Python transforms.RandomResizedCrop方法代码示例

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def load_data(root_path, dir, batch_size, phase):
    transform_dict = {
        'src': transforms.Compose(
        [transforms.RandomResizedCrop(224),
         transforms.RandomHorizontalFlip(),
         transforms.ToTensor(),
         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                              std=[0.229, 0.224, 0.225]),
         ]),
        'tar': transforms.Compose(
        [transforms.Resize(224),
         transforms.ToTensor(),
         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                              std=[0.229, 0.224, 0.225]),
         ])}
    data = datasets.ImageFolder(root=root_path + dir, transform=transform_dict[phase])
    data_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    return data_loader 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def load_train(root_path, dir, batch_size, phase):
    transform_dict = {
        'src': transforms.Compose(
            [transforms.RandomResizedCrop(224),
             transforms.RandomHorizontalFlip(),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ]),
        'tar': transforms.Compose(
            [transforms.Resize(224),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ])}
    data = datasets.ImageFolder(root=root_path + dir, transform=transform_dict[phase])
    train_size = int(0.8 * len(data))
    test_size = len(data) - train_size
    data_train, data_val = torch.utils.data.random_split(data, [train_size, test_size])
    train_loader = torch.utils.data.DataLoader(data_train, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    val_loader = torch.utils.data.DataLoader(data_val, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    return train_loader, val_loader 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def __init__(
        self,
        crop_size: int = ImagenetConstants.CROP_SIZE,
        mean: List[float] = ImagenetConstants.MEAN,
        std: List[float] = ImagenetConstants.STD,
    ):
        """The constructor method of ImagenetAugmentTransform class.

        Args:
            crop_size: expected output size per dimension after random 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.RandomResizedCrop(crop_size),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
                transforms.Normalize(mean=mean, std=std),
            ]
        ) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
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,
        )
    ]) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def get_jig_train_transformers(args):
    size = args.img_transform.random_resize_crop.size
    scale = args.img_transform.random_resize_crop.scale
    img_tr = [transforms.RandomResizedCrop((int(size[0]), int(size[1])), (scale[0], scale[1]))]
    if args.img_transform.random_horiz_flip > 0.0:
        img_tr.append(transforms.RandomHorizontalFlip(args.img_transform.random_horiz_flip))
    if args.img_transform.jitter > 0.0:
        img_tr.append(transforms.ColorJitter(
            brightness=args.img_transform.jitter, contrast=args.img_transform.jitter,
            saturation=args.jitter, hue=min(0.5, args.jitter)))

    tile_tr = []
    if args.jig_transform.tile_random_grayscale:
        tile_tr.append(transforms.RandomGrayscale(args.jig_transform.tile_random_grayscale))
    mean = args.normalize.mean
    std = args.normalize.std
    tile_tr = tile_tr + [transforms.ToTensor(), transforms.Normalize(mean=mean, std=std)]

    return transforms.Compose(img_tr), transforms.Compose(tile_tr) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def get_rot_train_transformers(args):
    size = args.img_transform.random_resize_crop.size
    scale = args.img_transform.random_resize_crop.scale
    img_tr = [transforms.RandomResizedCrop((int(size[0]), int(size[1])), (scale[0], scale[1]))]
    if args.img_transform.random_horiz_flip > 0.0:
        img_tr.append(transforms.RandomHorizontalFlip(args.img_transform.random_horiz_flip))
    if args.img_transform.jitter > 0.0:
        img_tr.append(transforms.ColorJitter(
            brightness=args.img_transform.jitter, contrast=args.img_transform.jitter,
            saturation=args.jitter, hue=min(0.5, args.jitter)))

    mean = args.normalize.mean
    std = args.normalize.std
    img_tr += [transforms.ToTensor(), transforms.Normalize(mean=mean, std=std)]

    return transforms.Compose(img_tr) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
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),
            ]) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
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]) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def get_img_tensor(img_path, use_cuda, get_size=False):
    img = Image.open(img_path)
    original_w, original_h = img.size

    img_size = (224, 224)  # crop image to (224, 224)
    img.thumbnail(img_size, Image.ANTIALIAS)
    img = img.convert('RGB')
    normalize = transforms.Normalize(
        mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    transform = transforms.Compose([
        transforms.RandomResizedCrop(img_size[0]),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        normalize,
    ])
    img_tensor = transform(img)
    img_tensor = torch.unsqueeze(img_tensor, 0)
    if use_cuda:
        img_tensor = img_tensor.cuda()
    if get_size:
        return img_tensor, original_w, original_w
    else:
        return img_tensor 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def get_pytorch_train_loader(data_path, batch_size, workers=5, _worker_init_fn=None, input_size=224):
    traindir = os.path.join(data_path, 'train')
    train_dataset = datasets.ImageFolder(
            traindir,
            transforms.Compose([
                transforms.RandomResizedCrop(input_size),
                transforms.RandomHorizontalFlip(),
                ]))

    if torch.distributed.is_initialized():
        train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
    else:
        train_sampler = None

    train_loader = torch.utils.data.DataLoader(
            train_dataset, batch_size=batch_size, shuffle=(train_sampler is None),
            num_workers=workers, worker_init_fn=_worker_init_fn, pin_memory=True, sampler=train_sampler, collate_fn=fast_collate)

    return PrefetchedWrapper(train_loader), len(train_loader) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def get_loaders(traindir, valdir, sz, bs, fp16=True, val_bs=None, workers=8, rect_val=False, min_scale=0.08, distributed=False):
    val_bs = val_bs or bs
    train_tfms = [
            transforms.RandomResizedCrop(sz, scale=(min_scale, 1.0)),
            transforms.RandomHorizontalFlip()
    ]
    train_dataset = datasets.ImageFolder(traindir, transforms.Compose(train_tfms))
    train_sampler = (DistributedSampler(train_dataset, num_replicas=env_world_size(), rank=env_rank()) if distributed else None)

    train_loader = torch.utils.data.DataLoader(
        train_dataset, batch_size=bs, shuffle=(train_sampler is None),
        num_workers=workers, pin_memory=True, collate_fn=fast_collate, 
        sampler=train_sampler)

    val_dataset, val_sampler = create_validation_set(valdir, val_bs, sz, rect_val=rect_val, distributed=distributed)
    val_loader = torch.utils.data.DataLoader(
        val_dataset,
        num_workers=workers, pin_memory=True, collate_fn=fast_collate, 
        batch_sampler=val_sampler)

    train_loader = BatchTransformDataLoader(train_loader, fp16=fp16)
    val_loader = BatchTransformDataLoader(val_loader, fp16=fp16)

    return train_loader, val_loader, train_sampler, val_sampler 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def make_transform(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,
        )
    ]) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def imgnet_transform(is_training=True):
  if is_training:
    transform_list = transforms.Compose([transforms.RandomResizedCrop(224),
                                         transforms.RandomHorizontalFlip(),
                                         transforms.ColorJitter(brightness=0.5,
                                                                contrast=0.5,
                                                                saturation=0.3),
                                         transforms.ToTensor(),
                                         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                                              std=[0.229, 0.224, 0.225])])
  else:
    transform_list = transforms.Compose([transforms.Resize(256),
                                         transforms.CenterCrop(224),
                                         transforms.ToTensor(),
                                         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                                              std=[0.229, 0.224, 0.225])])
  return transform_list 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def __init__(self, data_dir, image_size, is_train=True, **kwargs):
		self.image_size = image_size
		self.image_paths = []
		self.image_labels = []
		self.classes = sorted(os.listdir(data_dir))
		for idx, cls_ in enumerate(self.classes):
			self.image_paths += glob.glob(os.path.join(data_dir, cls_, '*.*'))
			self.image_labels += [idx] * len(glob.glob(os.path.join(data_dir, cls_, '*.*')))
		self.indexes = list(range(len(self.image_paths)))
		if is_train:
			random.shuffle(self.indexes)
			self.transform = transforms.Compose([transforms.RandomResizedCrop(image_size),
												 transforms.RandomHorizontalFlip(),
												 transforms.ColorJitter(brightness=1, contrast=1, saturation=0.5, hue=0.5),
												 transforms.ToTensor(),
												 transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
		else:
			self.transform = transforms.Compose([transforms.ToTensor(),
												 transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])]) 

# 需要导入模块: from torchvision import transforms [as 别名]
# 或者: from torchvision.transforms import RandomResizedCrop [as 别名]
def build_train_transform(self, distort_color, resize_scale):
        print('Color jitter: %s' % distort_color)
        if distort_color == 'strong':
            color_transform = transforms.ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.1)
        elif distort_color == 'normal':
            color_transform = transforms.ColorJitter(brightness=32. / 255., saturation=0.5)
        else:
            color_transform = None
        if color_transform is None:
            train_transforms = transforms.Compose([
                transforms.RandomResizedCrop(self.image_size, scale=(resize_scale, 1.0)),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
                self.normalize,
            ])
        else:
            train_transforms = transforms.Compose([
                transforms.RandomResizedCrop(self.image_size, scale=(resize_scale, 1.0)),
                transforms.RandomHorizontalFlip(),
                color_transform,
                transforms.ToTensor(),
                self.normalize,
            ])
        return train_transforms