inferno.io.box package

Submodules

inferno.io.box.camvid module

class inferno.io.box.camvid.CamVid(root, split='train', image_transform=None, label_transform=None, joint_transform=None, download=False, loader=<function default_loader>)

Bases: torch.utils.data.dataset.Dataset

CLASSES = ['Sky', 'Building', 'Column-Pole', 'Road', 'Sidewalk', 'Tree', 'Sign-Symbol', 'Fence', 'Car', 'Pedestrain', 'Bicyclist', 'Void']

CLASS_WEIGHTS = [0.58872014284134, 0.51052379608154, 2.6966278553009, 0.45021694898605, 1.1785038709641, 0.77028578519821, 2.4782588481903, 2.5273461341858, 1.0122526884079, 3.2375309467316, 4.1312313079834, 0]

MEAN = [0.41189489566336, 0.4251328133025, 0.4326707089857]

SPLIT_NAME_MAPPING = {'test': 'test', 'testing': 'test', 'train': 'train', 'training': 'train', 'val': 'val', 'validate': 'val', 'validation': 'val'}

STD = [0.27413549931506, 0.28506257482912, 0.28284674400252]

download()

inferno.io.box.camvid.get_camvid_loaders(root_directory, image_shape=(360, 480), labels_as_onehot=False, train_batch_size=1, validate_batch_size=1, test_batch_size=1, num_workers=2)

inferno.io.box.camvid.label_to_long_tensor(pic)

inferno.io.box.camvid.label_to_pil_image(label)

inferno.io.box.camvid.make_dataset(dir)

inferno.io.box.cifar module

inferno.io.box.cifar.get_cifar100_loaders(root_directory, train_batch_size=128, test_batch_size=100, download=False, augment=False, validation_dataset_size=None)

inferno.io.box.cifar.get_cifar10_loaders(root_directory, train_batch_size=128, test_batch_size=256, download=False, augment=False, validation_dataset_size=None)

inferno.io.box.cityscapes module

class inferno.io.box.cityscapes.Cityscapes(root_folder, split='train', read_from_zip_archive=True, image_transform=None, label_transform=None, joint_transform=None)

Bases: torch.utils.data.dataset.Dataset

BLACKLIST = ['leftImg8bit/train_extra/troisdorf/troisdorf_000000_000073_leftImg8bit.png']

CLASSES = {-1: 'license plate', 0: 'unlabeled', 1: 'ego vehicle', 2: 'rectification border', 3: 'out of roi', 4: 'static', 5: 'dynamic', 6: 'ground', 7: 'road', 8: 'sidewalk', 9: 'parking', 10: 'rail track', 11: 'building', 12: 'wall', 13: 'fence', 14: 'guard rail', 15: 'bridge', 16: 'tunnel', 17: 'pole', 18: 'polegroup', 19: 'traffic light', 20: 'traffic sign', 21: 'vegetation', 22: 'terrain', 23: 'sky', 24: 'person', 25: 'rider', 26: 'car', 27: 'truck', 28: 'bus', 29: 'caravan', 30: 'trailer', 31: 'train', 32: 'motorcycle', 33: 'bicycle'}

MEAN = [0.28689554, 0.32513303, 0.28389177]

SPLIT_NAME_MAPPING = {'test': 'test', 'testing': 'test', 'train': 'train', 'train_extra': 'train_extra', 'training': 'train', 'training_extra': 'train_extra', 'val': 'val', 'validate': 'val', 'validation': 'val'}

STD = [0.18696375, 0.19017339, 0.18720214]

download()

get_image_and_label_roots()

inferno.io.box.cityscapes.extract_image(path, image_path)

inferno.io.box.cityscapes.get_cityscapes_loaders(root_directory, image_shape=(1024, 2048), labels_as_onehot=False, include_coarse_dataset=False, read_from_zip_archive=True, train_batch_size=1, validate_batch_size=1, num_workers=2)

inferno.io.box.cityscapes.get_filelist(path)

inferno.io.box.cityscapes.get_matching_labelimage_file(f, groundtruth)

inferno.io.box.cityscapes.make_dataset(path, split)

inferno.io.box.cityscapes.make_transforms(image_shape, labels_as_onehot)

Module contents

Things that work out of the box. ;)