python取绝对值fab_Python transforms.CenterCrop方法代碼示例
本文整理匯總了Python中torchvision.transforms.CenterCrop方法的典型用法代碼示例。如果您正苦於以下問題：Python transforms.CenterCrop方法的具體用法？Python transforms.CenterCrop怎麼用？Python transforms.CenterCrop使用的例子？那麼恭喜您, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進(jìn)一步了解該方法所在模塊torchvision.transforms的用法示例。
在下文中一共展示了transforms.CenterCrop方法的30個代碼示例，這些例子默認(rèn)根據(jù)受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點(diǎn)讚，您的評價將有助於我們的係統(tǒng)推薦出更棒的Python代碼示例。
示例1: _get_ds_val
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def _get_ds_val(self, images_spec, crop=False, truncate=False):
img_to_tensor_t = [images_loader.IndexImagesDataset.to_tensor_uint8_transform()]
if crop:
img_to_tensor_t.insert(0, transforms.CenterCrop(crop))
img_to_tensor_t = transforms.Compose(img_to_tensor_t)
fixed_first = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'fixedimg.jpg')
if not os.path.isfile(fixed_first):
print(f'INFO: No file found at {fixed_first}')
fixed_first = None
ds = images_loader.IndexImagesDataset(
images=images_loader.ImagesCached(
images_spec, self.config_dl.image_cache_pkl,
min_size=self.config_dl.val_glob_min_size),
to_tensor_transform=img_to_tensor_t,
fixed_first=fixed_first) # fix a first image to have consistency in tensor board
if truncate:
ds = pe.TruncatedDataset(ds, num_elemens=truncate)
return ds
開發(fā)者ID:fab-jul，項(xiàng)目名稱:L3C-PyTorch，代碼行數(shù):24，
示例2: get_lsun_dataloader
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def get_lsun_dataloader(path_to_data='../lsun', dataset='bedroom_train',
batch_size=64):
"""LSUN dataloader with (128, 128) sized images.
path_to_data : str
One of 'bedroom_val' or 'bedroom_train'
"""
# Compose transforms
transform = transforms.Compose([
transforms.Resize(128),
transforms.CenterCrop(128),
transforms.ToTensor()
])
# Get dataset
lsun_dset = datasets.LSUN(db_path=path_to_data, classes=[dataset],
transform=transform)
# Create dataloader
return DataLoader(lsun_dset, batch_size=batch_size, shuffle=True)
開發(fā)者ID:vandit15，項(xiàng)目名稱:Self-Supervised-Gans-Pytorch，代碼行數(shù):21，
示例3: save_distorted
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def save_distorted(method=gaussian_noise):
for severity in range(1, 6):
print(method.__name__, severity)
distorted_dataset = DistortImageFolder(
root="/share/data/vision-greg/ImageNet/clsloc/images/val",
method=method, severity=severity,
transform=trn.Compose([trn.Resize(256), trn.CenterCrop(224)]))
distorted_dataset_loader = torch.utils.data.DataLoader(
distorted_dataset, batch_size=100, shuffle=False, num_workers=4)
for _ in distorted_dataset_loader: continue
# /// End Further Setup ///
# /// Display Results ///
開發(fā)者ID:hendrycks，項(xiàng)目名稱:robustness，代碼行數(shù):19，
示例4: transform
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def transform(is_train=True, normalize=True):
"""
Returns a transform object
"""
filters = []
filters.append(Scale(256))
if is_train:
filters.append(RandomCrop(224))
else:
filters.append(CenterCrop(224))
if is_train:
filters.append(RandomHorizontalFlip())
filters.append(ToTensor())
if normalize:
filters.append(Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]))
return Compose(filters)
開發(fā)者ID:uwnlp，項(xiàng)目名稱:verb-attributes，代碼行數(shù):22，
示例5: __init__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(
self,
resize: int = ImagenetConstants.RESIZE,
crop_size: int = ImagenetConstants.CROP_SIZE,
mean: List[float] = ImagenetConstants.MEAN,
std: List[float] = ImagenetConstants.STD,
):
"""The constructor method of ImagenetNoAugmentTransform class.
Args:
resize: expected image size per dimension after resizing
crop_size: expected size for a dimension of central cropping
mean: a 3-tuple denoting the pixel RGB mean
std: a 3-tuple denoting the pixel RGB standard deviation
"""
self.transform = transforms.Compose(
[
transforms.Resize(resize),
transforms.CenterCrop(crop_size),
transforms.ToTensor(),
transforms.Normalize(mean=mean, std=std),
]
)
開發(fā)者ID:facebookresearch，項(xiàng)目名稱:ClassyVision，代碼行數(shù):26，
示例6: make
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def make(sz_resize = 256, sz_crop = 227, mean = [104, 117, 128],
std = [1, 1, 1], rgb_to_bgr = True, is_train = True,
intensity_scale = None):
return transforms.Compose([
RGBToBGR() if rgb_to_bgr else Identity(),
transforms.RandomResizedCrop(sz_crop) if is_train else Identity(),
transforms.Resize(sz_resize) if not is_train else Identity(),
transforms.CenterCrop(sz_crop) if not is_train else Identity(),
transforms.RandomHorizontalFlip() if is_train else Identity(),
transforms.ToTensor(),
ScaleIntensities(
*intensity_scale) if intensity_scale is not None else Identity(),
transforms.Normalize(
mean=mean,
std=std,
)
])
開發(fā)者ID:CompVis，項(xiàng)目名稱:metric-learning-divide-and-conquer，代碼行數(shù):19，
示例7: test_on_validation_set
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def test_on_validation_set(model, validation_set=None):
if validation_set is None:
validation_set = get_validation_set()
total_ssim = 0
total_psnr = 0
iters = len(validation_set.tuples)
crop = CenterCrop(config.CROP_SIZE)
for i, tup in enumerate(validation_set.tuples):
x1, gt, x2, = [crop(load_img(p)) for p in tup]
pred = interpolate(model, x1, x2)
gt = pil_to_tensor(gt)
pred = pil_to_tensor(pred)
total_ssim += ssim(pred, gt).item()
total_psnr += psnr(pred, gt).item()
print(f'#{i+1} done')
avg_ssim = total_ssim / iters
avg_psnr = total_psnr / iters
print(f'avg_ssim: {avg_ssim}, avg_psnr: {avg_psnr}')
開發(fā)者ID:martkartasev，項(xiàng)目名稱:sepconv，代碼行數(shù):26，
示例8: test_linear_interp
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def test_linear_interp(validation_set=None):
if validation_set is None:
validation_set = get_validation_set()
total_ssim = 0
total_psnr = 0
iters = len(validation_set.tuples)
crop = CenterCrop(config.CROP_SIZE)
for tup in validation_set.tuples:
x1, gt, x2, = [pil_to_tensor(crop(load_img(p))) for p in tup]
pred = torch.mean(torch.stack((x1, x2), dim=0), dim=0)
total_ssim += ssim(pred, gt).item()
total_psnr += psnr(pred, gt).item()
avg_ssim = total_ssim / iters
avg_psnr = total_psnr / iters
print(f'avg_ssim: {avg_ssim}, avg_psnr: {avg_psnr}')
開發(fā)者ID:martkartasev，項(xiàng)目名稱:sepconv，代碼行數(shù):23，
示例9: __init__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(self, patches, use_cache, augment_data):
super(PatchDataset, self).__init__()
self.patches = patches
self.crop = CenterCrop(config.CROP_SIZE)
if augment_data:
self.random_transforms = [RandomRotation((90, 90)), RandomVerticalFlip(1.0), RandomHorizontalFlip(1.0),
(lambda x: x)]
self.get_aug_transform = (lambda: random.sample(self.random_transforms, 1)[0])
else:
# Transform does nothing. Not sure if horrible or very elegant...
self.get_aug_transform = (lambda: (lambda x: x))
if use_cache:
self.load_patch = data_manager.load_cached_patch
else:
self.load_patch = data_manager.load_patch
print('Dataset ready with {} tuples.'.format(len(patches)))
開發(fā)者ID:martkartasev，項(xiàng)目名稱:sepconv，代碼行數(shù):21，
示例10: preprocess
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def preprocess(self):
if self.train:
return transforms.Compose([
transforms.RandomResizedCrop(self.image_size),
transforms.RandomHorizontalFlip(),
transforms.ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.2),
transforms.ToTensor(),
transforms.Normalize(self.mean, self.std),
])
else:
return transforms.Compose([
transforms.Resize((int(self.image_size / 0.875), int(self.image_size / 0.875))),
transforms.CenterCrop(self.image_size),
transforms.ToTensor(),
transforms.Normalize(self.mean, self.std),
])
開發(fā)者ID:wandering007，項(xiàng)目名稱:nasnet-pytorch，代碼行數(shù):18，
示例11: __getitem__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __getitem__(self, index):
# get downscaled, cropped and gt (if available) image
hr_image = Image.open(self.hr_files[index])
w, h = hr_image.size
cs = utils.calculate_valid_crop_size(min(w, h), self.upscale_factor)
if self.crop_size is not None:
cs = min(cs, self.crop_size)
cropped_image = TF.to_tensor(T.CenterCrop(cs // self.upscale_factor)(hr_image))
hr_image = T.CenterCrop(cs)(hr_image)
hr_image = TF.to_tensor(hr_image)
resized_image = utils.imresize(hr_image, 1.0 / self.upscale_factor, True)
if self.lr_files is None:
return resized_image, cropped_image, resized_image
else:
lr_image = Image.open(self.lr_files[index])
lr_image = TF.to_tensor(T.CenterCrop(cs // self.upscale_factor)(lr_image))
return resized_image, cropped_image, lr_image
開發(fā)者ID:ManuelFritsche，項(xiàng)目名稱:real-world-sr，代碼行數(shù):19，
示例12: __init__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(self, options):
transform_list = []
if options.image_size is not None:
transform_list.append(transforms.Resize((options.image_size, options.image_size)))
# transform_list.append(transforms.CenterCrop(options.image_size))
transform_list.append(transforms.ToTensor())
if options.image_colors == 1:
transform_list.append(transforms.Normalize(mean=[0.5], std=[0.5]))
elif options.image_colors == 3:
transform_list.append(transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]))
transform = transforms.Compose(transform_list)
dataset = ImagePairs(options.data_dir, split=options.split, transform=transform)
self.dataloader = DataLoader(
dataset,
batch_size=options.batch_size,
num_workers=options.loader_workers,
shuffle=True,
drop_last=True,
pin_memory=options.pin_memory
)
self.iterator = iter(self.dataloader)
開發(fā)者ID:unicredit，項(xiàng)目名稱:ganzo，代碼行數(shù):25，
示例13: __init__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(self, path, classes, stage='train'):
self.data = []
for i, c in enumerate(classes):
cls_path = osp.join(path, c)
images = os.listdir(cls_path)
for image in images:
self.data.append((osp.join(cls_path, image), i))
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
if stage == 'train':
self.transforms = transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize])
if stage == 'test':
self.transforms = transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize])
開發(fā)者ID:cyvius96，項(xiàng)目名稱:DGP，代碼行數(shù):23，
示例14: __init__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(self, opt):
self.image_path = opt.dataroot
self.is_train = opt.is_train
self.d_num = opt.n_attribute
print ('Start preprocessing dataset..!')
random.seed(1234)
self.preprocess()
print ('Finished preprocessing dataset..!')
if self.is_train:
trs = [transforms.Resize(opt.load_size, interpolation=Image.ANTIALIAS), transforms.RandomCrop(opt.fine_size)]
else:
trs = [transforms.Resize(opt.load_size, interpolation=Image.ANTIALIAS), transforms.CenterCrop(opt.fine_size)]
if opt.is_flip:
trs.append(transforms.RandomHorizontalFlip())
self.transform = transforms.Compose(trs)
self.norm = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
self.num_data = max(self.num)
開發(fā)者ID:Xiaoming-Yu，項(xiàng)目名稱:DMIT，代碼行數(shù):21，
示例15: __init__
?點(diǎn)讚 6
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(self, opt):
'''Initialize this dataset class.
We need to specific the path of the dataset and the domain label of each image.
'''
self.image_list = []
self.label_list = []
if opt.is_train:
trs = [transforms.Resize(opt.load_size, interpolation=Image.ANTIALIAS), transforms.RandomCrop(opt.fine_size)]
else:
trs = [transforms.Resize(opt.load_size, interpolation=Image.ANTIALIAS), transforms.CenterCrop(opt.fine_size)]
if opt.is_flip:
trs.append(transforms.RandomHorizontalFlip())
trs.append(transforms.ToTensor())
trs.append(transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)))
self.transform = transforms.Compose(trs)
self.num_data = len(self.image_list)
開發(fā)者ID:Xiaoming-Yu，項(xiàng)目名稱:DMIT，代碼行數(shù):18，
示例16: get_transform
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def get_transform(data_name, split_name, opt):
normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
t_list = []
if split_name == 'train':
t_list = [transforms.RandomSizedCrop(opt.crop_size),
transforms.RandomHorizontalFlip()]
elif split_name == 'val':
t_list = [transforms.Scale(256), transforms.CenterCrop(224)]
elif split_name == 'test':
t_list = [transforms.Scale(256), transforms.CenterCrop(224)]
t_end = [transforms.ToTensor(), normalizer]
transform = transforms.Compose(t_list + t_end)
return transform
開發(fā)者ID:ExplorerFreda，項(xiàng)目名稱:VSE-C，代碼行數(shù):17，
示例17: test_loader
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def test_loader(path, batch_size=16, num_workers=1, pin_memory=True):
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
return data.DataLoader(
datasets.ImageFolder(path,
transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])),
batch_size=batch_size,
shuffle=False,
num_workers=num_workers,
pin_memory=pin_memory)
開發(fā)者ID:jindongwang，項(xiàng)目名稱:transferlearning，代碼行數(shù):16，
示例18: get_test_dataset
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def get_test_dataset(self, testset):
to_tensor_transform = [IndexImagesDataset.to_tensor_uint8_transform()]
if self.flags.crop:
print('*** WARN: Cropping to {}'.format(self.flags.crop))
to_tensor_transform.insert(0, transforms.CenterCrop(self.flags.crop))
return IndexImagesDataset(
testset,
to_tensor_transform=transforms.Compose(to_tensor_transform))
開發(fā)者ID:fab-jul，項(xiàng)目名稱:L3C-PyTorch，代碼行數(shù):10，
示例19: check_dataset
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def check_dataset(opt):
normalize_transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.485, 0.456, 0.406),
(0.229, 0.224, 0.225))])
train_large_transform = transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip()])
val_large_transform = transforms.Compose([transforms.Resize(256),
transforms.CenterCrop(224)])
train_small_transform = transforms.Compose([transforms.Pad(4),
transforms.RandomCrop(32),
transforms.RandomHorizontalFlip()])
splits = check_split(opt)
if opt.dataset in ['cub200', 'indoor', 'stanford40', 'dog']:
train, val = 'train', 'test'
train_transform = transforms.Compose([train_large_transform, normalize_transform])
val_transform = transforms.Compose([val_large_transform, normalize_transform])
sets = [dset.ImageFolder(root=os.path.join(opt.dataroot, train), transform=train_transform),
dset.ImageFolder(root=os.path.join(opt.dataroot, train), transform=val_transform),
dset.ImageFolder(root=os.path.join(opt.dataroot, val), transform=val_transform)]
sets = [FolderSubset(dataset, *split) for dataset, split in zip(sets, splits)]
opt.num_classes = len(splits[0][0])
else:
raise Exception('Unknown dataset')
loaders = [torch.utils.data.DataLoader(dataset,
batch_size=opt.batchSize,
shuffle=True,
num_workers=0) for dataset in sets]
return loaders
開發(fā)者ID:alinlab，項(xiàng)目名稱:L2T-ww，代碼行數(shù):35，
示例20: get_dataset_loaders
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def get_dataset_loaders(model, dataset, workers):
target_size = (model["common"]["image_size"],) * 2
batch_size = model["common"]["batch_size"]
path = dataset["common"]["dataset"]
mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]
transform = JointCompose(
[
JointTransform(ConvertImageMode("RGB"), ConvertImageMode("P")),
JointTransform(Resize(target_size, Image.BILINEAR), Resize(target_size, Image.NEAREST)),
JointTransform(CenterCrop(target_size), CenterCrop(target_size)),
JointRandomHorizontalFlip(0.5),
JointRandomRotation(0.5, 90),
JointRandomRotation(0.5, 90),
JointRandomRotation(0.5, 90),
JointTransform(ImageToTensor(), MaskToTensor()),
JointTransform(Normalize(mean=mean, std=std), None),
]
)
train_dataset = SlippyMapTilesConcatenation(
[os.path.join(path, "training", "images")], os.path.join(path, "training", "labels"), transform
)
val_dataset = SlippyMapTilesConcatenation(
[os.path.join(path, "validation", "images")], os.path.join(path, "validation", "labels"), transform
)
assert len(train_dataset) > 0, "at least one tile in training dataset"
assert len(val_dataset) > 0, "at least one tile in validation dataset"
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, drop_last=True, num_workers=workers)
val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False, drop_last=True, num_workers=workers)
return train_loader, val_loader
開發(fā)者ID:mapbox，項(xiàng)目名稱:robosat，代碼行數(shù):38，
示例21: scale_crop
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def scale_crop(input_size, scale_size=None, normalize=__imagenet_stats):
t_list = [
transforms.CenterCrop(input_size),
transforms.ToTensor(),
transforms.Normalize(**normalize),
]
if scale_size != input_size:
t_list = [transforms.Resize(scale_size)] + t_list
return transforms.Compose(t_list)
開發(fā)者ID:Randl，項(xiàng)目名稱:MobileNetV3-pytorch，代碼行數(shù):12，
示例22: main
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def main():
args = parser.parse_args()
model = ghostnet(num_classes=args.num_classes, width=args.width, dropout=args.dropout)
model.load_state_dict(torch.load('./models/state_dict_93.98.pth'))
if args.num_gpu > 1:
model = torch.nn.DataParallel(model, device_ids=list(range(args.num_gpu))).cuda()
elif args.num_gpu < 1:
model = model
else:
model = model.cuda()
print('GhostNet created.')
valdir = os.path.join(args.data, 'val')
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
loader = torch.utils.data.DataLoader(
datasets.ImageFolder(valdir, transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])),
batch_size=args.batch_size, shuffle=False,
num_workers=args.workers, pin_memory=True)
model.eval()
validate_loss_fn = nn.CrossEntropyLoss().cuda()
eval_metrics = validate(model, loader, validate_loss_fn, args)
print(eval_metrics)
開發(fā)者ID:huawei-noah，項(xiàng)目名稱:ghostnet，代碼行數(shù):34，
示例23: Imagenet_eval
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def Imagenet_eval():
return transforms.Compose([
transforms.Scale(256), # 重新改變大小為size=(w, h) 或 (size, size)
transforms.CenterCrop(224), # 將給定的數(shù)據(jù)進(jìn)行中心切割，得到給定的size。
transforms.ToTensor(), # 轉(zhuǎn)化為tensor數(shù)據(jù)
Normalize_Imagenet(),
])
開發(fā)者ID:wyf2017，項(xiàng)目名稱:DSMnet，代碼行數(shù):9，
示例24: data_loader
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def data_loader(root, batch_size=256, workers=1, pin_memory=True):
traindir = os.path.join(root, 'ILSVRC2012_img_train')
valdir = os.path.join(root, 'ILSVRC2012_img_val')
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_dataset = datasets.ImageFolder(
traindir,
transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize
])
)
val_dataset = datasets.ImageFolder(
valdir,
transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize
])
)
train_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=workers,
pin_memory=pin_memory,
sampler=None
)
val_loader = torch.utils.data.DataLoader(
val_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=workers,
pin_memory=pin_memory
)
return train_loader, val_loader
開發(fā)者ID:jiweibo，項(xiàng)目名稱:ImageNet，代碼行數(shù):43，
示例25: __init__
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def __init__(self, args):
super(BigCIFAR10, self).__init__()
data_root = os.path.join(args.data, "cifar10")
use_cuda = torch.cuda.is_available()
input_size = 128
# Data loading code
kwargs = {"num_workers": args.workers, "pin_memory": True} if use_cuda else {}
train_dataset = torchvision.datasets.CIFAR10(
root=data_root,
train=True,
download=True,
transform=transforms.Compose([
transforms.RandomResizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
)
self.train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=args.batch_size, shuffle=True, **kwargs
)
test_dataset = torchvision.datasets.CIFAR10(
root=data_root,
train=False,
download=True,
transform=transforms.Compose([
transforms.Resize(input_size),
transforms.CenterCrop(input_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
)
self.val_loader = torch.utils.data.DataLoader(
test_dataset, batch_size=args.batch_size, shuffle=False, **kwargs
)
開發(fā)者ID:allenai，項(xiàng)目名稱:hidden-networks，代碼行數(shù):43，
示例26: show_performance
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def show_performance(distortion_name):
errs = []
for severity in range(1, 6):
distorted_dataset = dset.ImageFolder(
root='/share/data/vision-greg/DistortedImageNet/JPEG/' + distortion_name + '/' + str(severity),
transform=trn.Compose([trn.CenterCrop(224), trn.ToTensor(), trn.Normalize(mean, std)]))
distorted_dataset_loader = torch.utils.data.DataLoader(
distorted_dataset, batch_size=args.test_bs, shuffle=False, num_workers=args.prefetch, pin_memory=True)
correct = 0
for batch_idx, (data, target) in enumerate(distorted_dataset_loader):
data = V(data.cuda(), volatile=True)
output = net(data)
pred = output.data.max(1)[1]
correct += pred.eq(target.cuda()).sum()
errs.append(1 - 1.*correct / len(distorted_dataset))
print('\n=Average', tuple(errs))
return np.mean(errs)
# /// End Further Setup ///
# /// Display Results ///
開發(fā)者ID:hendrycks，項(xiàng)目名稱:robustness，代碼行數(shù):32，
示例27: resize_crop_image
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def resize_crop_image(image, new_image_dims):
image_dims = [image.shape[1], image.shape[0]]
if image_dims == new_image_dims:
return image
resize_width = int(math.floor(new_image_dims[1] * float(image_dims[0]) / float(image_dims[1])))
image = transforms.Resize([new_image_dims[1], resize_width], interpolation=Image.NEAREST)(Image.fromarray(image))
image = transforms.CenterCrop([new_image_dims[1], new_image_dims[0]])(image)
image = np.array(image)
return image
開發(fā)者ID:daveredrum，項(xiàng)目名稱:Pointnet2.ScanNet，代碼行數(shù):12，
示例28: resize_crop_image
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def resize_crop_image(image, new_image_dims):
image_dims = [image.shape[1], image.shape[0]]
if image_dims != new_image_dims:
resize_width = int(math.floor(new_image_dims[1] * float(image_dims[0]) / float(image_dims[1])))
image = transforms.Resize([new_image_dims[1], resize_width], interpolation=Image.NEAREST)(Image.fromarray(image))
image = transforms.CenterCrop([new_image_dims[1], new_image_dims[0]])(image)
return np.array(image)
開發(fā)者ID:daveredrum，項(xiàng)目名稱:Pointnet2.ScanNet，代碼行數(shù):10，
示例29: _resize_crop_image
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def _resize_crop_image(self, image, new_image_dims):
image_dims = [image.shape[1], image.shape[0]]
if image_dims != new_image_dims:
resize_width = int(math.floor(new_image_dims[1] * float(image_dims[0]) / float(image_dims[1])))
image = transforms.Resize([new_image_dims[1], resize_width], interpolation=Image.NEAREST)(Image.fromarray(image))
image = transforms.CenterCrop([new_image_dims[1], new_image_dims[0]])(image)
return np.array(image)
開發(fā)者ID:daveredrum，項(xiàng)目名稱:Pointnet2.ScanNet，代碼行數(shù):10，
示例30: display_transform
?點(diǎn)讚 5
?
# 需要導(dǎo)入模塊: from torchvision import transforms [as 別名]
# 或者: from torchvision.transforms import CenterCrop [as 別名]
def display_transform():
return Compose([
ToPILImage(),
Resize(400),
CenterCrop(400),
ToTensor()
])
開發(fā)者ID:amanchadha，項(xiàng)目名稱:iSeeBetter，代碼行數(shù):9，
注：本文中的torchvision.transforms.CenterCrop方法示例整理自Github/MSDocs等源碼及文檔管理平臺，相關(guān)代碼片段篩選自各路編程大神貢獻(xiàn)的開源項(xiàng)目，源碼版權(quán)歸原作者所有，傳播和使用請參考對應(yīng)項(xiàng)目的License；未經(jīng)允許，請勿轉(zhuǎn)載。
總結(jié)
以上是生活随笔為你收集整理的python取绝对值fab_Python transforms.CenterCrop方法代碼示例的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： 线性时间选择算法
- 下一篇： PS教程第十一课:会打开 会关闭我回了