.2023, 0.1994, 0.2010)
elif opt.dataset == 'cifar100':
mean = (0.5071, 0.4867, 0.4408)
std = (0.2675, 0.2565, 0.2761)
elif opt.dataset == 'path' or opt.dataset == 'cmnist' or opt.dataset == 'celeba':
mean = eval(opt.mean)
std = eval(opt.std)
else:
raise ValueError('dataset not supported: {}'.format(opt.dataset))
normalize = transforms.Normalize(mean=mean, std=std)
train_transform = transforms.Compose([
transforms.RandomResizedCrop(size=opt.size, scale=(0.2, 1.)),
transforms.RandomHorizontalFlip(),
transforms.RandomApply([
transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)
], p=0.8),
transforms.RandomGrayscale(p=0.2),
transforms.ToTensor(),
normalize,
])
if opt.dataset == 'cifar10':
train_dataset = datasets.CIFAR10(root=opt.data_folder,
transform=TwoCropTransform(
train_transform),
download=True)
elif opt.dataset == 'cifar100':
train_dataset = datasets.CIFAR100(root=opt.data_folder,
transform=TwoCropTransform(
train_transform),
download=True)
elif opt.dataset == 'path':
train_dataset = datasets.ImageFolder(root=opt.data_folder,
transform=TwoCropTransform(train_transform))
elif opt.dataset == 'cmnist':
train_dataset = CMNIST(
opt.data_folder,
train=True,
variance=0.02,
colorize='fg',
# class_subset=[4, 9],
same_distribution=True,
transform=TwoCropTransform(train_transform))
elif opt.dataset == 'celeba':
train_dataset = CelebA(
root=opt.data_folder,
split='train',
class_subset=['Arched_Eyebrows'],
download=False,
transform=TwoCropTransform(train_transform)
)
else:
raise ValueError(opt.dataset)
train_sampler = None
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=opt.batch_size, shuffle=(
train_sampler is None),
num_workers=opt.num_workers, pin_memory=True, sampler=train_sampler)
return train_loader