Python torchvision.transforms.RandomGrayscale() Examples

The following are 6 code examples of torchvision.transforms.RandomGrayscale(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module torchvision.transforms , or try the search function .
Example #1
Source File: data_loader.py    From self-supervised-da with MIT License 6 votes vote down vote up 
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)
Example #2
Source File: datasets.py    From amdim-public with MIT License 6 votes vote down vote up 
def __init__(self):
        # flipping image along vertical axis
        self.flip_lr = transforms.RandomHorizontalFlip(p=0.5)
        # image augmentation functions
        normalize = transforms.Normalize(mean=[x / 255.0 for x in [125.3, 123.0, 113.9]],
                                         std=[x / 255.0 for x in [63.0, 62.1, 66.7]])
        col_jitter = transforms.RandomApply([
            transforms.ColorJitter(0.4, 0.4, 0.4, 0.2)], p=0.8)
        img_jitter = transforms.RandomApply([
            RandomTranslateWithReflect(4)], p=0.8)
        rnd_gray = transforms.RandomGrayscale(p=0.25)
        # main transform for self-supervised training
        self.train_transform = transforms.Compose([
            img_jitter,
            col_jitter,
            rnd_gray,
            transforms.ToTensor(),
            normalize
        ])
        # transform for testing
        self.test_transform = transforms.Compose([
            transforms.ToTensor(),
            normalize
        ])
Example #3
Source File: datasets.py    From amdim-public with MIT License 6 votes vote down vote up 
def __init__(self):
        # image augmentation functions
        self.flip_lr = transforms.RandomHorizontalFlip(p=0.5)
        rand_crop = \
            transforms.RandomResizedCrop(128, scale=(0.3, 1.0), ratio=(0.7, 1.4),
                                         interpolation=INTERP)
        col_jitter = transforms.RandomApply([
            transforms.ColorJitter(0.4, 0.4, 0.4, 0.1)], p=0.8)
        rnd_gray = transforms.RandomGrayscale(p=0.25)
        post_transform = transforms.Compose([
            transforms.ToTensor(),
            transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                 std=[0.229, 0.224, 0.225])
        ])
        self.test_transform = transforms.Compose([
            transforms.Resize(146, interpolation=INTERP),
            transforms.CenterCrop(128),
            post_transform
        ])
        self.train_transform = transforms.Compose([
            rand_crop,
            col_jitter,
            rnd_gray,
            post_transform
        ])
Example #4
Source File: datasets.py    From amdim-public with MIT License 5 votes vote down vote up 
def __init__(self):
        # flipping image along vertical axis
        self.flip_lr = transforms.RandomHorizontalFlip(p=0.5)
        normalize = transforms.Normalize(mean=(0.43, 0.42, 0.39), std=(0.27, 0.26, 0.27))
        # image augmentation functions
        col_jitter = transforms.RandomApply([
            transforms.ColorJitter(0.4, 0.4, 0.4, 0.2)], p=0.8)
        rnd_gray = transforms.RandomGrayscale(p=0.25)
        rand_crop = \
            transforms.RandomResizedCrop(64, scale=(0.3, 1.0), ratio=(0.7, 1.4),
                                         interpolation=INTERP)

        self.test_transform = transforms.Compose([
            transforms.Resize(70, interpolation=INTERP),
            transforms.CenterCrop(64),
            transforms.ToTensor(),
            normalize
        ])

        self.train_transform = transforms.Compose([
            rand_crop,
            col_jitter,
            rnd_gray,
            transforms.ToTensor(),
            normalize
        ])
Example #5
Source File: utils.py    From instance-segmentation-pytorch with GNU General Public License v3.0 5 votes vote down vote up 
def image_random_grayscaler(p=0.5):
        return transforms.RandomGrayscale(p=p)
Example #6
Source File: data_helper.py    From JigenDG with GNU Affero General Public License v3.0 5 votes vote down vote up 
def get_train_transformers(args):
    img_tr = [transforms.RandomResizedCrop((int(args.image_size), int(args.image_size)), (args.min_scale, args.max_scale))]
    if args.random_horiz_flip > 0.0:
        img_tr.append(transforms.RandomHorizontalFlip(args.random_horiz_flip))
    if args.jitter > 0.0:
        img_tr.append(transforms.ColorJitter(brightness=args.jitter, contrast=args.jitter, saturation=args.jitter, hue=min(0.5, args.jitter)))

    tile_tr = []
    if args.tile_random_grayscale:
        tile_tr.append(transforms.RandomGrayscale(args.tile_random_grayscale))
    tile_tr = tile_tr + [transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])]

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