Skip to content

GitLab

Commit cbc25585 authored by limm's avatar limm
Browse files

add mmpretrain/ part

parent 1baf0566
Pipeline #2801 canceled with stages
Show whitespace changes
Inline Side-by-side
Showing with 4268 additions and 0 deletions
mmpretrain/datasets/categories.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
# Pre-defined categories names of various datasets.
VOC2007_CATEGORIES = ('aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus',
'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
'horse', 'motorbike', 'person', 'pottedplant', 'sheep',
'sofa', 'train', 'tvmonitor')
CUB_CATEGORIES = (
'Black_footed_Albatross', 'Laysan_Albatross', 'Sooty_Albatross',
'Groove_billed_Ani', 'Crested_Auklet', 'Least_Auklet', 'Parakeet_Auklet',
'Rhinoceros_Auklet', 'Brewer_Blackbird', 'Red_winged_Blackbird',
'Rusty_Blackbird', 'Yellow_headed_Blackbird', 'Bobolink', 'Indigo_Bunting',
'Lazuli_Bunting', 'Painted_Bunting', 'Cardinal', 'Spotted_Catbird',
'Gray_Catbird', 'Yellow_breasted_Chat', 'Eastern_Towhee',
'Chuck_will_Widow', 'Brandt_Cormorant', 'Red_faced_Cormorant',
'Pelagic_Cormorant', 'Bronzed_Cowbird', 'Shiny_Cowbird', 'Brown_Creeper',
'American_Crow', 'Fish_Crow', 'Black_billed_Cuckoo', 'Mangrove_Cuckoo',
'Yellow_billed_Cuckoo', 'Gray_crowned_Rosy_Finch', 'Purple_Finch',
'Northern_Flicker', 'Acadian_Flycatcher', 'Great_Crested_Flycatcher',
'Least_Flycatcher', 'Olive_sided_Flycatcher', 'Scissor_tailed_Flycatcher',
'Vermilion_Flycatcher', 'Yellow_bellied_Flycatcher', 'Frigatebird',
'Northern_Fulmar', 'Gadwall', 'American_Goldfinch', 'European_Goldfinch',
'Boat_tailed_Grackle', 'Eared_Grebe', 'Horned_Grebe', 'Pied_billed_Grebe',
'Western_Grebe', 'Blue_Grosbeak', 'Evening_Grosbeak', 'Pine_Grosbeak',
'Rose_breasted_Grosbeak', 'Pigeon_Guillemot', 'California_Gull',
'Glaucous_winged_Gull', 'Heermann_Gull', 'Herring_Gull', 'Ivory_Gull',
'Ring_billed_Gull', 'Slaty_backed_Gull', 'Western_Gull',
'Anna_Hummingbird', 'Ruby_throated_Hummingbird', 'Rufous_Hummingbird',
'Green_Violetear', 'Long_tailed_Jaeger', 'Pomarine_Jaeger', 'Blue_Jay',
'Florida_Jay', 'Green_Jay', 'Dark_eyed_Junco', 'Tropical_Kingbird',
'Gray_Kingbird', 'Belted_Kingfisher', 'Green_Kingfisher',
'Pied_Kingfisher', 'Ringed_Kingfisher', 'White_breasted_Kingfisher',
'Red_legged_Kittiwake', 'Horned_Lark', 'Pacific_Loon', 'Mallard',
'Western_Meadowlark', 'Hooded_Merganser', 'Red_breasted_Merganser',
'Mockingbird', 'Nighthawk', 'Clark_Nutcracker', 'White_breasted_Nuthatch',
'Baltimore_Oriole', 'Hooded_Oriole', 'Orchard_Oriole', 'Scott_Oriole',
'Ovenbird', 'Brown_Pelican', 'White_Pelican', 'Western_Wood_Pewee',
'Sayornis', 'American_Pipit', 'Whip_poor_Will', 'Horned_Puffin',
'Common_Raven', 'White_necked_Raven', 'American_Redstart', 'Geococcyx',
'Loggerhead_Shrike', 'Great_Grey_Shrike', 'Baird_Sparrow',
'Black_throated_Sparrow', 'Brewer_Sparrow', 'Chipping_Sparrow',
'Clay_colored_Sparrow', 'House_Sparrow', 'Field_Sparrow', 'Fox_Sparrow',
'Grasshopper_Sparrow', 'Harris_Sparrow', 'Henslow_Sparrow',
'Le_Conte_Sparrow', 'Lincoln_Sparrow', 'Nelson_Sharp_tailed_Sparrow',
'Savannah_Sparrow', 'Seaside_Sparrow', 'Song_Sparrow', 'Tree_Sparrow',
'Vesper_Sparrow', 'White_crowned_Sparrow', 'White_throated_Sparrow',
'Cape_Glossy_Starling', 'Bank_Swallow', 'Barn_Swallow', 'Cliff_Swallow',
'Tree_Swallow', 'Scarlet_Tanager', 'Summer_Tanager', 'Artic_Tern',
'Black_Tern', 'Caspian_Tern', 'Common_Tern', 'Elegant_Tern',
'Forsters_Tern', 'Least_Tern', 'Green_tailed_Towhee', 'Brown_Thrasher',
'Sage_Thrasher', 'Black_capped_Vireo', 'Blue_headed_Vireo',
'Philadelphia_Vireo', 'Red_eyed_Vireo', 'Warbling_Vireo',
'White_eyed_Vireo', 'Yellow_throated_Vireo', 'Bay_breasted_Warbler',
'Black_and_white_Warbler', 'Black_throated_Blue_Warbler',
'Blue_winged_Warbler', 'Canada_Warbler', 'Cape_May_Warbler',
'Cerulean_Warbler', 'Chestnut_sided_Warbler', 'Golden_winged_Warbler',
'Hooded_Warbler', 'Kentucky_Warbler', 'Magnolia_Warbler',
'Mourning_Warbler', 'Myrtle_Warbler', 'Nashville_Warbler',
'Orange_crowned_Warbler', 'Palm_Warbler', 'Pine_Warbler',
'Prairie_Warbler', 'Prothonotary_Warbler', 'Swainson_Warbler',
'Tennessee_Warbler', 'Wilson_Warbler', 'Worm_eating_Warbler',
'Yellow_Warbler', 'Northern_Waterthrush', 'Louisiana_Waterthrush',
'Bohemian_Waxwing', 'Cedar_Waxwing', 'American_Three_toed_Woodpecker',
'Pileated_Woodpecker', 'Red_bellied_Woodpecker', 'Red_cockaded_Woodpecker',
'Red_headed_Woodpecker', 'Downy_Woodpecker', 'Bewick_Wren', 'Cactus_Wren',
'Carolina_Wren', 'House_Wren', 'Marsh_Wren', 'Rock_Wren', 'Winter_Wren',
'Common_Yellowthroat')
IMAGENET_CATEGORIES = (
'tench, Tinca tinca',
'goldfish, Carassius auratus',
'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias', # noqa: E501
'tiger shark, Galeocerdo cuvieri',
'hammerhead, hammerhead shark',
'electric ray, crampfish, numbfish, torpedo',
'stingray',
'cock',
'hen',
'ostrich, Struthio camelus',
'brambling, Fringilla montifringilla',
'goldfinch, Carduelis carduelis',
'house finch, linnet, Carpodacus mexicanus',
'junco, snowbird',
'indigo bunting, indigo finch, indigo bird, Passerina cyanea',
'robin, American robin, Turdus migratorius',
'bulbul',
'jay',
'magpie',
'chickadee',
'water ouzel, dipper',
'kite',
'bald eagle, American eagle, Haliaeetus leucocephalus',
'vulture',
'great grey owl, great gray owl, Strix nebulosa',
'European fire salamander, Salamandra salamandra',
'common newt, Triturus vulgaris',
'eft',
'spotted salamander, Ambystoma maculatum',
'axolotl, mud puppy, Ambystoma mexicanum',
'bullfrog, Rana catesbeiana',
'tree frog, tree-frog',
'tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui',
'loggerhead, loggerhead turtle, Caretta caretta',
'leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea', # noqa: E501
'mud turtle',
'terrapin',
'box turtle, box tortoise',
'banded gecko',
'common iguana, iguana, Iguana iguana',
'American chameleon, anole, Anolis carolinensis',
'whiptail, whiptail lizard',
'agama',
'frilled lizard, Chlamydosaurus kingi',
'alligator lizard',
'Gila monster, Heloderma suspectum',
'green lizard, Lacerta viridis',
'African chameleon, Chamaeleo chamaeleon',
'Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis', # noqa: E501
'African crocodile, Nile crocodile, Crocodylus niloticus',
'American alligator, Alligator mississipiensis',
'triceratops',
'thunder snake, worm snake, Carphophis amoenus',
'ringneck snake, ring-necked snake, ring snake',
'hognose snake, puff adder, sand viper',
'green snake, grass snake',
'king snake, kingsnake',
'garter snake, grass snake',
'water snake',
'vine snake',
'night snake, Hypsiglena torquata',
'boa constrictor, Constrictor constrictor',
'rock python, rock snake, Python sebae',
'Indian cobra, Naja naja',
'green mamba',
'sea snake',
'horned viper, cerastes, sand viper, horned asp, Cerastes cornutus',
'diamondback, diamondback rattlesnake, Crotalus adamanteus',
'sidewinder, horned rattlesnake, Crotalus cerastes',
'trilobite',
'harvestman, daddy longlegs, Phalangium opilio',
'scorpion',
'black and gold garden spider, Argiope aurantia',
'barn spider, Araneus cavaticus',
'garden spider, Aranea diademata',
'black widow, Latrodectus mactans',
'tarantula',
'wolf spider, hunting spider',
'tick',
'centipede',
'black grouse',
'ptarmigan',
'ruffed grouse, partridge, Bonasa umbellus',
'prairie chicken, prairie grouse, prairie fowl',
'peacock',
'quail',
'partridge',
'African grey, African gray, Psittacus erithacus',
'macaw',
'sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita',
'lorikeet',
'coucal',
'bee eater',
'hornbill',
'hummingbird',
'jacamar',
'toucan',
'drake',
'red-breasted merganser, Mergus serrator',
'goose',
'black swan, Cygnus atratus',
'tusker',
'echidna, spiny anteater, anteater',
'platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus', # noqa: E501
'wallaby, brush kangaroo',
'koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus', # noqa: E501
'wombat',
'jellyfish',
'sea anemone, anemone',
'brain coral',
'flatworm, platyhelminth',
'nematode, nematode worm, roundworm',
'conch',
'snail',
'slug',
'sea slug, nudibranch',
'chiton, coat-of-mail shell, sea cradle, polyplacophore',
'chambered nautilus, pearly nautilus, nautilus',
'Dungeness crab, Cancer magister',
'rock crab, Cancer irroratus',
'fiddler crab',
'king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica', # noqa: E501
'American lobster, Northern lobster, Maine lobster, Homarus americanus', # noqa: E501
'spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish', # noqa: E501
'crayfish, crawfish, crawdad, crawdaddy',
'hermit crab',
'isopod',
'white stork, Ciconia ciconia',
'black stork, Ciconia nigra',
'spoonbill',
'flamingo',
'little blue heron, Egretta caerulea',
'American egret, great white heron, Egretta albus',
'bittern',
'crane',
'limpkin, Aramus pictus',
'European gallinule, Porphyrio porphyrio',
'American coot, marsh hen, mud hen, water hen, Fulica americana',
'bustard',
'ruddy turnstone, Arenaria interpres',
'red-backed sandpiper, dunlin, Erolia alpina',
'redshank, Tringa totanus',
'dowitcher',
'oystercatcher, oyster catcher',
'pelican',
'king penguin, Aptenodytes patagonica',
'albatross, mollymawk',
'grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus', # noqa: E501
'killer whale, killer, orca, grampus, sea wolf, Orcinus orca',
'dugong, Dugong dugon',
'sea lion',
'Chihuahua',
'Japanese spaniel',
'Maltese dog, Maltese terrier, Maltese',
'Pekinese, Pekingese, Peke',
'Shih-Tzu',
'Blenheim spaniel',
'papillon',
'toy terrier',
'Rhodesian ridgeback',
'Afghan hound, Afghan',
'basset, basset hound',
'beagle',
'bloodhound, sleuthhound',
'bluetick',
'black-and-tan coonhound',
'Walker hound, Walker foxhound',
'English foxhound',
'redbone',
'borzoi, Russian wolfhound',
'Irish wolfhound',
'Italian greyhound',
'whippet',
'Ibizan hound, Ibizan Podenco',
'Norwegian elkhound, elkhound',
'otterhound, otter hound',
'Saluki, gazelle hound',
'Scottish deerhound, deerhound',
'Weimaraner',
'Staffordshire bullterrier, Staffordshire bull terrier',
'American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier', # noqa: E501
'Bedlington terrier',
'Border terrier',
'Kerry blue terrier',
'Irish terrier',
'Norfolk terrier',
'Norwich terrier',
'Yorkshire terrier',
'wire-haired fox terrier',
'Lakeland terrier',
'Sealyham terrier, Sealyham',
'Airedale, Airedale terrier',
'cairn, cairn terrier',
'Australian terrier',
'Dandie Dinmont, Dandie Dinmont terrier',
'Boston bull, Boston terrier',
'miniature schnauzer',
'giant schnauzer',
'standard schnauzer',
'Scotch terrier, Scottish terrier, Scottie',
'Tibetan terrier, chrysanthemum dog',
'silky terrier, Sydney silky',
'soft-coated wheaten terrier',
'West Highland white terrier',
'Lhasa, Lhasa apso',
'flat-coated retriever',
'curly-coated retriever',
'golden retriever',
'Labrador retriever',
'Chesapeake Bay retriever',
'German short-haired pointer',
'vizsla, Hungarian pointer',
'English setter',
'Irish setter, red setter',
'Gordon setter',
'Brittany spaniel',
'clumber, clumber spaniel',
'English springer, English springer spaniel',
'Welsh springer spaniel',
'cocker spaniel, English cocker spaniel, cocker',
'Sussex spaniel',
'Irish water spaniel',
'kuvasz',
'schipperke',
'groenendael',
'malinois',
'briard',
'kelpie',
'komondor',
'Old English sheepdog, bobtail',
'Shetland sheepdog, Shetland sheep dog, Shetland',
'collie',
'Border collie',
'Bouvier des Flandres, Bouviers des Flandres',
'Rottweiler',
'German shepherd, German shepherd dog, German police dog, alsatian',
'Doberman, Doberman pinscher',
'miniature pinscher',
'Greater Swiss Mountain dog',
'Bernese mountain dog',
'Appenzeller',
'EntleBucher',
'boxer',
'bull mastiff',
'Tibetan mastiff',
'French bulldog',
'Great Dane',
'Saint Bernard, St Bernard',
'Eskimo dog, husky',
'malamute, malemute, Alaskan malamute',
'Siberian husky',
'dalmatian, coach dog, carriage dog',
'affenpinscher, monkey pinscher, monkey dog',
'basenji',
'pug, pug-dog',
'Leonberg',
'Newfoundland, Newfoundland dog',
'Great Pyrenees',
'Samoyed, Samoyede',
'Pomeranian',
'chow, chow chow',
'keeshond',
'Brabancon griffon',
'Pembroke, Pembroke Welsh corgi',
'Cardigan, Cardigan Welsh corgi',
'toy poodle',
'miniature poodle',
'standard poodle',
'Mexican hairless',
'timber wolf, grey wolf, gray wolf, Canis lupus',
'white wolf, Arctic wolf, Canis lupus tundrarum',
'red wolf, maned wolf, Canis rufus, Canis niger',
'coyote, prairie wolf, brush wolf, Canis latrans',
'dingo, warrigal, warragal, Canis dingo',
'dhole, Cuon alpinus',
'African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus',
'hyena, hyaena',
'red fox, Vulpes vulpes',
'kit fox, Vulpes macrotis',
'Arctic fox, white fox, Alopex lagopus',
'grey fox, gray fox, Urocyon cinereoargenteus',
'tabby, tabby cat',
'tiger cat',
'Persian cat',
'Siamese cat, Siamese',
'Egyptian cat',
'cougar, puma, catamount, mountain lion, painter, panther, Felis concolor', # noqa: E501
'lynx, catamount',
'leopard, Panthera pardus',
'snow leopard, ounce, Panthera uncia',
'jaguar, panther, Panthera onca, Felis onca',
'lion, king of beasts, Panthera leo',
'tiger, Panthera tigris',
'cheetah, chetah, Acinonyx jubatus',
'brown bear, bruin, Ursus arctos',
'American black bear, black bear, Ursus americanus, Euarctos americanus', # noqa: E501
'ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus',
'sloth bear, Melursus ursinus, Ursus ursinus',
'mongoose',
'meerkat, mierkat',
'tiger beetle',
'ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle',
'ground beetle, carabid beetle',
'long-horned beetle, longicorn, longicorn beetle',
'leaf beetle, chrysomelid',
'dung beetle',
'rhinoceros beetle',
'weevil',
'fly',
'bee',
'ant, emmet, pismire',
'grasshopper, hopper',
'cricket',
'walking stick, walkingstick, stick insect',
'cockroach, roach',
'mantis, mantid',
'cicada, cicala',
'leafhopper',
'lacewing, lacewing fly',
"dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk", # noqa: E501
'damselfly',
'admiral',
'ringlet, ringlet butterfly',
'monarch, monarch butterfly, milkweed butterfly, Danaus plexippus',
'cabbage butterfly',
'sulphur butterfly, sulfur butterfly',
'lycaenid, lycaenid butterfly',
'starfish, sea star',
'sea urchin',
'sea cucumber, holothurian',
'wood rabbit, cottontail, cottontail rabbit',
'hare',
'Angora, Angora rabbit',
'hamster',
'porcupine, hedgehog',
'fox squirrel, eastern fox squirrel, Sciurus niger',
'marmot',
'beaver',
'guinea pig, Cavia cobaya',
'sorrel',
'zebra',
'hog, pig, grunter, squealer, Sus scrofa',
'wild boar, boar, Sus scrofa',
'warthog',
'hippopotamus, hippo, river horse, Hippopotamus amphibius',
'ox',
'water buffalo, water ox, Asiatic buffalo, Bubalus bubalis',
'bison',
'ram, tup',
'bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis', # noqa: E501
'ibex, Capra ibex',
'hartebeest',
'impala, Aepyceros melampus',
'gazelle',
'Arabian camel, dromedary, Camelus dromedarius',
'llama',
'weasel',
'mink',
'polecat, fitch, foulmart, foumart, Mustela putorius',
'black-footed ferret, ferret, Mustela nigripes',
'otter',
'skunk, polecat, wood pussy',
'badger',
'armadillo',
'three-toed sloth, ai, Bradypus tridactylus',
'orangutan, orang, orangutang, Pongo pygmaeus',
'gorilla, Gorilla gorilla',
'chimpanzee, chimp, Pan troglodytes',
'gibbon, Hylobates lar',
'siamang, Hylobates syndactylus, Symphalangus syndactylus',
'guenon, guenon monkey',
'patas, hussar monkey, Erythrocebus patas',
'baboon',
'macaque',
'langur',
'colobus, colobus monkey',
'proboscis monkey, Nasalis larvatus',
'marmoset',
'capuchin, ringtail, Cebus capucinus',
'howler monkey, howler',
'titi, titi monkey',
'spider monkey, Ateles geoffroyi',
'squirrel monkey, Saimiri sciureus',
'Madagascar cat, ring-tailed lemur, Lemur catta',
'indri, indris, Indri indri, Indri brevicaudatus',
'Indian elephant, Elephas maximus',
'African elephant, Loxodonta africana',
'lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens',
'giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca',
'barracouta, snoek',
'eel',
'coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch', # noqa: E501
'rock beauty, Holocanthus tricolor',
'anemone fish',
'sturgeon',
'gar, garfish, garpike, billfish, Lepisosteus osseus',
'lionfish',
'puffer, pufferfish, blowfish, globefish',
'abacus',
'abaya',
"academic gown, academic robe, judge's robe",
'accordion, piano accordion, squeeze box',
'acoustic guitar',
'aircraft carrier, carrier, flattop, attack aircraft carrier',
'airliner',
'airship, dirigible',
'altar',
'ambulance',
'amphibian, amphibious vehicle',
'analog clock',
'apiary, bee house',
'apron',
'ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin', # noqa: E501
'assault rifle, assault gun',
'backpack, back pack, knapsack, packsack, rucksack, haversack',
'bakery, bakeshop, bakehouse',
'balance beam, beam',
'balloon',
'ballpoint, ballpoint pen, ballpen, Biro',
'Band Aid',
'banjo',
'bannister, banister, balustrade, balusters, handrail',
'barbell',
'barber chair',
'barbershop',
'barn',
'barometer',
'barrel, cask',
'barrow, garden cart, lawn cart, wheelbarrow',
'baseball',
'basketball',
'bassinet',
'bassoon',
'bathing cap, swimming cap',
'bath towel',
'bathtub, bathing tub, bath, tub',
'beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon', # noqa: E501
'beacon, lighthouse, beacon light, pharos',
'beaker',
'bearskin, busby, shako',
'beer bottle',
'beer glass',
'bell cote, bell cot',
'bib',
'bicycle-built-for-two, tandem bicycle, tandem',
'bikini, two-piece',
'binder, ring-binder',
'binoculars, field glasses, opera glasses',
'birdhouse',
'boathouse',
'bobsled, bobsleigh, bob',
'bolo tie, bolo, bola tie, bola',
'bonnet, poke bonnet',
'bookcase',
'bookshop, bookstore, bookstall',
'bottlecap',
'bow',
'bow tie, bow-tie, bowtie',
'brass, memorial tablet, plaque',
'brassiere, bra, bandeau',
'breakwater, groin, groyne, mole, bulwark, seawall, jetty',
'breastplate, aegis, egis',
'broom',
'bucket, pail',
'buckle',
'bulletproof vest',
'bullet train, bullet',
'butcher shop, meat market',
'cab, hack, taxi, taxicab',
'caldron, cauldron',
'candle, taper, wax light',
'cannon',
'canoe',
'can opener, tin opener',
'cardigan',
'car mirror',
'carousel, carrousel, merry-go-round, roundabout, whirligig',
"carpenter's kit, tool kit",
'carton',
'car wheel',
'cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM', # noqa: E501
'cassette',
'cassette player',
'castle',
'catamaran',
'CD player',
'cello, violoncello',
'cellular telephone, cellular phone, cellphone, cell, mobile phone',
'chain',
'chainlink fence',
'chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour', # noqa: E501
'chain saw, chainsaw',
'chest',
'chiffonier, commode',
'chime, bell, gong',
'china cabinet, china closet',
'Christmas stocking',
'church, church building',
'cinema, movie theater, movie theatre, movie house, picture palace',
'cleaver, meat cleaver, chopper',
'cliff dwelling',
'cloak',
'clog, geta, patten, sabot',
'cocktail shaker',
'coffee mug',
'coffeepot',
'coil, spiral, volute, whorl, helix',
'combination lock',
'computer keyboard, keypad',
'confectionery, confectionary, candy store',
'container ship, containership, container vessel',
'convertible',
'corkscrew, bottle screw',
'cornet, horn, trumpet, trump',
'cowboy boot',
'cowboy hat, ten-gallon hat',
'cradle',
'crane',
'crash helmet',
'crate',
'crib, cot',
'Crock Pot',
'croquet ball',
'crutch',
'cuirass',
'dam, dike, dyke',
'desk',
'desktop computer',
'dial telephone, dial phone',
'diaper, nappy, napkin',
'digital clock',
'digital watch',
'dining table, board',
'dishrag, dishcloth',
'dishwasher, dish washer, dishwashing machine',
'disk brake, disc brake',
'dock, dockage, docking facility',
'dogsled, dog sled, dog sleigh',
'dome',
'doormat, welcome mat',
'drilling platform, offshore rig',
'drum, membranophone, tympan',
'drumstick',
'dumbbell',
'Dutch oven',
'electric fan, blower',
'electric guitar',
'electric locomotive',
'entertainment center',
'envelope',
'espresso maker',
'face powder',
'feather boa, boa',
'file, file cabinet, filing cabinet',
'fireboat',
'fire engine, fire truck',
'fire screen, fireguard',
'flagpole, flagstaff',
'flute, transverse flute',
'folding chair',
'football helmet',
'forklift',
'fountain',
'fountain pen',
'four-poster',
'freight car',
'French horn, horn',
'frying pan, frypan, skillet',
'fur coat',
'garbage truck, dustcart',
'gasmask, respirator, gas helmet',
'gas pump, gasoline pump, petrol pump, island dispenser',
'goblet',
'go-kart',
'golf ball',
'golfcart, golf cart',
'gondola',
'gong, tam-tam',
'gown',
'grand piano, grand',
'greenhouse, nursery, glasshouse',
'grille, radiator grille',
'grocery store, grocery, food market, market',
'guillotine',
'hair slide',
'hair spray',
'half track',
'hammer',
'hamper',
'hand blower, blow dryer, blow drier, hair dryer, hair drier',
'hand-held computer, hand-held microcomputer',
'handkerchief, hankie, hanky, hankey',
'hard disc, hard disk, fixed disk',
'harmonica, mouth organ, harp, mouth harp',
'harp',
'harvester, reaper',
'hatchet',
'holster',
'home theater, home theatre',
'honeycomb',
'hook, claw',
'hoopskirt, crinoline',
'horizontal bar, high bar',
'horse cart, horse-cart',
'hourglass',
'iPod',
'iron, smoothing iron',
"jack-o'-lantern",
'jean, blue jean, denim',
'jeep, landrover',
'jersey, T-shirt, tee shirt',
'jigsaw puzzle',
'jinrikisha, ricksha, rickshaw',
'joystick',
'kimono',
'knee pad',
'knot',
'lab coat, laboratory coat',
'ladle',
'lampshade, lamp shade',
'laptop, laptop computer',
'lawn mower, mower',
'lens cap, lens cover',
'letter opener, paper knife, paperknife',
'library',
'lifeboat',
'lighter, light, igniter, ignitor',
'limousine, limo',
'liner, ocean liner',
'lipstick, lip rouge',
'Loafer',
'lotion',
'loudspeaker, speaker, speaker unit, loudspeaker system, speaker system', # noqa: E501
"loupe, jeweler's loupe",
'lumbermill, sawmill',
'magnetic compass',
'mailbag, postbag',
'mailbox, letter box',
'maillot',
'maillot, tank suit',
'manhole cover',
'maraca',
'marimba, xylophone',
'mask',
'matchstick',
'maypole',
'maze, labyrinth',
'measuring cup',
'medicine chest, medicine cabinet',
'megalith, megalithic structure',
'microphone, mike',
'microwave, microwave oven',
'military uniform',
'milk can',
'minibus',
'miniskirt, mini',
'minivan',
'missile',
'mitten',
'mixing bowl',
'mobile home, manufactured home',
'Model T',
'modem',
'monastery',
'monitor',
'moped',
'mortar',
'mortarboard',
'mosque',
'mosquito net',
'motor scooter, scooter',
'mountain bike, all-terrain bike, off-roader',
'mountain tent',
'mouse, computer mouse',
'mousetrap',
'moving van',
'muzzle',
'nail',
'neck brace',
'necklace',
'nipple',
'notebook, notebook computer',
'obelisk',
'oboe, hautboy, hautbois',
'ocarina, sweet potato',
'odometer, hodometer, mileometer, milometer',
'oil filter',
'organ, pipe organ',
'oscilloscope, scope, cathode-ray oscilloscope, CRO',
'overskirt',
'oxcart',
'oxygen mask',
'packet',
'paddle, boat paddle',
'paddlewheel, paddle wheel',
'padlock',
'paintbrush',
"pajama, pyjama, pj's, jammies",
'palace',
'panpipe, pandean pipe, syrinx',
'paper towel',
'parachute, chute',
'parallel bars, bars',
'park bench',
'parking meter',
'passenger car, coach, carriage',
'patio, terrace',
'pay-phone, pay-station',
'pedestal, plinth, footstall',
'pencil box, pencil case',
'pencil sharpener',
'perfume, essence',
'Petri dish',
'photocopier',
'pick, plectrum, plectron',
'pickelhaube',
'picket fence, paling',
'pickup, pickup truck',
'pier',
'piggy bank, penny bank',
'pill bottle',
'pillow',
'ping-pong ball',
'pinwheel',
'pirate, pirate ship',
'pitcher, ewer',
"plane, carpenter's plane, woodworking plane",
'planetarium',
'plastic bag',
'plate rack',
'plow, plough',
"plunger, plumber's helper",
'Polaroid camera, Polaroid Land camera',
'pole',
'police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria', # noqa: E501
'poncho',
'pool table, billiard table, snooker table',
'pop bottle, soda bottle',
'pot, flowerpot',
"potter's wheel",
'power drill',
'prayer rug, prayer mat',
'printer',
'prison, prison house',
'projectile, missile',
'projector',
'puck, hockey puck',
'punching bag, punch bag, punching ball, punchball',
'purse',
'quill, quill pen',
'quilt, comforter, comfort, puff',
'racer, race car, racing car',
'racket, racquet',
'radiator',
'radio, wireless',
'radio telescope, radio reflector',
'rain barrel',
'recreational vehicle, RV, R.V.',
'reel',
'reflex camera',
'refrigerator, icebox',
'remote control, remote',
'restaurant, eating house, eating place, eatery',
'revolver, six-gun, six-shooter',
'rifle',
'rocking chair, rocker',
'rotisserie',
'rubber eraser, rubber, pencil eraser',
'rugby ball',
'rule, ruler',
'running shoe',
'safe',
'safety pin',
'saltshaker, salt shaker',
'sandal',
'sarong',
'sax, saxophone',
'scabbard',
'scale, weighing machine',
'school bus',
'schooner',
'scoreboard',
'screen, CRT screen',
'screw',
'screwdriver',
'seat belt, seatbelt',
'sewing machine',
'shield, buckler',
'shoe shop, shoe-shop, shoe store',
'shoji',
'shopping basket',
'shopping cart',
'shovel',
'shower cap',
'shower curtain',
'ski',
'ski mask',
'sleeping bag',
'slide rule, slipstick',
'sliding door',
'slot, one-armed bandit',
'snorkel',
'snowmobile',
'snowplow, snowplough',
'soap dispenser',
'soccer ball',
'sock',
'solar dish, solar collector, solar furnace',
'sombrero',
'soup bowl',
'space bar',
'space heater',
'space shuttle',
'spatula',
'speedboat',
"spider web, spider's web",
'spindle',
'sports car, sport car',
'spotlight, spot',
'stage',
'steam locomotive',
'steel arch bridge',
'steel drum',
'stethoscope',
'stole',
'stone wall',
'stopwatch, stop watch',
'stove',
'strainer',
'streetcar, tram, tramcar, trolley, trolley car',
'stretcher',
'studio couch, day bed',
'stupa, tope',
'submarine, pigboat, sub, U-boat',
'suit, suit of clothes',
'sundial',
'sunglass',
'sunglasses, dark glasses, shades',
'sunscreen, sunblock, sun blocker',
'suspension bridge',
'swab, swob, mop',
'sweatshirt',
'swimming trunks, bathing trunks',
'swing',
'switch, electric switch, electrical switch',
'syringe',
'table lamp',
'tank, army tank, armored combat vehicle, armoured combat vehicle',
'tape player',
'teapot',
'teddy, teddy bear',
'television, television system',
'tennis ball',
'thatch, thatched roof',
'theater curtain, theatre curtain',
'thimble',
'thresher, thrasher, threshing machine',
'throne',
'tile roof',
'toaster',
'tobacco shop, tobacconist shop, tobacconist',
'toilet seat',
'torch',
'totem pole',
'tow truck, tow car, wrecker',
'toyshop',
'tractor',
'trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi', # noqa: E501
'tray',
'trench coat',
'tricycle, trike, velocipede',
'trimaran',
'tripod',
'triumphal arch',
'trolleybus, trolley coach, trackless trolley',
'trombone',
'tub, vat',
'turnstile',
'typewriter keyboard',
'umbrella',
'unicycle, monocycle',
'upright, upright piano',
'vacuum, vacuum cleaner',
'vase',
'vault',
'velvet',
'vending machine',
'vestment',
'viaduct',
'violin, fiddle',
'volleyball',
'waffle iron',
'wall clock',
'wallet, billfold, notecase, pocketbook',
'wardrobe, closet, press',
'warplane, military plane',
'washbasin, handbasin, washbowl, lavabo, wash-hand basin',
'washer, automatic washer, washing machine',
'water bottle',
'water jug',
'water tower',
'whiskey jug',
'whistle',
'wig',
'window screen',
'window shade',
'Windsor tie',
'wine bottle',
'wing',
'wok',
'wooden spoon',
'wool, woolen, woollen',
'worm fence, snake fence, snake-rail fence, Virginia fence',
'wreck',
'yawl',
'yurt',
'web site, website, internet site, site',
'comic book',
'crossword puzzle, crossword',
'street sign',
'traffic light, traffic signal, stoplight',
'book jacket, dust cover, dust jacket, dust wrapper',
'menu',
'plate',
'guacamole',
'consomme',
'hot pot, hotpot',
'trifle',
'ice cream, icecream',
'ice lolly, lolly, lollipop, popsicle',
'French loaf',
'bagel, beigel',
'pretzel',
'cheeseburger',
'hotdog, hot dog, red hot',
'mashed potato',
'head cabbage',
'broccoli',
'cauliflower',
'zucchini, courgette',
'spaghetti squash',
'acorn squash',
'butternut squash',
'cucumber, cuke',
'artichoke, globe artichoke',
'bell pepper',
'cardoon',
'mushroom',
'Granny Smith',
'strawberry',
'orange',
'lemon',
'fig',
'pineapple, ananas',
'banana',
'jackfruit, jak, jack',
'custard apple',
'pomegranate',
'hay',
'carbonara',
'chocolate sauce, chocolate syrup',
'dough',
'meat loaf, meatloaf',
'pizza, pizza pie',
'potpie',
'burrito',
'red wine',
'espresso',
'cup',
'eggnog',
'alp',
'bubble',
'cliff, drop, drop-off',
'coral reef',
'geyser',
'lakeside, lakeshore',
'promontory, headland, head, foreland',
'sandbar, sand bar',
'seashore, coast, seacoast, sea-coast',
'valley, vale',
'volcano',
'ballplayer, baseball player',
'groom, bridegroom',
'scuba diver',
'rapeseed',
'daisy',
"yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum", # noqa: E501
'corn',
'acorn',
'hip, rose hip, rosehip',
'buckeye, horse chestnut, conker',
'coral fungus',
'agaric',
'gyromitra',
'stinkhorn, carrion fungus',
'earthstar',
'hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa', # noqa: E501
'bolete',
'ear, spike, capitulum',
'toilet tissue, toilet paper, bathroom tissue')
CIFAR10_CATEGORIES = ('airplane', 'automobile', 'bird', 'cat', 'deer', 'dog',
'frog', 'horse', 'ship', 'truck')
CIFAR100_CATEGORIES = (
'apple', 'aquarium_fish', 'baby', 'bear', 'beaver', 'bed', 'bee', 'beetle',
'bicycle', 'bottle', 'bowl', 'boy', 'bridge', 'bus', 'butterfly', 'camel',
'can', 'castle', 'caterpillar', 'cattle', 'chair', 'chimpanzee', 'clock',
'cloud', 'cockroach', 'couch', 'crab', 'crocodile', 'cup', 'dinosaur',
'dolphin', 'elephant', 'flatfish', 'forest', 'fox', 'girl', 'hamster',
'house', 'kangaroo', 'keyboard', 'lamp', 'lawn_mower', 'leopard', 'lion',
'lizard', 'lobster', 'man', 'maple_tree', 'motorcycle', 'mountain',
'mouse', 'mushroom', 'oak_tree', 'orange', 'orchid', 'otter', 'palm_tree',
'pear', 'pickup_truck', 'pine_tree', 'plain', 'plate', 'poppy',
'porcupine', 'possum', 'rabbit', 'raccoon', 'ray', 'road', 'rocket',
'rose', 'sea', 'seal', 'shark', 'shrew', 'skunk', 'skyscraper', 'snail',
'snake', 'spider', 'squirrel', 'streetcar', 'sunflower', 'sweet_pepper',
'table', 'tank', 'telephone', 'television', 'tiger', 'tractor', 'train',
'trout', 'tulip', 'turtle', 'wardrobe', 'whale', 'willow_tree', 'wolf',
'woman', 'worm')
MNIST_CATEGORITES = ('0 - zero', '1 - one', '2 - two', '3 - three', '4 - four',
'5 - five', '6 - six', '7 - seven', '8 - eight',
'9 - nine')
FASHIONMNIST_CATEGORITES = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress',
'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag',
'Ankle boot')
PLACES205_CATEGORIES = (
'abbey', 'airport_terminal', 'alley', 'amphitheater', 'amusement_park',
'aquarium', 'aqueduct', 'arch', 'art_gallery', 'art_studio',
'assembly_line', 'attic', 'auditorium', 'apartment_building/outdoor',
'badlands', 'ballroom', 'bamboo_forest', 'banquet_hall', 'bar',
'baseball_field', 'basement', 'basilica', 'bayou', 'beauty_salon',
'bedroom', 'boardwalk', 'boat_deck', 'bookstore', 'botanical_garden',
'bowling_alley', 'boxing_ring', 'bridge', 'building_facade',
'bus_interior', 'butchers_shop', 'butte', 'bakery/shop', 'cafeteria',
'campsite', 'candy_store', 'canyon', 'castle', 'cemetery', 'chalet',
'classroom', 'closet', 'clothing_store', 'coast', 'cockpit', 'coffee_shop',
'conference_center', 'conference_room', 'construction_site', 'corn_field',
'corridor', 'cottage_garden', 'courthouse', 'courtyard', 'creek',
'crevasse', 'crosswalk', 'cathedral/outdoor', 'church/outdoor', 'dam',
'dining_room', 'dock', 'dorm_room', 'driveway', 'desert/sand',
'desert/vegetation', 'dinette/home', 'doorway/outdoor', 'engine_room',
'excavation', 'fairway', 'fire_escape', 'fire_station', 'food_court',
'forest_path', 'forest_road', 'formal_garden', 'fountain',
'field/cultivated', 'field/wild', 'galley', 'game_room', 'garbage_dump',
'gas_station', 'gift_shop', 'golf_course', 'harbor', 'herb_garden',
'highway', 'home_office', 'hospital', 'hospital_room', 'hot_spring',
'hotel_room', 'hotel/outdoor', 'ice_cream_parlor', 'iceberg', 'igloo',
'islet', 'ice_skating_rink/outdoor', 'inn/outdoor', 'jail_cell', 'kasbah',
'kindergarden_classroom', 'kitchen', 'kitchenette', 'laundromat',
'lighthouse', 'living_room', 'lobby', 'locker_room', 'mansion', 'marsh',
'martial_arts_gym', 'mausoleum', 'medina', 'motel', 'mountain',
'mountain_snowy', 'music_studio', 'market/outdoor', 'monastery/outdoor',
'museum/indoor', 'nursery', 'ocean', 'office', 'office_building',
'orchard', 'pagoda', 'palace', 'pantry', 'parking_lot', 'parlor',
'pasture', 'patio', 'pavilion', 'phone_booth', 'picnic_area', 'playground',
'plaza', 'pond', 'pulpit', 'racecourse', 'raft', 'railroad_track',
'rainforest', 'reception', 'residential_neighborhood', 'restaurant',
'restaurant_kitchen', 'restaurant_patio', 'rice_paddy', 'river',
'rock_arch', 'rope_bridge', 'ruin', 'runway', 'sandbar', 'schoolhouse',
'sea_cliff', 'shed', 'shoe_shop', 'shopfront', 'shower', 'ski_resort',
'ski_slope', 'sky', 'skyscraper', 'slum', 'snowfield', 'staircase',
'supermarket', 'swamp', 'stadium/baseball', 'stadium/football',
'stage/indoor', 'subway_station/platform', 'swimming_pool/outdoor',
'television_studio', 'topiary_garden', 'tower', 'train_railway',
'tree_farm', 'trench', 'temple/east_asia', 'temple/south_asia',
'track/outdoor', 'train_station/platform', 'underwater/coral_reef',
'valley', 'vegetable_garden', 'veranda', 'viaduct', 'volcano',
'waiting_room', 'water_tower', 'watering_hole', 'wheat_field', 'wind_farm',
'windmill', 'yard')
OxfordIIITPet_CATEGORIES = (
'Abyssinian', 'american_bulldog', 'american_pit_bull_terrier',
'basset_hound', 'beagle', 'Bengal', 'Birman', 'Bombay', 'boxer',
'British_Shorthair', 'chihuahua', 'Egyptian_Mau', 'english_cocker_spaniel',
'english_setter', 'german_shorthaired', 'great_pyrenees', 'havanese',
'japanese_chin', 'keeshond', 'leonberger', 'Maine_Coon',
'miniature_pinscher', 'newfoundland', 'Persian', 'pomeranian', 'pug',
'Ragdoll', 'Russian_Blue', 'saint_bernard', 'samoyed', 'scottish_terrier',
'shiba_inu', 'Siamese', 'Sphynx', 'staffordshire_bull_terrier',
'wheaten_terrier', 'yorkshire_terrier')
DTD_CATEGORIES = ('banded', 'blotchy', 'braided', 'bubbly', 'bumpy',
'chequered', 'cobwebbed', 'cracked', 'crosshatched',
'crystalline', 'dotted', 'fibrous', 'flecked', 'freckled',
'frilly', 'gauzy', 'grid', 'grooved', 'honeycombed',
'interlaced', 'knitted', 'lacelike', 'lined', 'marbled',
'matted', 'meshed', 'paisley', 'perforated', 'pitted',
'pleated', 'polka-dotted', 'porous', 'potholed', 'scaly',
'smeared', 'spiralled', 'sprinkled', 'stained', 'stratified',
'striped', 'studded', 'swirly', 'veined', 'waffled', 'woven',
'wrinkled', 'zigzagged')
FGVCAIRCRAFT_CATEGORIES = (
'707-320', '727-200', '737-200', '737-300', '737-400', '737-500',
'737-600', '737-700', '737-800', '737-900', '747-100', '747-200',
'747-300', '747-400', '757-200', '757-300', '767-200', '767-300',
'767-400', '777-200', '777-300', 'A300B4', 'A310', 'A318', 'A319', 'A320',
'A321', 'A330-200', 'A330-300', 'A340-200', 'A340-300', 'A340-500',
'A340-600', 'A380', 'ATR-42', 'ATR-72', 'An-12', 'BAE 146-200',
'BAE 146-300', 'BAE-125', 'Beechcraft 1900', 'Boeing 717', 'C-130', 'C-47',
'CRJ-200', 'CRJ-700', 'CRJ-900', 'Cessna 172', 'Cessna 208', 'Cessna 525',
'Cessna 560', 'Challenger 600', 'DC-10', 'DC-3', 'DC-6', 'DC-8', 'DC-9-30',
'DH-82', 'DHC-1', 'DHC-6', 'DHC-8-100', 'DHC-8-300', 'DR-400',
'Dornier 328', 'E-170', 'E-190', 'E-195', 'EMB-120', 'ERJ 135', 'ERJ 145',
'Embraer Legacy 600', 'Eurofighter Typhoon', 'F-16A/B', 'F/A-18',
'Falcon 2000', 'Falcon 900', 'Fokker 100', 'Fokker 50', 'Fokker 70',
'Global Express', 'Gulfstream IV', 'Gulfstream V', 'Hawk T1', 'Il-76',
'L-1011', 'MD-11', 'MD-80', 'MD-87', 'MD-90', 'Metroliner', 'Model B200',
'PA-28', 'SR-20', 'Saab 2000', 'Saab 340', 'Spitfire', 'Tornado', 'Tu-134',
'Tu-154', 'Yak-42')
STANFORDCARS_CATEGORIES = (
'AM General Hummer SUV 2000', 'Acura RL Sedan 2012', 'Acura TL Sedan 2012',
'Acura TL Type-S 2008', 'Acura TSX Sedan 2012',
'Acura Integra Type R 2001', 'Acura ZDX Hatchback 2012',
'Aston Martin V8 Vantage Convertible 2012',
'Aston Martin V8 Vantage Coupe 2012',
'Aston Martin Virage Convertible 2012', 'Aston Martin Virage Coupe 2012',
'Audi RS 4 Convertible 2008', 'Audi A5 Coupe 2012', 'Audi TTS Coupe 2012',
'Audi R8 Coupe 2012', 'Audi V8 Sedan 1994', 'Audi 100 Sedan 1994',
'Audi 100 Wagon 1994', 'Audi TT Hatchback 2011', 'Audi S6 Sedan 2011',
'Audi S5 Convertible 2012', 'Audi S5 Coupe 2012', 'Audi S4 Sedan 2012',
'Audi S4 Sedan 2007', 'Audi TT RS Coupe 2012',
'BMW ActiveHybrid 5 Sedan 2012', 'BMW 1 Series Convertible 2012',
'BMW 1 Series Coupe 2012', 'BMW 3 Series Sedan 2012',
'BMW 3 Series Wagon 2012', 'BMW 6 Series Convertible 2007',
'BMW X5 SUV 2007', 'BMW X6 SUV 2012', 'BMW M3 Coupe 2012',
'BMW M5 Sedan 2010', 'BMW M6 Convertible 2010', 'BMW X3 SUV 2012',
'BMW Z4 Convertible 2012',
'Bentley Continental Supersports Conv. Convertible 2012',
'Bentley Arnage Sedan 2009', 'Bentley Mulsanne Sedan 2011',
'Bentley Continental GT Coupe 2012', 'Bentley Continental GT Coupe 2007',
'Bentley Continental Flying Spur Sedan 2007',
'Bugatti Veyron 16.4 Convertible 2009', 'Bugatti Veyron 16.4 Coupe 2009',
'Buick Regal GS 2012', 'Buick Rainier SUV 2007', 'Buick Verano Sedan 2012',
'Buick Enclave SUV 2012', 'Cadillac CTS-V Sedan 2012',
'Cadillac SRX SUV 2012', 'Cadillac Escalade EXT Crew Cab 2007',
'Chevrolet Silverado 1500 Hybrid Crew Cab 2012',
'Chevrolet Corvette Convertible 2012', 'Chevrolet Corvette ZR1 2012',
'Chevrolet Corvette Ron Fellows Edition Z06 2007',
'Chevrolet Traverse SUV 2012', 'Chevrolet Camaro Convertible 2012',
'Chevrolet HHR SS 2010', 'Chevrolet Impala Sedan 2007',
'Chevrolet Tahoe Hybrid SUV 2012', 'Chevrolet Sonic Sedan 2012',
'Chevrolet Express Cargo Van 2007', 'Chevrolet Avalanche Crew Cab 2012',
'Chevrolet Cobalt SS 2010', 'Chevrolet Malibu Hybrid Sedan 2010',
'Chevrolet TrailBlazer SS 2009',
'Chevrolet Silverado 2500HD Regular Cab 2012',
'Chevrolet Silverado 1500 Classic Extended Cab 2007',
'Chevrolet Express Van 2007', 'Chevrolet Monte Carlo Coupe 2007',
'Chevrolet Malibu Sedan 2007',
'Chevrolet Silverado 1500 Extended Cab 2012',
'Chevrolet Silverado 1500 Regular Cab 2012', 'Chrysler Aspen SUV 2009',
'Chrysler Sebring Convertible 2010',
'Chrysler Town and Country Minivan 2012', 'Chrysler 300 SRT-8 2010',
'Chrysler Crossfire Convertible 2008',
'Chrysler PT Cruiser Convertible 2008', 'Daewoo Nubira Wagon 2002',
'Dodge Caliber Wagon 2012', 'Dodge Caliber Wagon 2007',
'Dodge Caravan Minivan 1997', 'Dodge Ram Pickup 3500 Crew Cab 2010',
'Dodge Ram Pickup 3500 Quad Cab 2009', 'Dodge Sprinter Cargo Van 2009',
'Dodge Journey SUV 2012', 'Dodge Dakota Crew Cab 2010',
'Dodge Dakota Club Cab 2007', 'Dodge Magnum Wagon 2008',
'Dodge Challenger SRT8 2011', 'Dodge Durango SUV 2012',
'Dodge Durango SUV 2007', 'Dodge Charger Sedan 2012',
'Dodge Charger SRT-8 2009', 'Eagle Talon Hatchback 1998',
'FIAT 500 Abarth 2012', 'FIAT 500 Convertible 2012',
'Ferrari FF Coupe 2012', 'Ferrari California Convertible 2012',
'Ferrari 458 Italia Convertible 2012', 'Ferrari 458 Italia Coupe 2012',
'Fisker Karma Sedan 2012', 'Ford F-450 Super Duty Crew Cab 2012',
'Ford Mustang Convertible 2007', 'Ford Freestar Minivan 2007',
'Ford Expedition EL SUV 2009', 'Ford Edge SUV 2012',
'Ford Ranger SuperCab 2011', 'Ford GT Coupe 2006',
'Ford F-150 Regular Cab 2012', 'Ford F-150 Regular Cab 2007',
'Ford Focus Sedan 2007', 'Ford E-Series Wagon Van 2012',
'Ford Fiesta Sedan 2012', 'GMC Terrain SUV 2012', 'GMC Savana Van 2012',
'GMC Yukon Hybrid SUV 2012', 'GMC Acadia SUV 2012',
'GMC Canyon Extended Cab 2012', 'Geo Metro Convertible 1993',
'HUMMER H3T Crew Cab 2010', 'HUMMER H2 SUT Crew Cab 2009',
'Honda Odyssey Minivan 2012', 'Honda Odyssey Minivan 2007',
'Honda Accord Coupe 2012', 'Honda Accord Sedan 2012',
'Hyundai Veloster Hatchback 2012', 'Hyundai Santa Fe SUV 2012',
'Hyundai Tucson SUV 2012', 'Hyundai Veracruz SUV 2012',
'Hyundai Sonata Hybrid Sedan 2012', 'Hyundai Elantra Sedan 2007',
'Hyundai Accent Sedan 2012', 'Hyundai Genesis Sedan 2012',
'Hyundai Sonata Sedan 2012', 'Hyundai Elantra Touring Hatchback 2012',
'Hyundai Azera Sedan 2012', 'Infiniti G Coupe IPL 2012',
'Infiniti QX56 SUV 2011', 'Isuzu Ascender SUV 2008', 'Jaguar XK XKR 2012',
'Jeep Patriot SUV 2012', 'Jeep Wrangler SUV 2012', 'Jeep Liberty SUV 2012',
'Jeep Grand Cherokee SUV 2012', 'Jeep Compass SUV 2012',
'Lamborghini Reventon Coupe 2008', 'Lamborghini Aventador Coupe 2012',
'Lamborghini Gallardo LP 570-4 Superleggera 2012',
'Lamborghini Diablo Coupe 2001', 'Land Rover Range Rover SUV 2012',
'Land Rover LR2 SUV 2012', 'Lincoln Town Car Sedan 2011',
'MINI Cooper Roadster Convertible 2012',
'Maybach Landaulet Convertible 2012', 'Mazda Tribute SUV 2011',
'McLaren MP4-12C Coupe 2012', 'Mercedes-Benz 300-Class Convertible 1993',
'Mercedes-Benz C-Class Sedan 2012', 'Mercedes-Benz SL-Class Coupe 2009',
'Mercedes-Benz E-Class Sedan 2012', 'Mercedes-Benz S-Class Sedan 2012',
'Mercedes-Benz Sprinter Van 2012', 'Mitsubishi Lancer Sedan 2012',
'Nissan Leaf Hatchback 2012', 'Nissan NV Passenger Van 2012',
'Nissan Juke Hatchback 2012', 'Nissan 240SX Coupe 1998',
'Plymouth Neon Coupe 1999', 'Porsche Panamera Sedan 2012',
'Ram C/V Cargo Van Minivan 2012',
'Rolls-Royce Phantom Drophead Coupe Convertible 2012',
'Rolls-Royce Ghost Sedan 2012', 'Rolls-Royce Phantom Sedan 2012',
'Scion xD Hatchback 2012', 'Spyker C8 Convertible 2009',
'Spyker C8 Coupe 2009', 'Suzuki Aerio Sedan 2007',
'Suzuki Kizashi Sedan 2012', 'Suzuki SX4 Hatchback 2012',
'Suzuki SX4 Sedan 2012', 'Tesla Model S Sedan 2012',
'Toyota Sequoia SUV 2012', 'Toyota Camry Sedan 2012',
'Toyota Corolla Sedan 2012', 'Toyota 4Runner SUV 2012',
'Volkswagen Golf Hatchback 2012', 'Volkswagen Golf Hatchback 1991',
'Volkswagen Beetle Hatchback 2012', 'Volvo C30 Hatchback 2012',
'Volvo 240 Sedan 1993', 'Volvo XC90 SUV 2007',
'smart fortwo Convertible 2012')
SUN397_CATEGORIES = (
'abbey', 'airplane_cabin', 'airport_terminal', 'alley', 'amphitheater',
'amusement_arcade', 'amusement_park', 'anechoic_chamber',
'apartment_building_outdoor', 'apse_indoor', 'aquarium', 'aqueduct',
'arch', 'archive', 'arrival_gate_outdoor', 'art_gallery', 'art_school',
'art_studio', 'assembly_line', 'athletic_field_outdoor', 'atrium_public',
'attic', 'auditorium', 'auto_factory', 'badlands',
'badminton_court_indoor', 'baggage_claim', 'bakery_shop',
'balcony_exterior', 'balcony_interior', 'ball_pit', 'ballroom',
'bamboo_forest', 'banquet_hall', 'bar', 'barn', 'barndoor',
'baseball_field', 'basement', 'basilica', 'basketball_court_outdoor',
'bathroom', 'batters_box', 'bayou', 'bazaar_indoor', 'bazaar_outdoor',
'beach', 'beauty_salon', 'bedroom', 'berth', 'biology_laboratory',
'bistro_indoor', 'boardwalk', 'boat_deck', 'boathouse', 'bookstore',
'booth_indoor', 'botanical_garden', 'bow_window_indoor',
'bow_window_outdoor', 'bowling_alley', 'boxing_ring', 'brewery_indoor',
'bridge', 'building_facade', 'bullring', 'burial_chamber', 'bus_interior',
'butchers_shop', 'butte', 'cabin_outdoor', 'cafeteria', 'campsite',
'campus', 'canal_natural', 'canal_urban', 'candy_store', 'canyon',
'car_interior_backseat', 'car_interior_frontseat', 'carrousel',
'casino_indoor', 'castle', 'catacomb', 'cathedral_indoor',
'cathedral_outdoor', 'cavern_indoor', 'cemetery', 'chalet',
'cheese_factory', 'chemistry_lab', 'chicken_coop_indoor',
'chicken_coop_outdoor', 'childs_room', 'church_indoor', 'church_outdoor',
'classroom', 'clean_room', 'cliff', 'cloister_indoor', 'closet',
'clothing_store', 'coast', 'cockpit', 'coffee_shop', 'computer_room',
'conference_center', 'conference_room', 'construction_site',
'control_room', 'control_tower_outdoor', 'corn_field', 'corral',
'corridor', 'cottage_garden', 'courthouse', 'courtroom', 'courtyard',
'covered_bridge_exterior', 'creek', 'crevasse', 'crosswalk',
'cubicle_office', 'dam', 'delicatessen', 'dentists_office', 'desert_sand',
'desert_vegetation', 'diner_indoor', 'diner_outdoor', 'dinette_home',
'dinette_vehicle', 'dining_car', 'dining_room', 'discotheque', 'dock',
'doorway_outdoor', 'dorm_room', 'driveway', 'driving_range_outdoor',
'drugstore', 'electrical_substation', 'elevator_door', 'elevator_interior',
'elevator_shaft', 'engine_room', 'escalator_indoor', 'excavation',
'factory_indoor', 'fairway', 'fastfood_restaurant', 'field_cultivated',
'field_wild', 'fire_escape', 'fire_station', 'firing_range_indoor',
'fishpond', 'florist_shop_indoor', 'food_court', 'forest_broadleaf',
'forest_needleleaf', 'forest_path', 'forest_road', 'formal_garden',
'fountain', 'galley', 'game_room', 'garage_indoor', 'garbage_dump',
'gas_station', 'gazebo_exterior', 'general_store_indoor',
'general_store_outdoor', 'gift_shop', 'golf_course', 'greenhouse_indoor',
'greenhouse_outdoor', 'gymnasium_indoor', 'hangar_indoor',
'hangar_outdoor', 'harbor', 'hayfield', 'heliport', 'herb_garden',
'highway', 'hill', 'home_office', 'hospital', 'hospital_room',
'hot_spring', 'hot_tub_outdoor', 'hotel_outdoor', 'hotel_room', 'house',
'hunting_lodge_outdoor', 'ice_cream_parlor', 'ice_floe', 'ice_shelf',
'ice_skating_rink_indoor', 'ice_skating_rink_outdoor', 'iceberg', 'igloo',
'industrial_area', 'inn_outdoor', 'islet', 'jacuzzi_indoor', 'jail_indoor',
'jail_cell', 'jewelry_shop', 'kasbah', 'kennel_indoor', 'kennel_outdoor',
'kindergarden_classroom', 'kitchen', 'kitchenette', 'labyrinth_outdoor',
'lake_natural', 'landfill', 'landing_deck', 'laundromat', 'lecture_room',
'library_indoor', 'library_outdoor', 'lido_deck_outdoor', 'lift_bridge',
'lighthouse', 'limousine_interior', 'living_room', 'lobby', 'lock_chamber',
'locker_room', 'mansion', 'manufactured_home', 'market_indoor',
'market_outdoor', 'marsh', 'martial_arts_gym', 'mausoleum', 'medina',
'moat_water', 'monastery_outdoor', 'mosque_indoor', 'mosque_outdoor',
'motel', 'mountain', 'mountain_snowy', 'movie_theater_indoor',
'museum_indoor', 'music_store', 'music_studio',
'nuclear_power_plant_outdoor', 'nursery', 'oast_house',
'observatory_outdoor', 'ocean', 'office', 'office_building',
'oil_refinery_outdoor', 'oilrig', 'operating_room', 'orchard',
'outhouse_outdoor', 'pagoda', 'palace', 'pantry', 'park',
'parking_garage_indoor', 'parking_garage_outdoor', 'parking_lot', 'parlor',
'pasture', 'patio', 'pavilion', 'pharmacy', 'phone_booth',
'physics_laboratory', 'picnic_area', 'pilothouse_indoor',
'planetarium_outdoor', 'playground', 'playroom', 'plaza', 'podium_indoor',
'podium_outdoor', 'pond', 'poolroom_establishment', 'poolroom_home',
'power_plant_outdoor', 'promenade_deck', 'pub_indoor', 'pulpit',
'putting_green', 'racecourse', 'raceway', 'raft', 'railroad_track',
'rainforest', 'reception', 'recreation_room', 'residential_neighborhood',
'restaurant', 'restaurant_kitchen', 'restaurant_patio', 'rice_paddy',
'riding_arena', 'river', 'rock_arch', 'rope_bridge', 'ruin', 'runway',
'sandbar', 'sandbox', 'sauna', 'schoolhouse', 'sea_cliff', 'server_room',
'shed', 'shoe_shop', 'shopfront', 'shopping_mall_indoor', 'shower',
'skatepark', 'ski_lodge', 'ski_resort', 'ski_slope', 'sky', 'skyscraper',
'slum', 'snowfield', 'squash_court', 'stable', 'stadium_baseball',
'stadium_football', 'stage_indoor', 'staircase', 'street',
'subway_interior', 'subway_station_platform', 'supermarket', 'sushi_bar',
'swamp', 'swimming_pool_indoor', 'swimming_pool_outdoor',
'synagogue_indoor', 'synagogue_outdoor', 'television_studio',
'temple_east_asia', 'temple_south_asia', 'tennis_court_indoor',
'tennis_court_outdoor', 'tent_outdoor', 'theater_indoor_procenium',
'theater_indoor_seats', 'thriftshop', 'throne_room', 'ticket_booth',
'toll_plaza', 'topiary_garden', 'tower', 'toyshop', 'track_outdoor',
'train_railway', 'train_station_platform', 'tree_farm', 'tree_house',
'trench', 'underwater_coral_reef', 'utility_room', 'valley',
'van_interior', 'vegetable_garden', 'veranda', 'veterinarians_office',
'viaduct', 'videostore', 'village', 'vineyard', 'volcano',
'volleyball_court_indoor', 'volleyball_court_outdoor', 'waiting_room',
'warehouse_indoor', 'water_tower', 'waterfall_block', 'waterfall_fan',
'waterfall_plunge', 'watering_hole', 'wave', 'wet_bar', 'wheat_field',
'wind_farm', 'windmill', 'wine_cellar_barrel_storage',
'wine_cellar_bottle_storage', 'wrestling_ring_indoor', 'yard',
'youth_hostel')
CALTECH101_CATEGORIES = (
'BACKGROUND_Google', 'Faces', 'Faces_easy', 'Leopards', 'Motorbikes',
'accordion', 'airplanes', 'anchor', 'ant', 'barrel', 'bass', 'beaver',
'binocular', 'bonsai', 'brain', 'brontosaurus', 'buddha', 'butterfly',
'camera', 'cannon', 'car_side', 'ceiling_fan', 'cellphone', 'chair',
'chandelier', 'cougar_body', 'cougar_face', 'crab', 'crayfish',
'crocodile', 'crocodile_head', 'cup', 'dalmatian', 'dollar_bill',
'dolphin', 'dragonfly', 'electric_guitar', 'elephant', 'emu', 'euphonium',
'ewer', 'ferry', 'flamingo', 'flamingo_head', 'garfield', 'gerenuk',
'gramophone', 'grand_piano', 'hawksbill', 'headphone', 'hedgehog',
'helicopter', 'ibis', 'inline_skate', 'joshua_tree', 'kangaroo', 'ketch',
'lamp', 'laptop', 'llama', 'lobster', 'lotus', 'mandolin', 'mayfly',
'menorah', 'metronome', 'minaret', 'nautilus', 'octopus', 'okapi',
'pagoda', 'panda', 'pigeon', 'pizza', 'platypus', 'pyramid', 'revolver',
'rhino', 'rooster', 'saxophone', 'schooner', 'scissors', 'scorpion',
'sea_horse', 'snoopy', 'soccer_ball', 'stapler', 'starfish', 'stegosaurus',
'stop_sign', 'strawberry', 'sunflower', 'tick', 'trilobite', 'umbrella',
'watch', 'water_lilly', 'wheelchair', 'wild_cat', 'windsor_chair',
'wrench', 'yin_yang')
FOOD101_CATEGORIES = (
'apple_pie', 'baby_back_ribs', 'baklava', 'beef_carpaccio', 'beef_tartare',
'beet_salad', 'beignets', 'bibimbap', 'bread_pudding', 'breakfast_burrito',
'bruschetta', 'caesar_salad', 'cannoli', 'caprese_salad', 'carrot_cake',
'ceviche', 'cheesecake', 'cheese_plate', 'chicken_curry',
'chicken_quesadilla', 'chicken_wings', 'chocolate_cake',
'chocolate_mousse', 'churros', 'clam_chowder', 'club_sandwich',
'crab_cakes', 'creme_brulee', 'croque_madame', 'cup_cakes', 'deviled_eggs',
'donuts', 'dumplings', 'edamame', 'eggs_benedict', 'escargots', 'falafel',
'filet_mignon', 'fish_and_chips', 'foie_gras', 'french_fries',
'french_onion_soup', 'french_toast', 'fried_calamari', 'fried_rice',
'frozen_yogurt', 'garlic_bread', 'gnocchi', 'greek_salad',
'grilled_cheese_sandwich', 'grilled_salmon', 'guacamole', 'gyoza',
'hamburger', 'hot_and_sour_soup', 'hot_dog', 'huevos_rancheros', 'hummus',
'ice_cream', 'lasagna', 'lobster_bisque', 'lobster_roll_sandwich',
'macaroni_and_cheese', 'macarons', 'miso_soup', 'mussels', 'nachos',
'omelette', 'onion_rings', 'oysters', 'pad_thai', 'paella', 'pancakes',
'panna_cotta', 'peking_duck', 'pho', 'pizza', 'pork_chop', 'poutine',
'prime_rib', 'pulled_pork_sandwich', 'ramen', 'ravioli', 'red_velvet_cake',
'risotto', 'samosa', 'sashimi', 'scallops', 'seaweed_salad',
'shrimp_and_grits', 'spaghetti_bolognese', 'spaghetti_carbonara',
'spring_rolls', 'steak', 'strawberry_shortcake', 'sushi', 'tacos',
'takoyaki', 'tiramisu', 'tuna_tartare', 'waffles')
CIFAR100_CATEGORIES_CN = (
'苹果', '水族馆鱼', '婴儿', '熊', '河狸', '床', '蜜蜂', '甲虫', '自行车', '瓶子', '碗', '小男孩',
'桥', '公共汽车', '蝴蝶', '骆驼', '易拉罐', '城堡', '毛毛虫', '牛', '椅子', '猩猩', '钟', '白云',
'蟑螂', '沙发', '螃蟹', '鳄鱼', '杯子', '恐龙', '海豚', '大象', '比目鱼', '森林', '狐狸', '小女孩',
'仓鼠', '屋子', '袋鼠', '键盘', '台灯', '割草机', '猎豹', '狮子', '蜥蜴', '龙虾', '男人', '枫树',
'摩托车', '山', '老鼠', '蘑菇', '橡树', '橙子橘子', '兰花', '水獭', '棕榈树', '梨', '皮卡车', '松树',
'田野', '盘子', '罂粟', '豪猪', '负鼠', '兔子', '浣熊', '鳐鱼', '公路', '火箭', '玫瑰', '大海',
'海豹', '鲨鱼', '尖嘴小鼠', '臭鼬', '摩天大楼', '蜗牛', '蛇', '蜘蛛', '松鼠', '电车', '向日葵', '甜椒',
'桌子', '坦克', '电话', '电视', '老虎', '拖拉机', '火车', '鳟鱼', '郁金香', '乌龟', '衣柜', '鲸鱼',
'柳树', '狼', '女人', '蠕虫')
IMAGENET_SIMPLE_CATEGORIES = (
'tench', 'goldfish', 'great white shark', 'tiger shark',
'hammerhead shark', 'electric ray', 'stingray', 'rooster', 'hen',
'ostrich', 'brambling', 'goldfinch', 'house finch', 'junco',
'indigo bunting', 'American robin', 'bulbul', 'jay', 'magpie', 'chickadee',
'American dipper', 'kite (bird of prey)', 'bald eagle', 'vulture',
'great grey owl', 'fire salamander', 'smooth newt', 'newt',
'spotted salamander', 'axolotl', 'American bullfrog', 'tree frog',
'tailed frog', 'loggerhead sea turtle', 'leatherback sea turtle',
'mud turtle', 'terrapin', 'box turtle', 'banded gecko', 'green iguana',
'Carolina anole', 'desert grassland whiptail lizard', 'agama',
'frilled-necked lizard', 'alligator lizard', 'Gila monster',
'European green lizard', 'chameleon', 'Komodo dragon', 'Nile crocodile',
'American alligator', 'triceratops', 'worm snake', 'ring-necked snake',
'eastern hog-nosed snake', 'smooth green snake', 'kingsnake',
'garter snake', 'water snake', 'vine snake', 'night snake',
'boa constrictor', 'African rock python', 'Indian cobra', 'green mamba',
'sea snake', 'Saharan horned viper', 'eastern diamondback rattlesnake',
'sidewinder rattlesnake', 'trilobite', 'harvestman', 'scorpion',
'yellow garden spider', 'barn spider', 'European garden spider',
'southern black widow', 'tarantula', 'wolf spider', 'tick', 'centipede',
'black grouse', 'ptarmigan', 'ruffed grouse', 'prairie grouse', 'peafowl',
'quail', 'partridge', 'african grey parrot', 'macaw',
'sulphur-crested cockatoo', 'lorikeet', 'coucal', 'bee eater', 'hornbill',
'hummingbird', 'jacamar', 'toucan', 'duck', 'red-breasted merganser',
'goose', 'black swan', 'tusker', 'echidna', 'platypus', 'wallaby', 'koala',
'wombat', 'jellyfish', 'sea anemone', 'brain coral', 'flatworm',
'nematode', 'conch', 'snail', 'slug', 'sea slug', 'chiton',
'chambered nautilus', 'Dungeness crab', 'rock crab', 'fiddler crab',
'red king crab', 'American lobster', 'spiny lobster', 'crayfish',
'hermit crab', 'isopod', 'white stork', 'black stork', 'spoonbill',
'flamingo', 'little blue heron', 'great egret', 'bittern bird',
'crane bird', 'limpkin', 'common gallinule', 'American coot', 'bustard',
'ruddy turnstone', 'dunlin', 'common redshank', 'dowitcher',
'oystercatcher', 'pelican', 'king penguin', 'albatross', 'grey whale',
'killer whale', 'dugong', 'sea lion', 'Chihuahua', 'Japanese Chin',
'Maltese', 'Pekingese', 'Shih Tzu', 'King Charles Spaniel', 'Papillon',
'toy terrier', 'Rhodesian Ridgeback', 'Afghan Hound', 'Basset Hound',
'Beagle', 'Bloodhound', 'Bluetick Coonhound', 'Black and Tan Coonhound',
'Treeing Walker Coonhound', 'English foxhound', 'Redbone Coonhound',
'borzoi', 'Irish Wolfhound', 'Italian Greyhound', 'Whippet',
'Ibizan Hound', 'Norwegian Elkhound', 'Otterhound', 'Saluki',
'Scottish Deerhound', 'Weimaraner', 'Staffordshire Bull Terrier',
'American Staffordshire Terrier', 'Bedlington Terrier', 'Border Terrier',
'Kerry Blue Terrier', 'Irish Terrier', 'Norfolk Terrier',
'Norwich Terrier', 'Yorkshire Terrier', 'Wire Fox Terrier',
'Lakeland Terrier', 'Sealyham Terrier', 'Airedale Terrier',
'Cairn Terrier', 'Australian Terrier', 'Dandie Dinmont Terrier',
'Boston Terrier', 'Miniature Schnauzer', 'Giant Schnauzer',
'Standard Schnauzer', 'Scottish Terrier', 'Tibetan Terrier',
'Australian Silky Terrier', 'Soft-coated Wheaten Terrier',
'West Highland White Terrier', 'Lhasa Apso', 'Flat-Coated Retriever',
'Curly-coated Retriever', 'Golden Retriever', 'Labrador Retriever',
'Chesapeake Bay Retriever', 'German Shorthaired Pointer', 'Vizsla',
'English Setter', 'Irish Setter', 'Gordon Setter', 'Brittany dog',
'Clumber Spaniel', 'English Springer Spaniel', 'Welsh Springer Spaniel',
'Cocker Spaniel', 'Sussex Spaniel', 'Irish Water Spaniel', 'Kuvasz',
'Schipperke', 'Groenendael dog', 'Malinois', 'Briard', 'Australian Kelpie',
'Komondor', 'Old English Sheepdog', 'Shetland Sheepdog', 'collie',
'Border Collie', 'Bouvier des Flandres dog', 'Rottweiler',
'German Shepherd Dog', 'Dobermann', 'Miniature Pinscher',
'Greater Swiss Mountain Dog', 'Bernese Mountain Dog',
'Appenzeller Sennenhund', 'Entlebucher Sennenhund', 'Boxer', 'Bullmastiff',
'Tibetan Mastiff', 'French Bulldog', 'Great Dane', 'St. Bernard', 'husky',
'Alaskan Malamute', 'Siberian Husky', 'Dalmatian', 'Affenpinscher',
'Basenji', 'pug', 'Leonberger', 'Newfoundland dog', 'Great Pyrenees dog',
'Samoyed', 'Pomeranian', 'Chow Chow', 'Keeshond', 'brussels griffon',
'Pembroke Welsh Corgi', 'Cardigan Welsh Corgi', 'Toy Poodle',
'Miniature Poodle', 'Standard Poodle',
'Mexican hairless dog (xoloitzcuintli)', 'grey wolf',
'Alaskan tundra wolf', 'red wolf or maned wolf', 'coyote', 'dingo',
'dhole', 'African wild dog', 'hyena', 'red fox', 'kit fox', 'Arctic fox',
'grey fox', 'tabby cat', 'tiger cat', 'Persian cat', 'Siamese cat',
'Egyptian Mau', 'cougar', 'lynx', 'leopard', 'snow leopard', 'jaguar',
'lion', 'tiger', 'cheetah', 'brown bear', 'American black bear',
'polar bear', 'sloth bear', 'mongoose', 'meerkat', 'tiger beetle',
'ladybug', 'ground beetle', 'longhorn beetle', 'leaf beetle',
'dung beetle', 'rhinoceros beetle', 'weevil', 'fly', 'bee', 'ant',
'grasshopper', 'cricket insect', 'stick insect', 'cockroach',
'praying mantis', 'cicada', 'leafhopper', 'lacewing', 'dragonfly',
'damselfly', 'red admiral butterfly', 'ringlet butterfly',
'monarch butterfly', 'small white butterfly', 'sulphur butterfly',
'gossamer-winged butterfly', 'starfish', 'sea urchin', 'sea cucumber',
'cottontail rabbit', 'hare', 'Angora rabbit', 'hamster', 'porcupine',
'fox squirrel', 'marmot', 'beaver', 'guinea pig', 'common sorrel horse',
'zebra', 'pig', 'wild boar', 'warthog', 'hippopotamus', 'ox',
'water buffalo', 'bison', 'ram (adult male sheep)', 'bighorn sheep',
'Alpine ibex', 'hartebeest', 'impala (antelope)', 'gazelle',
'arabian camel', 'llama', 'weasel', 'mink', 'European polecat',
'black-footed ferret', 'otter', 'skunk', 'badger', 'armadillo',
'three-toed sloth', 'orangutan', 'gorilla', 'chimpanzee', 'gibbon',
'siamang', 'guenon', 'patas monkey', 'baboon', 'macaque', 'langur',
'black-and-white colobus', 'proboscis monkey', 'marmoset',
'white-headed capuchin', 'howler monkey', 'titi monkey',
"Geoffroy's spider monkey", 'common squirrel monkey', 'ring-tailed lemur',
'indri', 'Asian elephant', 'African bush elephant', 'red panda',
'giant panda', 'snoek fish', 'eel', 'silver salmon', 'rock beauty fish',
'clownfish', 'sturgeon', 'gar fish', 'lionfish', 'pufferfish', 'abacus',
'abaya', 'academic gown', 'accordion', 'acoustic guitar',
'aircraft carrier', 'airliner', 'airship', 'altar', 'ambulance',
'amphibious vehicle', 'analog clock', 'apiary', 'apron', 'trash can',
'assault rifle', 'backpack', 'bakery', 'balance beam', 'balloon',
'ballpoint pen', 'Band-Aid', 'banjo', 'baluster / handrail', 'barbell',
'barber chair', 'barbershop', 'barn', 'barometer', 'barrel', 'wheelbarrow',
'baseball', 'basketball', 'bassinet', 'bassoon', 'swimming cap',
'bath towel', 'bathtub', 'station wagon', 'lighthouse', 'beaker',
'military hat (bearskin or shako)', 'beer bottle', 'beer glass',
'bell tower', 'baby bib', 'tandem bicycle', 'bikini', 'ring binder',
'binoculars', 'birdhouse', 'boathouse', 'bobsleigh', 'bolo tie',
'poke bonnet', 'bookcase', 'bookstore', 'bottle cap', 'hunting bow',
'bow tie', 'brass memorial plaque', 'bra', 'breakwater', 'breastplate',
'broom', 'bucket', 'buckle', 'bulletproof vest', 'high-speed train',
'butcher shop', 'taxicab', 'cauldron', 'candle', 'cannon', 'canoe',
'can opener', 'cardigan', 'car mirror', 'carousel', 'tool kit',
'cardboard box / carton', 'car wheel', 'automated teller machine',
'cassette', 'cassette player', 'castle', 'catamaran', 'CD player', 'cello',
'mobile phone', 'chain', 'chain-link fence', 'chain mail', 'chainsaw',
'storage chest', 'chiffonier', 'bell or wind chime', 'china cabinet',
'Christmas stocking', 'church', 'movie theater', 'cleaver',
'cliff dwelling', 'cloak', 'clogs', 'cocktail shaker', 'coffee mug',
'coffeemaker', 'spiral or coil', 'combination lock', 'computer keyboard',
'candy store', 'container ship', 'convertible', 'corkscrew', 'cornet',
'cowboy boot', 'cowboy hat', 'cradle', 'construction crane',
'crash helmet', 'crate', 'infant bed', 'Crock Pot', 'croquet ball',
'crutch', 'cuirass', 'dam', 'desk', 'desktop computer',
'rotary dial telephone', 'diaper', 'digital clock', 'digital watch',
'dining table', 'dishcloth', 'dishwasher', 'disc brake', 'dock',
'dog sled', 'dome', 'doormat', 'drilling rig', 'drum', 'drumstick',
'dumbbell', 'Dutch oven', 'electric fan', 'electric guitar',
'electric locomotive', 'entertainment center', 'envelope',
'espresso machine', 'face powder', 'feather boa', 'filing cabinet',
'fireboat', 'fire truck', 'fire screen', 'flagpole', 'flute',
'folding chair', 'football helmet', 'forklift', 'fountain', 'fountain pen',
'four-poster bed', 'freight car', 'French horn', 'frying pan', 'fur coat',
'garbage truck', 'gas mask or respirator', 'gas pump', 'goblet', 'go-kart',
'golf ball', 'golf cart', 'gondola', 'gong', 'gown', 'grand piano',
'greenhouse', 'radiator grille', 'grocery store', 'guillotine',
'hair clip', 'hair spray', 'half-track', 'hammer', 'hamper', 'hair dryer',
'hand-held computer', 'handkerchief', 'hard disk drive', 'harmonica',
'harp', 'combine harvester', 'hatchet', 'holster', 'home theater',
'honeycomb', 'hook', 'hoop skirt', 'gymnastic horizontal bar',
'horse-drawn vehicle', 'hourglass', 'iPod', 'clothes iron',
'carved pumpkin', 'jeans', 'jeep', 'T-shirt', 'jigsaw puzzle', 'rickshaw',
'joystick', 'kimono', 'knee pad', 'knot', 'lab coat', 'ladle', 'lampshade',
'laptop computer', 'lawn mower', 'lens cap', 'letter opener', 'library',
'lifeboat', 'lighter', 'limousine', 'ocean liner', 'lipstick',
'slip-on shoe', 'lotion', 'music speaker', 'loupe magnifying glass',
'sawmill', 'magnetic compass', 'messenger bag', 'mailbox', 'tights',
'one-piece bathing suit', 'manhole cover', 'maraca', 'marimba', 'mask',
'matchstick', 'maypole', 'maze', 'measuring cup', 'medicine cabinet',
'megalith', 'microphone', 'microwave oven', 'military uniform', 'milk can',
'minibus', 'miniskirt', 'minivan', 'missile', 'mitten', 'mixing bowl',
'mobile home', 'ford model t', 'modem', 'monastery', 'monitor', 'moped',
'mortar and pestle', 'graduation cap', 'mosque', 'mosquito net', 'vespa',
'mountain bike', 'tent', 'computer mouse', 'mousetrap', 'moving van',
'muzzle', 'metal nail', 'neck brace', 'necklace', 'baby pacifier',
'notebook computer', 'obelisk', 'oboe', 'ocarina', 'odometer',
'oil filter', 'pipe organ', 'oscilloscope', 'overskirt', 'bullock cart',
'oxygen mask', 'product packet / packaging', 'paddle', 'paddle wheel',
'padlock', 'paintbrush', 'pajamas', 'palace', 'pan flute', 'paper towel',
'parachute', 'parallel bars', 'park bench', 'parking meter',
'railroad car', 'patio', 'payphone', 'pedestal', 'pencil case',
'pencil sharpener', 'perfume', 'Petri dish', 'photocopier', 'plectrum',
'Pickelhaube', 'picket fence', 'pickup truck', 'pier', 'piggy bank',
'pill bottle', 'pillow', 'ping-pong ball', 'pinwheel', 'pirate ship',
'drink pitcher', 'block plane', 'planetarium', 'plastic bag', 'plate rack',
'farm plow', 'plunger', 'Polaroid camera', 'pole', 'police van', 'poncho',
'pool table', 'soda bottle', 'plant pot', "potter's wheel", 'power drill',
'prayer rug', 'printer', 'prison', 'missile', 'projector', 'hockey puck',
'punching bag', 'purse', 'quill', 'quilt', 'race car', 'racket',
'radiator', 'radio', 'radio telescope', 'rain barrel',
'recreational vehicle', 'fishing casting reel', 'reflex camera',
'refrigerator', 'remote control', 'restaurant', 'revolver', 'rifle',
'rocking chair', 'rotisserie', 'eraser', 'rugby ball',
'ruler measuring stick', 'sneaker', 'safe', 'safety pin', 'salt shaker',
'sandal', 'sarong', 'saxophone', 'scabbard', 'weighing scale',
'school bus', 'schooner', 'scoreboard', 'CRT monitor', 'screw',
'screwdriver', 'seat belt', 'sewing machine', 'shield', 'shoe store',
'shoji screen / room divider', 'shopping basket', 'shopping cart',
'shovel', 'shower cap', 'shower curtain', 'ski', 'balaclava ski mask',
'sleeping bag', 'slide rule', 'sliding door', 'slot machine', 'snorkel',
'snowmobile', 'snowplow', 'soap dispenser', 'soccer ball', 'sock',
'solar thermal collector', 'sombrero', 'soup bowl', 'keyboard space bar',
'space heater', 'space shuttle', 'spatula', 'motorboat', 'spider web',
'spindle', 'sports car', 'spotlight', 'stage', 'steam locomotive',
'through arch bridge', 'steel drum', 'stethoscope', 'scarf', 'stone wall',
'stopwatch', 'stove', 'strainer', 'tram', 'stretcher', 'couch', 'stupa',
'submarine', 'suit', 'sundial', 'sunglasses', 'sunglasses', 'sunscreen',
'suspension bridge', 'mop', 'sweatshirt', 'swim trunks / shorts', 'swing',
'electrical switch', 'syringe', 'table lamp', 'tank', 'tape player',
'teapot', 'teddy bear', 'television', 'tennis ball', 'thatched roof',
'front curtain', 'thimble', 'threshing machine', 'throne', 'tile roof',
'toaster', 'tobacco shop', 'toilet seat', 'torch', 'totem pole',
'tow truck', 'toy store', 'tractor', 'semi-trailer truck', 'tray',
'trench coat', 'tricycle', 'trimaran', 'tripod', 'triumphal arch',
'trolleybus', 'trombone', 'hot tub', 'turnstile', 'typewriter keyboard',
'umbrella', 'unicycle', 'upright piano', 'vacuum cleaner', 'vase',
'vaulted or arched ceiling', 'velvet fabric', 'vending machine',
'vestment', 'viaduct', 'violin', 'volleyball', 'waffle iron', 'wall clock',
'wallet', 'wardrobe', 'military aircraft', 'sink', 'washing machine',
'water bottle', 'water jug', 'water tower', 'whiskey jug', 'whistle',
'hair wig', 'window screen', 'window shade', 'Windsor tie', 'wine bottle',
'airplane wing', 'wok', 'wooden spoon', 'wool', 'split-rail fence',
'shipwreck', 'sailboat', 'yurt', 'website', 'comic book', 'crossword',
'traffic or street sign', 'traffic light', 'dust jacket', 'menu', 'plate',
'guacamole', 'consomme', 'hot pot', 'trifle', 'ice cream', 'popsicle',
'baguette', 'bagel', 'pretzel', 'cheeseburger', 'hot dog',
'mashed potatoes', 'cabbage', 'broccoli', 'cauliflower', 'zucchini',
'spaghetti squash', 'acorn squash', 'butternut squash', 'cucumber',
'artichoke', 'bell pepper', 'cardoon', 'mushroom', 'Granny Smith apple',
'strawberry', 'orange', 'lemon', 'fig', 'pineapple', 'banana', 'jackfruit',
'cherimoya (custard apple)', 'pomegranate', 'hay', 'carbonara',
'chocolate syrup', 'dough', 'meatloaf', 'pizza', 'pot pie', 'burrito',
'red wine', 'espresso', 'tea cup', 'eggnog', 'mountain', 'bubble', 'cliff',
'coral reef', 'geyser', 'lakeshore', 'promontory', 'sandbar', 'beach',
'valley', 'volcano', 'baseball player', 'bridegroom', 'scuba diver',
'rapeseed', 'daisy', "yellow lady's slipper", 'corn', 'acorn', 'rose hip',
'horse chestnut seed', 'coral fungus', 'agaric', 'gyromitra',
'stinkhorn mushroom', 'earth star fungus', 'hen of the woods mushroom',
'bolete', 'corn cob', 'toilet paper')
mmpretrain/datasets/cifar.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
import pickle
from typing import List, Optional
import mmengine.dist as dist
import numpy as np
from mmengine.fileio import (LocalBackend, exists, get, get_file_backend,
join_path)
from mmengine.logging import MMLogger
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
from .categories import CIFAR10_CATEGORIES, CIFAR100_CATEGORIES
from .utils import check_md5, download_and_extract_archive
@DATASETS.register_module()
class CIFAR10(BaseDataset):
"""`CIFAR10 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.
This implementation is modified from
https://github.com/pytorch/vision/blob/master/torchvision/datasets/cifar.py
Args:
data_root (str): The root directory of the CIFAR Dataset.
split (str, optional): The dataset split, supports "train" and "test".
Default to "train".
metainfo (dict, optional): Meta information for dataset, such as
categories information. Defaults to None.
download (bool): Whether to download the dataset if not exists.
Defaults to True.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
""" # noqa: E501
base_folder = 'cifar-10-batches-py'
url = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
filename = 'cifar-10-python.tar.gz'
tgz_md5 = 'c58f30108f718f92721af3b95e74349a'
train_list = [
['data_batch_1', 'c99cafc152244af753f735de768cd75f'],
['data_batch_2', 'd4bba439e000b95fd0a9bffe97cbabec'],
['data_batch_3', '54ebc095f3ab1f0389bbae665268c751'],
['data_batch_4', '634d18415352ddfa80567beed471001a'],
['data_batch_5', '482c414d41f54cd18b22e5b47cb7c3cb'],
]
test_list = [
['test_batch', '40351d587109b95175f43aff81a1287e'],
]
meta = {
'filename': 'batches.meta',
'key': 'label_names',
'md5': '5ff9c542aee3614f3951f8cda6e48888',
}
METAINFO = {'classes': CIFAR10_CATEGORIES}
def __init__(self,
data_root: str = '',
split: str = 'train',
metainfo: Optional[dict] = None,
download: bool = True,
data_prefix: str = '',
test_mode: bool = False,
**kwargs):
splits = ['train', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
self.split = split
# To handle the BC-breaking
if split == 'train' and test_mode:
logger = MMLogger.get_current_instance()
logger.warning('split="train" but test_mode=True. '
'The training set will be used.')
if not data_root and not data_prefix:
raise RuntimeError('Please set ``data_root`` to'
'specify the dataset path')
self.download = download
super().__init__(
# The CIFAR dataset doesn't need specify annotation file
ann_file='',
metainfo=metainfo,
data_root=data_root,
data_prefix=dict(root=data_prefix),
test_mode=test_mode,
**kwargs)
def load_data_list(self):
"""Load images and ground truth labels."""
root = self.data_prefix['root']
backend = get_file_backend(root, enable_singleton=True)
if dist.is_main_process() and not self._check_integrity():
if not isinstance(backend, LocalBackend):
raise RuntimeError(f'The dataset on {root} is not integrated, '
f'please manually handle it.')
if self.download:
download_and_extract_archive(
self.url, root, filename=self.filename, md5=self.tgz_md5)
else:
raise RuntimeError(
f'Cannot find {self.__class__.__name__} dataset in '
f"{self.data_prefix['root']}, you can specify "
'`download=True` to download automatically.')
dist.barrier()
assert self._check_integrity(), \
'Download failed or shared storage is unavailable. Please ' \
f'download the dataset manually through {self.url}.'
if self.split == 'train':
downloaded_list = self.train_list
else:
downloaded_list = self.test_list
imgs = []
gt_labels = []
# load the picked numpy arrays
for file_name, _ in downloaded_list:
file_path = join_path(root, self.base_folder, file_name)
entry = pickle.loads(get(file_path), encoding='latin1')
imgs.append(entry['data'])
if 'labels' in entry:
gt_labels.extend(entry['labels'])
else:
gt_labels.extend(entry['fine_labels'])
imgs = np.vstack(imgs).reshape(-1, 3, 32, 32)
imgs = imgs.transpose((0, 2, 3, 1)) # convert to HWC
if self.CLASSES is None:
# The metainfo in the file has the lowest priority, therefore
# we only need to load it if classes is not specified.
self._load_meta()
data_list = []
for img, gt_label in zip(imgs, gt_labels):
info = {'img': img, 'gt_label': int(gt_label)}
data_list.append(info)
return data_list
def _load_meta(self):
"""Load categories information from metafile."""
root = self.data_prefix['root']
path = join_path(root, self.base_folder, self.meta['filename'])
md5 = self.meta.get('md5', None)
if not exists(path) or (md5 is not None and not check_md5(path, md5)):
raise RuntimeError(
'Dataset metadata file not found or corrupted.' +
' You can use `download=True` to download it')
data = pickle.loads(get(path), encoding='latin1')
self._metainfo.setdefault('classes', data[self.meta['key']])
def _check_integrity(self):
"""Check the integrity of data files."""
root = self.data_prefix['root']
for fentry in (self.train_list + self.test_list):
filename, md5 = fentry[0], fentry[1]
fpath = join_path(root, self.base_folder, filename)
if not exists(fpath):
return False
if md5 is not None and not check_md5(fpath, md5):
return False
return True
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [f"Prefix of data: \t{self.data_prefix['root']}"]
return body
@DATASETS.register_module()
class CIFAR100(CIFAR10):
"""`CIFAR100 <https://www.cs.toronto.edu/~kriz/cifar.html>`_ Dataset.
Args:
data_root (str): The root directory of the CIFAR Dataset.
split (str, optional): The dataset split, supports "train" and "test".
Default to "train".
metainfo (dict, optional): Meta information for dataset, such as
categories information. Defaults to None.
download (bool): Whether to download the dataset if not exists.
Defaults to True.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
base_folder = 'cifar-100-python'
url = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
filename = 'cifar-100-python.tar.gz'
tgz_md5 = 'eb9058c3a382ffc7106e4002c42a8d85'
train_list = [
['train', '16019d7e3df5f24257cddd939b257f8d'],
]
test_list = [
['test', 'f0ef6b0ae62326f3e7ffdfab6717acfc'],
]
meta = {
'filename': 'meta',
'key': 'fine_label_names',
'md5': '7973b15100ade9c7d40fb424638fde48',
}
METAINFO = {'classes': CIFAR100_CATEGORIES}
mmpretrain/datasets/coco_caption.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from pathlib import Path
from typing import List
import mmengine
from mmengine.dataset import BaseDataset
from mmengine.fileio import get_file_backend
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class COCOCaption(BaseDataset):
"""COCO Caption dataset.
Args:
data_root (str): The root directory for ``data_prefix`` and
``ann_file``..
ann_file (str): Annotation file path.
data_prefix (dict): Prefix for data field. Defaults to
``dict(img_path='')``.
pipeline (Sequence): Processing pipeline. Defaults to an empty tuple.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def load_data_list(self) -> List[dict]:
"""Load data list."""
img_prefix = self.data_prefix['img_path']
annotations = mmengine.load(self.ann_file)
file_backend = get_file_backend(img_prefix)
data_list = []
for ann in annotations:
data_info = {
'image_id': Path(ann['image']).stem.split('_')[-1],
'img_path': file_backend.join_path(img_prefix, ann['image']),
'gt_caption': ann['caption'],
}
data_list.append(data_info)
return data_list
mmpretrain/datasets/coco_retrieval.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
import json
import os.path as osp
from collections import OrderedDict
from os import PathLike
from typing import List, Sequence, Union
from mmengine import get_file_backend
from mmpretrain.registry import DATASETS, TRANSFORMS
from .base_dataset import BaseDataset
def expanduser(data_prefix):
if isinstance(data_prefix, (str, PathLike)):
return osp.expanduser(data_prefix)
else:
return data_prefix
@DATASETS.register_module()
class COCORetrieval(BaseDataset):
"""COCO Retrieval dataset.
COCO (Common Objects in Context): The COCO dataset contains more than
330K images,each of which has approximately 5 descriptive annotations.
This dataset was releasedin collaboration between Microsoft and Carnegie
Mellon University
COCO_2014 dataset directory: ::
COCO_2014
├── val2014
├── train2014
├── annotations
├── instances_train2014.json
├── instances_val2014.json
├── person_keypoints_train2014.json
├── person_keypoints_val2014.json
├── captions_train2014.json
├── captions_val2014.json
Args:
ann_file (str): Annotation file path.
test_mode (bool): Whether dataset is used for evaluation. This will
decide the annotation format in data list annotations.
Defaults to False.
data_root (str): The root directory for ``data_prefix`` and
``ann_file``. Defaults to ''.
data_prefix (str | dict): Prefix for training data. Defaults to ''.
pipeline (Sequence): Processing pipeline. Defaults to an empty tuple.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
Examples:
>>> from mmpretrain.datasets import COCORetrieval
>>> train_dataset=COCORetrieval(data_root='coco2014/')
>>> train_dataset
Dataset COCORetrieval
Number of samples: 414113
Annotation file: /coco2014/annotations/captions_train2014.json
Prefix of images: /coco2014/
>>> from mmpretrain.datasets import COCORetrieval
>>> val_dataset = COCORetrieval(data_root='coco2014/')
>>> val_dataset
Dataset COCORetrieval
Number of samples: 202654
Annotation file: /coco2014/annotations/captions_val2014.json
Prefix of images: /coco2014/
"""
def __init__(self,
ann_file: str,
test_mode: bool = False,
data_prefix: Union[str, dict] = '',
data_root: str = '',
pipeline: Sequence = (),
**kwargs):
if isinstance(data_prefix, str):
data_prefix = dict(img_path=expanduser(data_prefix))
ann_file = expanduser(ann_file)
transforms = []
for transform in pipeline:
if isinstance(transform, dict):
transforms.append(TRANSFORMS.build(transform))
else:
transforms.append(transform)
super().__init__(
data_root=data_root,
data_prefix=data_prefix,
test_mode=test_mode,
pipeline=transforms,
ann_file=ann_file,
**kwargs,
)
def load_data_list(self) -> List[dict]:
"""Load data list."""
# get file backend
img_prefix = self.data_prefix['img_path']
file_backend = get_file_backend(img_prefix)
anno_info = json.load(open(self.ann_file, 'r'))
# mapping img_id to img filename
img_dict = OrderedDict()
for idx, img in enumerate(anno_info['images']):
if img['id'] not in img_dict:
img_rel_path = img['coco_url'].rsplit('/', 2)[-2:]
img_path = file_backend.join_path(img_prefix, *img_rel_path)
# create new idx for image
img_dict[img['id']] = dict(
ori_id=img['id'],
image_id=idx, # will be used for evaluation
img_path=img_path,
text=[],
gt_text_id=[],
gt_image_id=[],
)
train_list = []
for idx, anno in enumerate(anno_info['annotations']):
anno['text'] = anno.pop('caption')
anno['ori_id'] = anno.pop('id')
anno['text_id'] = idx # will be used for evaluation
# 1. prepare train data list item
train_data = anno.copy()
train_image = img_dict[train_data['image_id']]
train_data['img_path'] = train_image['img_path']
train_data['image_ori_id'] = train_image['ori_id']
train_data['image_id'] = train_image['image_id']
train_data['is_matched'] = True
train_list.append(train_data)
# 2. prepare eval data list item based on img dict
img_dict[anno['image_id']]['gt_text_id'].append(anno['text_id'])
img_dict[anno['image_id']]['text'].append(anno['text'])
img_dict[anno['image_id']]['gt_image_id'].append(
train_image['image_id'])
self.img_size = len(img_dict)
self.text_size = len(anno_info['annotations'])
# return needed format data list
if self.test_mode:
return list(img_dict.values())
return train_list
mmpretrain/datasets/coco_vqa.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp
import re
from collections import Counter
from typing import List
import mmengine
from mmengine.dataset import BaseDataset
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class COCOVQA(BaseDataset):
"""VQAv2 dataset.
Args:
data_root (str): The root directory for ``data_prefix``, ``ann_file``
and ``question_file``.
data_prefix (str): The directory of images.
question_file (str): Question file path.
ann_file (str, optional): Annotation file path for training and
validation. Defaults to an empty string.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
data_root: str,
data_prefix: str,
question_file: str,
ann_file: str = '',
**kwarg):
self.question_file = question_file
super().__init__(
data_root=data_root,
data_prefix=dict(img_path=data_prefix),
ann_file=ann_file,
**kwarg,
)
def _join_prefix(self):
if not mmengine.is_abs(self.question_file) and self.question_file:
self.question_file = osp.join(self.data_root, self.question_file)
return super()._join_prefix()
def _create_image_index(self):
img_prefix = self.data_prefix['img_path']
files = mmengine.list_dir_or_file(img_prefix, list_dir=False)
image_index = {}
for file in files:
image_id = re.findall(r'\d{12}', file)
if len(image_id) > 0:
image_id = int(image_id[-1])
image_index[image_id] = mmengine.join_path(img_prefix, file)
return image_index
def load_data_list(self) -> List[dict]:
"""Load data list."""
questions = mmengine.load(self.question_file)['questions']
if self.ann_file:
annotations = mmengine.load(self.ann_file)['annotations']
assert len(questions) == len(annotations)
else:
annotations = [None] * len(questions)
# The original VQAv2 annotation file and question file includes
# only image id but no image file paths.
self.image_index = self._create_image_index()
data_list = []
for question, ann in zip(questions, annotations):
# question example
# {
# 'image_id': 262144,
# 'question': "Is the ball flying towards the batter?",
# 'question_id': 262144000
# }
#
# ann example
# {
# 'question_type': "what are the",
# 'answer_type': "other",
# 'answers': [
# {'answer': 'watching',
# 'answer_id': 1,
# 'answer_confidence': 'yes'},
# ...
# ],
# 'image_id': 262148,
# 'question_id': 262148000,
# 'multiple_choice_answer': 'watching',
# 'answer_type': 'other',
# }
data_info = question
data_info['img_path'] = self.image_index[question['image_id']]
if ann is not None:
assert ann['question_id'] == question['question_id']
# add answer_weight & answer_count, delete duplicate answer
answers = [item['answer'] for item in ann.pop('answers')]
count = Counter(answers)
answer_weight = [i / len(answers) for i in count.values()]
data_info['gt_answer'] = list(count.keys())
data_info['gt_answer_weight'] = answer_weight
data_info.update(ann)
data_list.append(data_info)
return data_list
mmpretrain/datasets/cub.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
from mmengine import get_file_backend, list_from_file
from mmengine.logging import MMLogger
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
from .categories import CUB_CATEGORIES
@DATASETS.register_module()
class CUB(BaseDataset):
"""The CUB-200-2011 Dataset.
Support the `CUB-200-2011 <http://www.vision.caltech.edu/visipedia/CUB-200-2011.html>`_ Dataset.
Comparing with the `CUB-200 <http://www.vision.caltech.edu/visipedia/CUB-200.html>`_ Dataset,
there are much more pictures in `CUB-200-2011`. After downloading and decompression, the dataset
directory structure is as follows.
CUB dataset directory: ::
CUB_200_2011
├── images
│ ├── class_x
│ │ ├── xx1.jpg
│ │ ├── xx2.jpg
│ │ └── ...
│ ├── class_y
│ │ ├── yy1.jpg
│ │ ├── yy2.jpg
│ │ └── ...
│ └── ...
├── images.txt
├── image_class_labels.txt
├── train_test_split.txt
└── ....
Args:
data_root (str): The root directory for CUB-200-2011 dataset.
split (str, optional): The dataset split, supports "train" and "test".
Default to "train".
Examples:
>>> from mmpretrain.datasets import CUB
>>> train_dataset = CUB(data_root='data/CUB_200_2011', split='train')
>>> train_dataset
Dataset CUB
Number of samples: 5994
Number of categories: 200
Root of dataset: data/CUB_200_2011
>>> test_dataset = CUB(data_root='data/CUB_200_2011', split='test')
>>> test_dataset
Dataset CUB
Number of samples: 5794
Number of categories: 200
Root of dataset: data/CUB_200_2011
""" # noqa: E501
METAINFO = {'classes': CUB_CATEGORIES}
def __init__(self,
data_root: str,
split: str = 'train',
test_mode: bool = False,
**kwargs):
splits = ['train', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
self.split = split
# To handle the BC-breaking
if split == 'train' and test_mode:
logger = MMLogger.get_current_instance()
logger.warning('split="train" but test_mode=True. '
'The training set will be used.')
ann_file = 'images.txt'
data_prefix = 'images'
image_class_labels_file = 'image_class_labels.txt'
train_test_split_file = 'train_test_split.txt'
self.backend = get_file_backend(data_root, enable_singleton=True)
self.image_class_labels_file = self.backend.join_path(
data_root, image_class_labels_file)
self.train_test_split_file = self.backend.join_path(
data_root, train_test_split_file)
super(CUB, self).__init__(
ann_file=ann_file,
data_root=data_root,
data_prefix=data_prefix,
test_mode=test_mode,
**kwargs)
def _load_data_from_txt(self, filepath):
"""load data from CUB txt file, the every line of the file is idx and a
data item."""
pairs = list_from_file(filepath)
data_dict = dict()
for pair in pairs:
idx, data_item = pair.split()
# all the index starts from 1 in CUB files,
# here we need to '- 1' to let them start from 0.
data_dict[int(idx) - 1] = data_item
return data_dict
def load_data_list(self):
"""Load images and ground truth labels."""
sample_dict = self._load_data_from_txt(self.ann_file)
label_dict = self._load_data_from_txt(self.image_class_labels_file)
split_dict = self._load_data_from_txt(self.train_test_split_file)
assert sample_dict.keys() == label_dict.keys() == split_dict.keys(),\
f'sample_ids should be same in files {self.ann_file}, ' \
f'{self.image_class_labels_file} and {self.train_test_split_file}'
data_list = []
for sample_id in sample_dict.keys():
if split_dict[sample_id] == '1' and self.split == 'test':
# skip train samples when split='test'
continue
elif split_dict[sample_id] == '0' and self.split == 'train':
# skip test samples when split='train'
continue
img_path = self.backend.join_path(self.img_prefix,
sample_dict[sample_id])
gt_label = int(label_dict[sample_id]) - 1
info = dict(img_path=img_path, gt_label=gt_label)
data_list.append(info)
return data_list
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [
f'Root of dataset: \t{self.data_root}',
]
return body
mmpretrain/datasets/custom.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import Callable, Dict, List, Optional, Sequence, Tuple, Union
from mmengine.fileio import (BaseStorageBackend, get_file_backend,
list_from_file)
from mmengine.logging import MMLogger
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
def find_folders(
root: str,
backend: Optional[BaseStorageBackend] = None
) -> Tuple[List[str], Dict[str, int]]:
"""Find classes by folders under a root.
Args:
root (string): root directory of folders
backend (BaseStorageBackend | None): The file backend of the root.
If None, auto infer backend from the root path. Defaults to None.
Returns:
Tuple[List[str], Dict[str, int]]:
- folders: The name of sub folders under the root.
- folder_to_idx: The map from folder name to class idx.
"""
# Pre-build file backend to prevent verbose file backend inference.
backend = backend or get_file_backend(root, enable_singleton=True)
folders = list(
backend.list_dir_or_file(
root,
list_dir=True,
list_file=False,
recursive=False,
))
folders.sort()
folder_to_idx = {folders[i]: i for i in range(len(folders))}
return folders, folder_to_idx
def get_samples(
root: str,
folder_to_idx: Dict[str, int],
is_valid_file: Callable,
backend: Optional[BaseStorageBackend] = None,
):
"""Make dataset by walking all images under a root.
Args:
root (string): root directory of folders
folder_to_idx (dict): the map from class name to class idx
is_valid_file (Callable): A function that takes path of a file
and check if the file is a valid sample file.
backend (BaseStorageBackend | None): The file backend of the root.
If None, auto infer backend from the root path. Defaults to None.
Returns:
Tuple[list, set]:
- samples: a list of tuple where each element is (image, class_idx)
- empty_folders: The folders don't have any valid files.
"""
samples = []
available_classes = set()
# Pre-build file backend to prevent verbose file backend inference.
backend = backend or get_file_backend(root, enable_singleton=True)
if folder_to_idx is not None:
for folder_name in sorted(list(folder_to_idx.keys())):
_dir = backend.join_path(root, folder_name)
files = backend.list_dir_or_file(
_dir,
list_dir=False,
list_file=True,
recursive=True,
)
for file in sorted(list(files)):
if is_valid_file(file):
path = backend.join_path(folder_name, file)
item = (path, folder_to_idx[folder_name])
samples.append(item)
available_classes.add(folder_name)
empty_folders = set(folder_to_idx.keys()) - available_classes
else:
files = backend.list_dir_or_file(
root,
list_dir=False,
list_file=True,
recursive=True,
)
samples = [file for file in sorted(list(files)) if is_valid_file(file)]
empty_folders = None
return samples, empty_folders
@DATASETS.register_module()
class CustomDataset(BaseDataset):
"""A generic dataset for multiple tasks.
The dataset supports two kinds of style.
1. Use an annotation file to specify all samples, and each line indicates a
sample:
The annotation file (for ``with_label=True``, supervised tasks.): ::
folder_1/xxx.png 0
folder_1/xxy.png 1
123.png 4
nsdf3.png 3
...
The annotation file (for ``with_label=False``, unsupervised tasks.): ::
folder_1/xxx.png
folder_1/xxy.png
123.png
nsdf3.png
...
Sample files: ::
data_prefix/
├── folder_1
│ ├── xxx.png
│ ├── xxy.png
│ └── ...
├── 123.png
├── nsdf3.png
└── ...
Please use the argument ``metainfo`` to specify extra information for
the task, like ``{'classes': ('bird', 'cat', 'deer', 'dog', 'frog')}``.
2. Place all samples in one folder as below:
Sample files (for ``with_label=True``, supervised tasks, we use the name
of sub-folders as the categories names): ::
data_prefix/
├── class_x
│ ├── xxx.png
│ ├── xxy.png
│ └── ...
│ └── xxz.png
└── class_y
├── 123.png
├── nsdf3.png
├── ...
└── asd932_.png
Sample files (for ``with_label=False``, unsupervised tasks, we use all
sample files under the specified folder): ::
data_prefix/
├── folder_1
│ ├── xxx.png
│ ├── xxy.png
│ └── ...
├── 123.png
├── nsdf3.png
└── ...
If the ``ann_file`` is specified, the dataset will be generated by the
first way, otherwise, try the second way.
Args:
data_root (str): The root directory for ``data_prefix`` and
``ann_file``. Defaults to ''.
data_prefix (str | dict): Prefix for the data. Defaults to ''.
ann_file (str): Annotation file path. Defaults to ''.
with_label (bool): Whether the annotation file includes ground truth
labels, or use sub-folders to specify categories.
Defaults to True.
extensions (Sequence[str]): A sequence of allowed extensions. Defaults
to ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif').
metainfo (dict, optional): Meta information for dataset, such as class
information. Defaults to None.
lazy_init (bool): Whether to load annotation during instantiation.
In some cases, such as visualization, only the meta information of
the dataset is needed, which is not necessary to load annotation
file. ``Basedataset`` can skip load annotations to save time by set
``lazy_init=False``. Defaults to False.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
data_root: str = '',
data_prefix: Union[str, dict] = '',
ann_file: str = '',
with_label=True,
extensions: Sequence[str] = ('.jpg', '.jpeg', '.png', '.ppm',
'.bmp', '.pgm', '.tif'),
metainfo: Optional[dict] = None,
lazy_init: bool = False,
**kwargs):
assert (ann_file or data_prefix or data_root), \
'One of `ann_file`, `data_root` and `data_prefix` must '\
'be specified.'
self.extensions = tuple(set([i.lower() for i in extensions]))
self.with_label = with_label
super().__init__(
# The base class requires string ann_file but this class doesn't
ann_file=ann_file,
metainfo=metainfo,
data_root=data_root,
data_prefix=data_prefix,
# Force to lazy_init for some modification before loading data.
lazy_init=True,
**kwargs)
# Full initialize the dataset.
if not lazy_init:
self.full_init()
def _find_samples(self):
"""find samples from ``data_prefix``."""
if self.with_label:
classes, folder_to_idx = find_folders(self.img_prefix)
samples, empty_classes = get_samples(
self.img_prefix,
folder_to_idx,
is_valid_file=self.is_valid_file,
)
self.folder_to_idx = folder_to_idx
if self.CLASSES is not None:
assert len(self.CLASSES) == len(classes), \
f"The number of subfolders ({len(classes)}) doesn't " \
f'match the number of specified classes ' \
f'({len(self.CLASSES)}). Please check the data folder.'
else:
self._metainfo['classes'] = tuple(classes)
else:
samples, empty_classes = get_samples(
self.img_prefix,
None,
is_valid_file=self.is_valid_file,
)
if len(samples) == 0:
raise RuntimeError(
f'Found 0 files in subfolders of: {self.data_prefix}. '
f'Supported extensions are: {",".join(self.extensions)}')
if empty_classes:
logger = MMLogger.get_current_instance()
logger.warning(
'Found no valid file in the folder '
f'{", ".join(empty_classes)}. '
f"Supported extensions are: {', '.join(self.extensions)}")
return samples
def load_data_list(self):
"""Load image paths and gt_labels."""
if not self.ann_file:
samples = self._find_samples()
elif self.with_label:
lines = list_from_file(self.ann_file)
samples = [x.strip().rsplit(' ', 1) for x in lines]
else:
samples = list_from_file(self.ann_file)
# Pre-build file backend to prevent verbose file backend inference.
backend = get_file_backend(self.img_prefix, enable_singleton=True)
data_list = []
for sample in samples:
if self.with_label:
filename, gt_label = sample
img_path = backend.join_path(self.img_prefix, filename)
info = {'img_path': img_path, 'gt_label': int(gt_label)}
else:
img_path = backend.join_path(self.img_prefix, sample)
info = {'img_path': img_path}
data_list.append(info)
return data_list
def is_valid_file(self, filename: str) -> bool:
"""Check if a file is a valid sample."""
return filename.lower().endswith(self.extensions)
mmpretrain/datasets/dataset_wrappers.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
import copy
import numpy as np
from mmengine.dataset import BaseDataset, force_full_init
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class KFoldDataset:
"""A wrapper of dataset for K-Fold cross-validation.
K-Fold cross-validation divides all the samples in groups of samples,
called folds, of almost equal sizes. And we use k-1 of folds to do training
and use the fold left to do validation.
Args:
dataset (:obj:`mmengine.dataset.BaseDataset` | dict): The dataset to be
divided
fold (int): The fold used to do validation. Defaults to 0.
num_splits (int): The number of all folds. Defaults to 5.
test_mode (bool): Use the training dataset or validation dataset.
Defaults to False.
seed (int, optional): The seed to shuffle the dataset before splitting.
If None, not shuffle the dataset. Defaults to None.
"""
def __init__(self,
dataset,
fold=0,
num_splits=5,
test_mode=False,
seed=None):
if isinstance(dataset, dict):
self.dataset = DATASETS.build(dataset)
# Init the dataset wrapper lazily according to the dataset setting.
lazy_init = dataset.get('lazy_init', False)
elif isinstance(dataset, BaseDataset):
self.dataset = dataset
else:
raise TypeError(f'Unsupported dataset type {type(dataset)}.')
self._metainfo = getattr(self.dataset, 'metainfo', {})
self.fold = fold
self.num_splits = num_splits
self.test_mode = test_mode
self.seed = seed
self._fully_initialized = False
if not lazy_init:
self.full_init()
@property
def metainfo(self) -> dict:
"""Get the meta information of ``self.dataset``.
Returns:
dict: Meta information of the dataset.
"""
# Prevent `self._metainfo` from being modified by outside.
return copy.deepcopy(self._metainfo)
def full_init(self):
"""fully initialize the dataset."""
if self._fully_initialized:
return
self.dataset.full_init()
ori_len = len(self.dataset)
indices = list(range(ori_len))
if self.seed is not None:
rng = np.random.default_rng(self.seed)
rng.shuffle(indices)
test_start = ori_len * self.fold // self.num_splits
test_end = ori_len * (self.fold + 1) // self.num_splits
if self.test_mode:
indices = indices[test_start:test_end]
else:
indices = indices[:test_start] + indices[test_end:]
self._ori_indices = indices
self.dataset = self.dataset.get_subset(indices)
self._fully_initialized = True
@force_full_init
def _get_ori_dataset_idx(self, idx: int) -> int:
"""Convert global idx to local index.
Args:
idx (int): Global index of ``KFoldDataset``.
Returns:
int: The original index in the whole dataset.
"""
return self._ori_indices[idx]
@force_full_init
def get_data_info(self, idx: int) -> dict:
"""Get annotation by index.
Args:
idx (int): Global index of ``KFoldDataset``.
Returns:
dict: The idx-th annotation of the datasets.
"""
return self.dataset.get_data_info(idx)
@force_full_init
def __len__(self):
return len(self.dataset)
@force_full_init
def __getitem__(self, idx):
return self.dataset[idx]
@force_full_init
def get_cat_ids(self, idx):
return self.dataset.get_cat_ids(idx)
@force_full_init
def get_gt_labels(self):
return self.dataset.get_gt_labels()
@property
def CLASSES(self):
"""Return all categories names."""
return self._metainfo.get('classes', None)
@property
def class_to_idx(self):
"""Map mapping class name to class index.
Returns:
dict: mapping from class name to class index.
"""
return {cat: i for i, cat in enumerate(self.CLASSES)}
def __repr__(self):
"""Print the basic information of the dataset.
Returns:
str: Formatted string.
"""
head = 'Dataset ' + self.__class__.__name__
body = []
type_ = 'test' if self.test_mode else 'training'
body.append(f'Type: \t{type_}')
body.append(f'Seed: \t{self.seed}')
def ordinal(n):
# Copy from https://codegolf.stackexchange.com/a/74047
suffix = 'tsnrhtdd'[(n // 10 % 10 != 1) * (n % 10 < 4) * n % 10::4]
return f'{n}{suffix}'
body.append(
f'Fold: \t{ordinal(self.fold+1)} of {self.num_splits}-fold')
if self._fully_initialized:
body.append(f'Number of samples: \t{self.__len__()}')
else:
body.append("Haven't been initialized")
if self.CLASSES is not None:
body.append(f'Number of categories: \t{len(self.CLASSES)}')
else:
body.append('The `CLASSES` meta info is not set.')
body.append(
f'Original dataset type:\t{self.dataset.__class__.__name__}')
lines = [head] + [' ' * 4 + line for line in body]
return '\n'.join(lines)
mmpretrain/datasets/dtd.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
import mat4py
from mmengine import get_file_backend
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
from .categories import DTD_CATEGORIES
@DATASETS.register_module()
class DTD(BaseDataset):
"""The Describable Texture Dataset (DTD).
Support the `Describable Texture Dataset <https://www.robots.ox.ac.uk/~vgg/data/dtd/>`_ Dataset.
After downloading and decompression, the dataset directory structure is as follows.
DTD dataset directory: ::
dtd
├── images
│ ├── banded
| | ├──banded_0002.jpg
| | ├──banded_0004.jpg
| | └── ...
│ └── ...
├── imdb
│ └── imdb.mat
├── labels
| | ├──labels_joint_anno.txt
| | ├──test1.txt
| | ├──test2.txt
| | └── ...
│ └── ...
└── ....
Args:
data_root (str): The root directory for Describable Texture dataset.
split (str, optional): The dataset split, supports "train",
"val", "trainval", and "test". Default to "trainval".
Examples:
>>> from mmpretrain.datasets import DTD
>>> train_dataset = DTD(data_root='data/dtd', split='trainval')
>>> train_dataset
Dataset DTD
Number of samples: 3760
Number of categories: 47
Root of dataset: data/dtd
>>> test_dataset = DTD(data_root='data/dtd', split='test')
>>> test_dataset
Dataset DTD
Number of samples: 1880
Number of categories: 47
Root of dataset: data/dtd
""" # noqa: E501
METAINFO = {'classes': DTD_CATEGORIES}
def __init__(self, data_root: str, split: str = 'trainval', **kwargs):
splits = ['train', 'val', 'trainval', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
self.split = split
data_prefix = 'images'
test_mode = split == 'test'
self.backend = get_file_backend(data_root, enable_singleton=True)
ann_file = self.backend.join_path('imdb', 'imdb.mat')
super(DTD, self).__init__(
ann_file=ann_file,
data_root=data_root,
data_prefix=data_prefix,
test_mode=test_mode,
**kwargs)
def load_data_list(self):
"""Load images and ground truth labels."""
data = mat4py.loadmat(self.ann_file)['images']
names = data['name']
labels = data['class']
parts = data['set']
num = len(names)
assert num == len(labels) == len(parts), 'get error ann file'
if self.split == 'train':
target_set = {1}
elif self.split == 'val':
target_set = {2}
elif self.split == 'test':
target_set = {3}
else:
target_set = {1, 2}
data_list = []
for i in range(num):
if parts[i] in target_set:
img_name = names[i]
img_path = self.backend.join_path(self.img_prefix, img_name)
gt_label = labels[i] - 1
info = dict(img_path=img_path, gt_label=gt_label)
data_list.append(info)
return data_list
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [
f'Root of dataset: \t{self.data_root}',
]
return body
mmpretrain/datasets/fgvcaircraft.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
from mmengine import get_file_backend, list_from_file
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
from .categories import FGVCAIRCRAFT_CATEGORIES
@DATASETS.register_module()
class FGVCAircraft(BaseDataset):
"""The FGVC_Aircraft Dataset.
Support the `FGVC_Aircraft Dataset <https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/>`_ Dataset.
After downloading and decompression, the dataset directory structure is as follows.
FGVC_Aircraft dataset directory: ::
fgvc-aircraft-2013b
└── data
├── images
│ ├── 1.jpg
│ ├── 2.jpg
│ └── ...
├── images_variant_train.txt
├── images_variant_test.txt
├── images_variant_trainval.txt
├── images_variant_val.txt
├── variants.txt
└── ....
Args:
data_root (str): The root directory for FGVC_Aircraft dataset.
split (str, optional): The dataset split, supports "train",
"val", "trainval", and "test". Default to "trainval".
Examples:
>>> from mmpretrain.datasets import FGVCAircraft
>>> train_dataset = FGVCAircraft(data_root='data/fgvc-aircraft-2013b', split='trainval')
>>> train_dataset
Dataset FGVCAircraft
Number of samples: 6667
Number of categories: 100
Root of dataset: data/fgvc-aircraft-2013b
>>> test_dataset = FGVCAircraft(data_root='data/fgvc-aircraft-2013b', split='test')
>>> test_dataset
Dataset FGVCAircraft
Number of samples: 3333
Number of categories: 100
Root of dataset: data/fgvc-aircraft-2013b
""" # noqa: E501
METAINFO = {'classes': FGVCAIRCRAFT_CATEGORIES}
def __init__(self, data_root: str, split: str = 'trainval', **kwargs):
splits = ['train', 'val', 'trainval', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
self.split = split
self.backend = get_file_backend(data_root, enable_singleton=True)
ann_file = self.backend.join_path('data',
f'images_variant_{split}.txt')
data_prefix = self.backend.join_path('data', 'images')
test_mode = split == 'test'
super(FGVCAircraft, self).__init__(
ann_file=ann_file,
data_root=data_root,
test_mode=test_mode,
data_prefix=data_prefix,
**kwargs)
def load_data_list(self):
"""Load images and ground truth labels."""
pairs = list_from_file(self.ann_file)
data_list = []
for pair in pairs:
pair = pair.split()
img_name = pair[0]
class_name = ' '.join(pair[1:])
img_name = f'{img_name}.jpg'
img_path = self.backend.join_path(self.img_prefix, img_name)
gt_label = self.METAINFO['classes'].index(class_name)
info = dict(img_path=img_path, gt_label=gt_label)
data_list.append(info)
return data_list
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [
f'Root of dataset: \t{self.data_root}',
]
return body
mmpretrain/datasets/flamingo.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
import random
from abc import abstractmethod
from collections import Counter
from typing import List
import mmengine
import numpy as np
from mmengine.dataset import BaseDataset
from pycocotools.coco import COCO
from mmpretrain.registry import DATASETS
from .coco_vqa import COCOVQA
class FlamingoFewShotMixin:
"""Flamingo fewshot eval dataset minin.
Args:
num_shots (int): Number of shots to perform evaluation.
Defaults to 0.
Note: 0 does not mean a strict zero-shot in Flamingo setting.
It will use 2 only-text prompt without in context images.
num_support_examples (int): Number of support examples to get the
few shots from. Defaults to 2048.
num_query_examples (int): Number of query examples to perform the
final evaluation. Defaults to 5000.
incontext_prompt_temp (str): In context prompt template for few shot
examples. Defaults to ''.
final_prompt_temp (str): Final query prompt template. Defaults to ''.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
num_shots: int = 0,
num_support_examples: int = 2048,
num_query_examples: int = 5000,
incontext_prompt_temp: str = '',
final_prompt_temp: str = '',
**kwarg):
self.num_shots = num_shots
self.num_support_examples = num_support_examples
self.num_query_examples = num_query_examples
self.incontext_prompt_temp = incontext_prompt_temp
self.final_prompt_temp = final_prompt_temp
super().__init__(**kwarg)
def get_subset_idx(self, total_num):
random_idx = np.random.choice(
total_num,
self.num_support_examples + self.num_query_examples,
replace=False)
support_idx = random_idx[:self.num_support_examples]
query_idx = random_idx[self.num_support_examples:]
return support_idx, query_idx
@abstractmethod
def parse_basic_anno(self, anno: dict) -> dict:
"""Parse basic annotation for support and query set."""
pass
@abstractmethod
def parse_fewshot_anno(self, anno: dict, support_list: List) -> dict:
"""Parse fewshot related annotation for query set with support list."""
pass
@DATASETS.register_module()
class FlamingoEvalCOCOVQA(FlamingoFewShotMixin, COCOVQA):
"""Flamingo few shot VQAv2 dataset.
Args:
data_root (str): The root directory for ``data_prefix`` and
``ann_file``.
ann_file (str): Annotation file path.
question_file (str): Question file path.
num_shots (int): Number of shots to perform evaluation.
Defaults to 0.
Note: 0 does not mean a strict zero-shot in Flamingo setting.
It will use 2 only-text prompt without in context images.
num_support_examples (int): Number of support examples to get the
few shots from. Defaults to 2048.
num_query_examples (int): Number of query examples to perform the
final evaluation. Defaults to 5000.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
data_root: str,
question_file: str,
ann_file: str = '',
num_shots: int = 0,
num_support_examples: int = 2048,
num_query_examples: int = 5000,
**kwarg):
super().__init__(
data_root=data_root,
question_file=question_file,
ann_file=ann_file,
num_shots=num_shots,
num_support_examples=num_support_examples,
num_query_examples=num_query_examples,
**kwarg)
def parse_basic_anno(self, ann: dict) -> dict:
"""Parse basic annotation for support and query set.
Args:
anno (dict): Annotation for single example.
Return:
dict: Parsed annotation for single example.
"""
if ann is None:
return {}
answers = [a['answer'] for a in ann['answers']]
count = Counter(answers)
answer_weight = [i / len(answers) for i in count.values()]
answer_info = {
'gt_answer': list(count.keys()),
'gt_answer_weight': answer_weight
}
return answer_info
def parse_fewshot_anno(self, query: dict, support_list: List) -> dict:
"""Parse fewshot related annotation for query set with support list.
Args:
anno (dict): Annotation for single example.
support_list (List): List of support subset to subsample few shots.
Return:
dict: Parsed annotation for single example.
"""
# prepare n shots examples
shots = random.sample(support_list, self.num_shots)
# append image path for n shots
img_path = [shot['img_path'] for shot in shots]
img_path.append(query['img_path'])
query['img_path'] = img_path
query['shots'] = [
dict(
question=item['question'],
answer=item['gt_answer'][0],
) for item in shots
]
return query
def load_data_list(self) -> List[dict]:
"""Load data list."""
questions = mmengine.load(self.question_file)['questions']
if self.ann_file:
annotations = mmengine.load(self.ann_file)['annotations']
assert len(questions) == len(annotations)
else:
annotations = [None] * len(questions)
if self.num_shots > 0:
raise ValueError('Unable to construct few-shot examples '
'since no annotation file.')
# The original VQAv2 annotation file and question file includes
# only image id but no image file paths.
self.image_index = self._create_image_index()
num_data = len(questions)
support_idx, query_idx = self.get_subset_idx(num_data)
# prepare support subset
if self.num_shots > 0:
support_list = []
for idx in support_idx:
question = questions[idx]
ann = annotations[idx]
support = {**question, **self.parse_basic_anno(ann)}
support['img_path'] = self.image_index[question['image_id']]
support_list.append(support)
# prepare query subset
data_list = []
for idx in query_idx:
question = questions[idx]
ann = annotations[idx]
data_info = {**question, **self.parse_basic_anno(ann)}
data_info['img_path'] = self.image_index[question['image_id']]
if self.num_shots > 0:
data_info = self.parse_fewshot_anno(data_info, support_list)
data_list.append(data_info)
return data_list
@DATASETS.register_module()
class FlamingoEvalCOCOCaption(FlamingoFewShotMixin, BaseDataset):
"""Flamingo few shot COCO Caption dataset.
Args:
data_root (str): The root directory for ``data_prefix`` and
``ann_file``.
ann_file (str): Annotation file path.
data_prefix (dict): Prefix for data field. Defaults to
``dict(img_path='')``.
num_shots (int): Number of shots to perform evaluation.
Defaults to 0.
num_support_examples (int): Number of support examples to get the
few shots from. Defaults to 2048.
num_query_examples (int): Number of query examples to perform the
final evaluation. Defaults to 5000.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
data_root: str,
ann_file: str,
num_shots: int = 0,
num_support_examples: int = 2048,
num_query_examples: int = 5000,
**kwarg):
super().__init__(
data_root=data_root,
ann_file=ann_file,
num_shots=num_shots,
num_support_examples=num_support_examples,
num_query_examples=num_query_examples,
**kwarg)
def parse_basic_anno(self, ann: dict, coco: COCO) -> dict:
"""Parse basic annotation for support and query set.
Args:
anno (dict): Annotation for single example.
coco (COCO): The coco dataset.
Return:
dict: Parsed annotation for single example.
"""
img_prefix = self.data_prefix['img_path']
img = coco.imgs[ann['image_id']]
data_info = dict(
img_path=mmengine.join_path(img_prefix, img['file_name']),
gt_caption=ann['caption'],
image_id=ann['image_id'],
)
return data_info
def parse_fewshot_anno(self, query: dict, support_list: List) -> dict:
"""Parse fewshot related annotation for query set with support list.
Args:
query (dict): Annotation for single example.
support_list (List): List of support subset to subsample few shots.
coco (COCO): The coco dataset.
Return:
dict: Parsed annotation for single example.
"""
# prepare n shots examples
shots = random.sample(support_list, self.num_shots)
# append image path for n shots
img_path = [shot['img_path'] for shot in shots]
img_path.append(query['img_path'])
query['img_path'] = img_path
query['shots'] = [dict(caption=item['gt_caption']) for item in shots]
return query
def load_data_list(self) -> List[dict]:
"""Load data list."""
with mmengine.get_local_path(self.ann_file) as ann_file:
coco = COCO(ann_file)
num_data = len(coco.anns)
support_idx, query_idx = self.get_subset_idx(num_data)
ann_ids = list(coco.anns)
# prepare support subset
if self.num_shots > 0:
support_list = []
for idx in support_idx:
support = self.parse_basic_anno(coco.anns[ann_ids[idx]], coco)
support_list.append(support)
# prepare query subset
query_list = []
for idx in query_idx:
data_info = self.parse_basic_anno(coco.anns[ann_ids[idx]], coco)
if self.num_shots > 0:
data_info = self.parse_fewshot_anno(data_info, support_list)
query_list.append(data_info)
return query_list
mmpretrain/datasets/flickr30k_caption.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
import mmengine
from mmengine.dataset import BaseDataset
from mmengine.fileio import get_file_backend
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class Flickr30kCaption(BaseDataset):
"""Flickr30k Caption dataset. To generate coco-style GT annotation for
evaluation, please refer to
tools/dataset_converters/convert_flickr30k_ann.py.
Args:
data_root (str): The root directory for ``data_prefix``, ``ann_file``
and ``question_file``.
data_prefix (str): The directory of images.
ann_file (str): Annotation file path for training and validation.
split (str): 'train', 'val' or 'test'.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self, data_root: str, data_prefix: str, ann_file: str,
split: str, **kwarg):
assert split in ['train', 'val', 'test'], \
'`split` must be train, val or test'
self.split = split
super().__init__(
data_root=data_root,
data_prefix=dict(img_path=data_prefix),
ann_file=ann_file,
**kwarg,
)
def load_data_list(self) -> List[dict]:
"""Load data list."""
img_prefix = self.data_prefix['img_path']
annotations = mmengine.load(self.ann_file)
file_backend = get_file_backend(img_prefix)
data_list = []
for img in annotations['images']:
# img_example={
# "sentids": [0, 1, 2],
# "imgid": 0,
# "sentences": [
# {"raw": "Two men in green shirts standing in a yard.",
# "imgid": 0, "sentid": 0},
# {"raw": "A man in a blue shirt standing in a garden.",
# "imgid": 0, "sentid": 1},
# {"raw": "Two friends enjoy time spent together.",
# "imgid": 0, "sentid": 2}
# ],
# "split": "train",
# "filename": "1000092795.jpg"
# },
if img['split'] != self.split:
continue
for sentence in img['sentences']:
data_info = {
'image_id': img['imgid'],
'img_path': file_backend.join_path(img_prefix,
img['filename']),
'gt_caption': sentence['raw']
}
data_list.append(data_info)
return data_list
mmpretrain/datasets/flickr30k_retrieval.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from collections import OrderedDict
from typing import List
import mmengine
from mmengine import get_file_backend
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
@DATASETS.register_module()
class Flickr30kRetrieval(BaseDataset):
"""Flickr30k Retrieval dataset.
Args:
data_root (str): The root directory for ``data_prefix``, ``ann_file``
and ``question_file``.
data_prefix (str): The directory of images.
ann_file (str): Annotation file path for training and validation.
split (str): 'train', 'val' or 'test'.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self, data_root: str, data_prefix: str, ann_file: str,
split: str, **kwarg):
assert split in ['train', 'val', 'test'], \
'`split` must be train, val or test'
self.split = split
super().__init__(
data_root=data_root,
data_prefix=dict(img_path=data_prefix),
ann_file=ann_file,
**kwarg,
)
def load_data_list(self) -> List[dict]:
"""Load data list."""
# get file backend
img_prefix = self.data_prefix['img_path']
file_backend = get_file_backend(img_prefix)
annotations = mmengine.load(self.ann_file)
# mapping img_id to img filename
img_dict = OrderedDict()
img_idx = 0
sentence_idx = 0
train_list = []
for img in annotations['images']:
# img_example={
# "sentids": [0, 1, 2],
# "imgid": 0,
# "sentences": [
# {"raw": "Two men in green shirts standing in a yard.",
# "imgid": 0, "sentid": 0},
# {"raw": "A man in a blue shirt standing in a garden.",
# "imgid": 0, "sentid": 1},
# {"raw": "Two friends enjoy time spent together.",
# "imgid": 0, "sentid": 2}
# ],
# "split": "train",
# "filename": "1000092795.jpg"
# },
if img['split'] != self.split:
continue
# create new idx for image
train_image = dict(
ori_id=img['imgid'],
image_id=img_idx, # used for evaluation
img_path=file_backend.join_path(img_prefix, img['filename']),
text=[],
gt_text_id=[],
gt_image_id=[],
)
for sentence in img['sentences']:
ann = {}
ann['text'] = sentence['raw']
ann['ori_id'] = sentence['sentid']
ann['text_id'] = sentence_idx # used for evaluation
ann['image_ori_id'] = train_image['ori_id']
ann['image_id'] = train_image['image_id']
ann['img_path'] = train_image['img_path']
ann['is_matched'] = True
# 1. prepare train data list item
train_list.append(ann)
# 2. prepare eval data list item based on img dict
train_image['text'].append(ann['text'])
train_image['gt_text_id'].append(ann['text_id'])
train_image['gt_image_id'].append(ann['image_id'])
sentence_idx += 1
img_dict[img['imgid']] = train_image
img_idx += 1
self.img_size = len(img_dict)
self.text_size = len(train_list)
# return needed format data list
if self.test_mode:
return list(img_dict.values())
return train_list
mmpretrain/datasets/flowers102.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
import mat4py
from mmengine import get_file_backend
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
@DATASETS.register_module()
class Flowers102(BaseDataset):
"""The Oxford 102 Flower Dataset.
Support the `Oxford 102 Flowers Dataset <https://www.robots.ox.ac.uk/~vgg/data/flowers/102/>`_ Dataset.
After downloading and decompression, the dataset directory structure is as follows.
Flowers102 dataset directory: ::
Flowers102
├── jpg
│ ├── image_00001.jpg
│ ├── image_00002.jpg
│ └── ...
├── imagelabels.mat
├── setid.mat
└── ...
Args:
data_root (str): The root directory for Oxford 102 Flowers dataset.
split (str, optional): The dataset split, supports "train",
"val", "trainval", and "test". Default to "trainval".
Examples:
>>> from mmpretrain.datasets import Flowers102
>>> train_dataset = Flowers102(data_root='data/Flowers102', split='trainval')
>>> train_dataset
Dataset Flowers102
Number of samples: 2040
Root of dataset: data/Flowers102
>>> test_dataset = Flowers102(data_root='data/Flowers102', split='test')
>>> test_dataset
Dataset Flowers102
Number of samples: 6149
Root of dataset: data/Flowers102
""" # noqa: E501
def __init__(self, data_root: str, split: str = 'trainval', **kwargs):
splits = ['train', 'val', 'trainval', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
self.split = split
ann_file = 'imagelabels.mat'
data_prefix = 'jpg'
train_test_split_file = 'setid.mat'
test_mode = split == 'test'
self.backend = get_file_backend(data_root, enable_singleton=True)
self.train_test_split_file = self.backend.join_path(
data_root, train_test_split_file)
super(Flowers102, self).__init__(
ann_file=ann_file,
data_root=data_root,
data_prefix=data_prefix,
test_mode=test_mode,
**kwargs)
def load_data_list(self):
"""Load images and ground truth labels."""
label_dict = mat4py.loadmat(self.ann_file)['labels']
split_list = mat4py.loadmat(self.train_test_split_file)
if self.split == 'train':
split_list = split_list['trnid']
elif self.split == 'val':
split_list = split_list['valid']
elif self.split == 'test':
split_list = split_list['tstid']
else:
train_ids = split_list['trnid']
val_ids = split_list['valid']
train_ids.extend(val_ids)
split_list = train_ids
data_list = []
for sample_id in split_list:
img_name = 'image_%05d.jpg' % (sample_id)
img_path = self.backend.join_path(self.img_prefix, img_name)
gt_label = int(label_dict[sample_id - 1]) - 1
info = dict(img_path=img_path, gt_label=gt_label)
data_list.append(info)
return data_list
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [
f'Root of dataset: \t{self.data_root}',
]
return body
mmpretrain/datasets/food101.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
from mmengine import get_file_backend, list_from_file
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
from .categories import FOOD101_CATEGORIES
@DATASETS.register_module()
class Food101(BaseDataset):
"""The Food101 Dataset.
Support the `Food101 Dataset <https://data.vision.ee.ethz.ch/cvl/datasets_extra/food-101/>`_ Dataset.
After downloading and decompression, the dataset directory structure is as follows.
Food101 dataset directory: ::
food-101
├── images
│ ├── class_x
│ │ ├── xx1.jpg
│ │ ├── xx2.jpg
│ │ └── ...
│ ├── class_y
│ │ ├── yy1.jpg
│ │ ├── yy2.jpg
│ │ └── ...
│ └── ...
├── meta
│ ├── train.txt
│ └── test.txt
└── ....
Args:
data_root (str): The root directory for Food101 dataset.
split (str, optional): The dataset split, supports "train" and "test".
Default to "train".
Examples:
>>> from mmpretrain.datasets import Food101
>>> train_dataset = Food101(data_root='data/food-101', split='train')
>>> train_dataset
Dataset Food101
Number of samples: 75750
Number of categories: 101
Root of dataset: data/food-101
>>> test_dataset = Food101(data_root='data/food-101', split='test')
>>> test_dataset
Dataset Food101
Number of samples: 25250
Number of categories: 101
Root of dataset: data/food-101
""" # noqa: E501
METAINFO = {'classes': FOOD101_CATEGORIES}
def __init__(self, data_root: str, split: str = 'train', **kwargs):
splits = ['train', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
self.split = split
self.backend = get_file_backend(data_root, enable_singleton=True)
if split == 'train':
ann_file = self.backend.join_path('meta', 'train.txt')
else:
ann_file = self.backend.join_path('meta', 'test.txt')
test_mode = split == 'test'
data_prefix = 'images'
super(Food101, self).__init__(
ann_file=ann_file,
data_root=data_root,
test_mode=test_mode,
data_prefix=data_prefix,
**kwargs)
def load_data_list(self):
"""Load images and ground truth labels."""
pairs = list_from_file(self.ann_file)
data_list = []
for pair in pairs:
class_name, img_name = pair.split('/')
img_name = f'{img_name}.jpg'
img_path = self.backend.join_path(self.img_prefix, class_name,
img_name)
gt_label = self.METAINFO['classes'].index(class_name)
info = dict(img_path=img_path, gt_label=gt_label)
data_list.append(info)
return data_list
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [
f'Root of dataset: \t{self.data_root}',
]
return body
mmpretrain/datasets/gqa_dataset.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp
from typing import List
import mmengine
from mmengine.dataset import BaseDataset
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class GQA(BaseDataset):
"""GQA dataset.
We use the annotation file from LAVIS, and you can download all annotation files from following links: # noqa: E501
train:
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/gqa/train_balanced_questions.json # noqa: E501
val:
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/gqa/testdev_balanced_questions.json # noqa: E501
test:
https://storage.googleapis.com/sfr-vision-language-research/LAVIS/datasets/gqa/test_balanced_questions.json # noqa: E501
and images from the official website:
https://cs.stanford.edu/people/dorarad/gqa/index.html
Args:
data_root (str): The root directory for ``data_prefix``, ``ann_file``
and ``question_file``.
data_prefix (str): The directory of images.
ann_file (str, optional): Annotation file path for training and
validation. Defaults to an empty string.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
data_root: str,
data_prefix: str,
ann_file: str = '',
**kwarg):
super().__init__(
data_root=data_root,
data_prefix=dict(img_path=data_prefix),
ann_file=ann_file,
**kwarg,
)
def load_data_list(self) -> List[dict]:
"""Load data list."""
annotations = mmengine.load(self.ann_file)
data_list = []
for ann in annotations:
# ann example
# {
# 'question': "Is it overcast?",
# 'answer': 'no,
# 'image_id': n161313.jpg,
# 'question_id': 262148000,
# ....
# }
data_info = dict()
data_info['img_path'] = osp.join(self.data_prefix['img_path'],
ann['image'])
data_info['question'] = ann['question']
data_info['gt_answer'] = ann['answer']
data_list.append(data_info)
return data_list
mmpretrain/datasets/iconqa.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
import mmengine
from mmengine.dataset import BaseDataset
from mmengine.fileio import list_dir_or_file
from mmengine.utils import check_file_exist
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class IconQA(BaseDataset):
"""IconQA: A benchmark for abstract diagram understanding
and visual language reasoning.
Args:
data_root (str): The root directory for ``data_prefix``, ``ann_file``
and ``question_file``.
data_prefix (str): The directory of the specific task and split.
eg. ``iconqa/val/choose_text/``.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self, data_root: str, data_prefix: str, **kwarg):
super().__init__(
data_root=data_root,
data_prefix=dict(img_path=data_prefix),
**kwarg,
)
def load_data_list(self) -> List[dict]:
"""Load data list."""
sample_list = list(
list_dir_or_file(self.data_prefix['img_path'], list_file=False))
data_list = list()
for sample_id in sample_list:
# data json
# {
# "question": "How likely is it that you will pick a black one?",
# "choices": [
# "certain",
# "unlikely",
# "impossible",
# "probable"
# ],
# "answer": 2,
# "ques_type": "choose_txt",
# "grade": "grade1",
# "label": "S2"
# }
data_info = mmengine.load(
mmengine.join_path(self.data_prefix['img_path'], sample_id,
'data.json'))
data_info['gt_answer'] = data_info['choices'][int(
data_info['answer'])]
data_info['img_path'] = mmengine.join_path(
self.data_prefix['img_path'], sample_id, 'image.png')
check_file_exist(data_info['img_path'])
data_list.append(data_info)
return data_list
mmpretrain/datasets/imagenet.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List, Optional, Union
from mmengine import fileio
from mmengine.logging import MMLogger
from mmpretrain.registry import DATASETS
from .categories import IMAGENET_CATEGORIES
from .custom import CustomDataset
@DATASETS.register_module()
class ImageNet(CustomDataset):
"""`ImageNet <http://www.image-net.org>`_ Dataset.
The dataset supports two kinds of directory format,
::
imagenet
├── train
│ ├──class_x
| | ├── x1.jpg
| | ├── x2.jpg
| | └── ...
│ ├── class_y
| | ├── y1.jpg
| | ├── y2.jpg
| | └── ...
| └── ...
├── val
│ ├──class_x
| | └── ...
│ ├── class_y
| | └── ...
| └── ...
└── test
├── test1.jpg
├── test2.jpg
└── ...
or ::
imagenet
├── train
│ ├── x1.jpg
│ ├── y1.jpg
│ └── ...
├── val
│ ├── x3.jpg
│ ├── y3.jpg
│ └── ...
├── test
│ ├── test1.jpg
│ ├── test2.jpg
│ └── ...
└── meta
├── train.txt
└── val.txt
Args:
data_root (str): The root directory for ``data_prefix`` and
``ann_file``. Defaults to ''.
split (str): The dataset split, supports "train", "val" and "test".
Default to ''.
data_prefix (str | dict): Prefix for training data. Defaults to ''.
ann_file (str): Annotation file path. Defaults to ''.
metainfo (dict, optional): Meta information for dataset, such as class
information. Defaults to None.
**kwargs: Other keyword arguments in :class:`CustomDataset` and
:class:`BaseDataset`.
Examples:
>>> from mmpretrain.datasets import ImageNet
>>> train_dataset = ImageNet(data_root='data/imagenet', split='train')
>>> train_dataset
Dataset ImageNet
Number of samples: 1281167
Number of categories: 1000
Root of dataset: data/imagenet
>>> test_dataset = ImageNet(data_root='data/imagenet', split='val')
>>> test_dataset
Dataset ImageNet
Number of samples: 50000
Number of categories: 1000
Root of dataset: data/imagenet
""" # noqa: E501
IMG_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif')
METAINFO = {'classes': IMAGENET_CATEGORIES}
def __init__(self,
data_root: str = '',
split: str = '',
data_prefix: Union[str, dict] = '',
ann_file: str = '',
metainfo: Optional[dict] = None,
**kwargs):
kwargs = {'extensions': self.IMG_EXTENSIONS, **kwargs}
if split:
splits = ['train', 'val', 'test']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'"
if split == 'test':
logger = MMLogger.get_current_instance()
logger.info(
'Since the ImageNet1k test set does not provide label'
'annotations, `with_label` is set to False')
kwargs['with_label'] = False
data_prefix = split if data_prefix == '' else data_prefix
if ann_file == '':
_ann_path = fileio.join_path(data_root, 'meta', f'{split}.txt')
if fileio.exists(_ann_path):
ann_file = fileio.join_path('meta', f'{split}.txt')
super().__init__(
data_root=data_root,
data_prefix=data_prefix,
ann_file=ann_file,
metainfo=metainfo,
**kwargs)
def extra_repr(self) -> List[str]:
"""The extra repr information of the dataset."""
body = [
f'Root of dataset: \t{self.data_root}',
]
return body
@DATASETS.register_module()
class ImageNet21k(CustomDataset):
"""ImageNet21k Dataset.
Since the dataset ImageNet21k is extremely big, contains 21k+ classes
and 1.4B files. We won't provide the default categories list. Please
specify it from the ``classes`` argument.
The dataset directory structure is as follows,
ImageNet21k dataset directory ::
imagenet21k
├── train
│ ├──class_x
| | ├── x1.jpg
| | ├── x2.jpg
| | └── ...
│ ├── class_y
| | ├── y1.jpg
| | ├── y2.jpg
| | └── ...
| └── ...
└── meta
└── train.txt
Args:
data_root (str): The root directory for ``data_prefix`` and
``ann_file``. Defaults to ''.
data_prefix (str | dict): Prefix for training data. Defaults to ''.
ann_file (str): Annotation file path. Defaults to ''.
metainfo (dict, optional): Meta information for dataset, such as class
information. Defaults to None.
multi_label (bool): Not implement by now. Use multi label or not.
Defaults to False.
**kwargs: Other keyword arguments in :class:`CustomDataset` and
:class:`BaseDataset`.
Examples:
>>> from mmpretrain.datasets import ImageNet21k
>>> train_dataset = ImageNet21k(data_root='data/imagenet21k', split='train')
>>> train_dataset
Dataset ImageNet21k
Number of samples: 14197088
Annotation file: data/imagenet21k/meta/train.txt
Prefix of images: data/imagenet21k/train
""" # noqa: E501
IMG_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif')
def __init__(self,
data_root: str = '',
split: str = '',
data_prefix: Union[str, dict] = '',
ann_file: str = '',
metainfo: Optional[dict] = None,
multi_label: bool = False,
**kwargs):
if multi_label:
raise NotImplementedError(
'The `multi_label` option is not supported by now.')
self.multi_label = multi_label
if split:
splits = ['train']
assert split in splits, \
f"The split must be one of {splits}, but get '{split}'.\
If you want to specify your own validation set or test set,\
please set split to None."
self.split = split
data_prefix = split if data_prefix == '' else data_prefix
if not ann_file:
_ann_path = fileio.join_path(data_root, 'meta', f'{split}.txt')
if fileio.exists(_ann_path):
ann_file = fileio.join_path('meta', f'{split}.txt')
logger = MMLogger.get_current_instance()
if not ann_file:
logger.warning(
'The ImageNet21k dataset is large, and scanning directory may '
'consume long time. Considering to specify the `ann_file` to '
'accelerate the initialization.')
kwargs = {'extensions': self.IMG_EXTENSIONS, **kwargs}
super().__init__(
data_root=data_root,
data_prefix=data_prefix,
ann_file=ann_file,
metainfo=metainfo,
**kwargs)
if self.CLASSES is None:
logger.warning(
'The CLASSES is not stored in the `ImageNet21k` class. '
'Considering to specify the `classes` argument if you need '
'do inference on the ImageNet-21k dataset')
mmpretrain/datasets/infographic_vqa.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
import mmengine
from mmengine.dataset import BaseDataset
from mmpretrain.registry import DATASETS
@DATASETS.register_module()
class InfographicVQA(BaseDataset):
"""Infographic VQA dataset.
Args:
data_root (str): The root directory for ``data_prefix``, ``ann_file``.
data_prefix (str): The directory of images.
ann_file (str, optional): Annotation file path for training and
validation. Defaults to an empty string.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
"""
def __init__(self,
data_root: str,
data_prefix: str,
ann_file: str = '',
**kwarg):
super().__init__(
data_root=data_root,
data_prefix=dict(img_path=data_prefix),
ann_file=ann_file,
**kwarg,
)
def load_data_list(self) -> List[dict]:
"""Load data list."""
annotations = mmengine.load(self.ann_file)
annotations = annotations['data']
data_list = []
for ann in annotations:
# ann example
# {
# "questionId": 98313,
# "question": "Which social platform has heavy female audience?",
# "image_local_name": "37313.jpeg",
# "image_url": "https://xxx.png",
# "ocr_output_file": "37313.json",
# "answers": [
# "pinterest"
# ],
# "data_split": "val"
# }
data_info = dict()
data_info['question'] = ann['question']
data_info['img_path'] = mmengine.join_path(
self.data_prefix['img_path'], ann['image_local_name'])
if 'answers' in ann.keys(): # test splits do not include gt
data_info['gt_answer'] = ann['answers']
data_list.append(data_info)
return data_list
mmpretrain/datasets/inshop.py 0 → 100644
View file @ cbc25585
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine import get_file_backend, list_from_file
from mmpretrain.registry import DATASETS
from .base_dataset import BaseDataset
@DATASETS.register_module()
class InShop(BaseDataset):
"""InShop Dataset for Image Retrieval.
Please download the images from the homepage
'https://mmlab.ie.cuhk.edu.hk/projects/DeepFashion/InShopRetrieval.html'
(In-shop Clothes Retrieval Benchmark -> Img -> img.zip,
Eval/list_eval_partition.txt), and organize them as follows way: ::
In-shop Clothes Retrieval Benchmark (data_root)/
├── Eval /
│ └── list_eval_partition.txt (ann_file)
├── Img (img_prefix)
│ └── img/
├── README.txt
└── .....
Args:
data_root (str): The root directory for dataset.
split (str): Choose from 'train', 'query' and 'gallery'.
Defaults to 'train'.
data_prefix (str | dict): Prefix for training data.
Defaults to 'Img'.
ann_file (str): Annotation file path, path relative to
``data_root``. Defaults to 'Eval/list_eval_partition.txt'.
**kwargs: Other keyword arguments in :class:`BaseDataset`.
Examples:
>>> from mmpretrain.datasets import InShop
>>>
>>> # build train InShop dataset
>>> inshop_train_cfg = dict(data_root='data/inshop', split='train')
>>> inshop_train = InShop(**inshop_train_cfg)
>>> inshop_train
Dataset InShop
Number of samples: 25882
The `CLASSES` meta info is not set.
Root of dataset: data/inshop
>>>
>>> # build query InShop dataset
>>> inshop_query_cfg = dict(data_root='data/inshop', split='query')
>>> inshop_query = InShop(**inshop_query_cfg)
>>> inshop_query
Dataset InShop
Number of samples: 14218
The `CLASSES` meta info is not set.
Root of dataset: data/inshop
>>>
>>> # build gallery InShop dataset
>>> inshop_gallery_cfg = dict(data_root='data/inshop', split='gallery')
>>> inshop_gallery = InShop(**inshop_gallery_cfg)
>>> inshop_gallery
Dataset InShop
Number of samples: 12612
The `CLASSES` meta info is not set.
Root of dataset: data/inshop
"""
def __init__(self,
data_root: str,
split: str = 'train',
data_prefix: str = 'Img',
ann_file: str = 'Eval/list_eval_partition.txt',
**kwargs):
assert split in ('train', 'query', 'gallery'), "'split' of `InShop`" \
f" must be one of ['train', 'query', 'gallery'], bu get '{split}'"
self.backend = get_file_backend(data_root, enable_singleton=True)
self.split = split
super().__init__(
data_root=data_root,
data_prefix=data_prefix,
ann_file=ann_file,
**kwargs)
def _process_annotations(self):
lines = list_from_file(self.ann_file)
anno_train = dict(metainfo=dict(), data_list=list())
anno_gallery = dict(metainfo=dict(), data_list=list())
# item_id to label, each item corresponds to one class label
class_num = 0
gt_label_train = {}
# item_id to label, each label corresponds to several items
gallery_num = 0
gt_label_gallery = {}
# (lines[0], lines[1]) is the image number and the field name;
# Each line format as 'image_name, item_id, evaluation_status'
for line in lines[2:]:
img_name, item_id, status = line.split()
img_path = self.backend.join_path(self.img_prefix, img_name)
if status == 'train':
if item_id not in gt_label_train:
gt_label_train[item_id] = class_num
class_num += 1
# item_id to class_id (for the training set)
anno_train['data_list'].append(
dict(img_path=img_path, gt_label=gt_label_train[item_id]))
elif status == 'gallery':
if item_id not in gt_label_gallery:
gt_label_gallery[item_id] = []
# Since there are multiple images for each item,
# record the corresponding item for each image.
gt_label_gallery[item_id].append(gallery_num)
anno_gallery['data_list'].append(
dict(img_path=img_path, sample_idx=gallery_num))
gallery_num += 1
if self.split == 'train':
anno_train['metainfo']['class_number'] = class_num
anno_train['metainfo']['sample_number'] = \
len(anno_train['data_list'])
return anno_train
elif self.split == 'gallery':
anno_gallery['metainfo']['sample_number'] = gallery_num
return anno_gallery
# Generate the label for the query(val) set
anno_query = dict(metainfo=dict(), data_list=list())
query_num = 0
for line in lines[2:]:
img_name, item_id, status = line.split()
img_path = self.backend.join_path(self.img_prefix, img_name)
if status == 'query':
anno_query['data_list'].append(
dict(
img_path=img_path, gt_label=gt_label_gallery[item_id]))
query_num += 1
anno_query['metainfo']['sample_number'] = query_num
return anno_query
def load_data_list(self):
"""load data list.
For the train set, return image and ground truth label. For the query
set, return image and ids of images in gallery. For the gallery set,
return image and its id.
"""
data_info = self._process_annotations()
data_list = data_info['data_list']
return data_list
def extra_repr(self):
"""The extra repr information of the dataset."""
body = [f'Root of dataset: \t{self.data_root}']
return body
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment