Upload 5 files

README.md

@@ -1,3 +1,55 @@
 ---
 license: apache-2.0
 ---
+## FDViT: Improve the Hierarchical Architecture of Vision Transformer (ICCV 2023)
+
+**Yixing Xu, Chao Li, Dong Li, Xiao Sheng, Fan Jiang, Lu Tian, Ashish Sirasao** | [Paper](https://openaccess.thecvf.com/content/ICCV2023/papers/Xu_FDViT_Improve_the_Hierarchical_Architecture_of_Vision_Transformer_ICCV_2023_paper.pdf)
+
+Advanced Micro Devices, Inc.
+
+---
+
+## Dependancies
+
+```bash
+torch == 1.13.1
+torchvision == 0.14.1
+timm == 0.6.12
+einops == 0.6.1
+```
+
+## Model performance
+
+The image classification results of FDViT models on ImageNet dataset are shown in the following table.
+
+|Model|Parameters (M)|FLOPs(G)|Top-1 Accuracy (%)|
+|-|-|-|-|
+|FDViT-Ti|4.6|0.6|73.74|
+|FDViT-S|21.6|2.8|81.45|
+|FDViT-B|68.1|11.9|82.39|
+
+## Model Usage
+
+```bash
+from transformers import AutoModelForImageClassification
+import torch
+
+model = AutoModelForImageClassification.from_pretrained("FDViT_b", trust_remote_code=True)
+
+model.eval()
+
+inp = torch.ones(1,3,224,224)
+out = model(inp)
+```
+
+## Citation
+
+```
+@inproceedings{xu2023fdvit,
+  title={FDViT: Improve the Hierarchical Architecture of Vision Transformer},
+  author={Xu, Yixing and Li, Chao and Li, Dong and Sheng, Xiao and Jiang, Fan and Tian, Lu and Sirasao, Ashish},
+  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={5950--5960},
+  year={2023}
+}
+```

config.json

@@ -0,0 +1,2063 @@
+ {
+  "architectures": [
+    "FDViTForImageClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_fdvit.FDViTConfig",
+    "AutoModel": "modeling_fdvit.FDViTModel",
+    "AutoModelForImageClassification": "modeling_fdvit.FDViTForImageClassification",
+    "AutoImageProcessor": "image_processing_fdvit.FDViTImageProcessor"
+  }, 
+  "depth": [
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "heads": [
+    4,
+    8,
+    8,
+    16,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge's robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenter's kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o'-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jeweler's loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pj's, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenter's plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumber's helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potter's wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spider's web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Afghan hound, Afghan": 160,
+    "African chameleon, Chamaeleo chamaeleon": 47,
+    "African crocodile, Nile crocodile, Crocodylus niloticus": 49,
+    "African elephant, Loxodonta africana": 386,
+    "African grey, African gray, Psittacus erithacus": 87,
+    "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus": 275,
+    "Airedale, Airedale terrier": 191,
+    "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier": 180,
+    "American alligator, Alligator mississipiensis": 50,
+    "American black bear, black bear, Ursus americanus, Euarctos americanus": 295,
+    "American chameleon, anole, Anolis carolinensis": 40,
+    "American coot, marsh hen, mud hen, water hen, Fulica americana": 137,
+    "American egret, great white heron, Egretta albus": 132,
+    "American lobster, Northern lobster, Maine lobster, Homarus americanus": 122,
+    "Angora, Angora rabbit": 332,
+    "Appenzeller": 240,
+    "Arabian camel, dromedary, Camelus dromedarius": 354,
+    "Arctic fox, white fox, Alopex lagopus": 279,
+    "Australian terrier": 193,
+    "Band Aid": 419,
+    "Bedlington terrier": 181,
+    "Bernese mountain dog": 239,
+    "Blenheim spaniel": 156,
+    "Border collie": 232,
+    "Border terrier": 182,
+    "Boston bull, Boston terrier": 195,
+    "Bouvier des Flandres, Bouviers des Flandres": 233,
+    "Brabancon griffon": 262,
+    "Brittany spaniel": 215,
+    "CD player": 485,
+    "Cardigan, Cardigan Welsh corgi": 264,
+    "Chesapeake Bay retriever": 209,
+    "Chihuahua": 151,
+    "Christmas stocking": 496,
+    "Crock Pot": 521,
+    "Dandie Dinmont, Dandie Dinmont terrier": 194,
+    "Doberman, Doberman pinscher": 236,
+    "Dungeness crab, Cancer magister": 118,
+    "Dutch oven": 544,
+    "Egyptian cat": 285,
+    "English foxhound": 167,
+    "English setter": 212,
+    "English springer, English springer spaniel": 217,
+    "EntleBucher": 241,
+    "Eskimo dog, husky": 248,
+    "European fire salamander, Salamandra salamandra": 25,
+    "European gallinule, Porphyrio porphyrio": 136,
+    "French bulldog": 245,
+    "French horn, horn": 566,
+    "French loaf": 930,
+    "German shepherd, German shepherd dog, German police dog, alsatian": 235,
+    "German short-haired pointer": 210,
+    "Gila monster, Heloderma suspectum": 45,
+    "Gordon setter": 214,
+    "Granny Smith": 948,
+    "Great Dane": 246,
+    "Great Pyrenees": 257,
+    "Greater Swiss Mountain dog": 238,
+    "Ibizan hound, Ibizan Podenco": 173,
+    "Indian cobra, Naja naja": 63,
+    "Indian elephant, Elephas maximus": 385,
+    "Irish setter, red setter": 213,
+    "Irish terrier": 184,
+    "Irish water spaniel": 221,
+    "Irish wolfhound": 170,
+    "Italian greyhound": 171,
+    "Japanese spaniel": 152,
+    "Kerry blue terrier": 183,
+    "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis": 48,
+    "Labrador retriever": 208,
+    "Lakeland terrier": 189,
+    "Leonberg": 255,
+    "Lhasa, Lhasa apso": 204,
+    "Loafer": 630,
+    "Madagascar cat, ring-tailed lemur, Lemur catta": 383,
+    "Maltese dog, Maltese terrier, Maltese": 153,
+    "Mexican hairless": 268,
+    "Model T": 661,
+    "Newfoundland, Newfoundland dog": 256,
+    "Norfolk terrier": 185,
+    "Norwegian elkhound, elkhound": 174,
+    "Norwich terrier": 186,
+    "Old English sheepdog, bobtail": 229,
+    "Pekinese, Pekingese, Peke": 154,
+    "Pembroke, Pembroke Welsh corgi": 263,
+    "Persian cat": 283,
+    "Petri dish": 712,
+    "Polaroid camera, Polaroid Land camera": 732,
+    "Pomeranian": 259,
+    "Rhodesian ridgeback": 159,
+    "Rottweiler": 234,
+    "Saint Bernard, St Bernard": 247,
+    "Saluki, gazelle hound": 176,
+    "Samoyed, Samoyede": 258,
+    "Scotch terrier, Scottish terrier, Scottie": 199,
+    "Scottish deerhound, deerhound": 177,
+    "Sealyham terrier, Sealyham": 190,
+    "Shetland sheepdog, Shetland sheep dog, Shetland": 230,
+    "Shih-Tzu": 155,
+    "Siamese cat, Siamese": 284,
+    "Siberian husky": 250,
+    "Staffordshire bullterrier, Staffordshire bull terrier": 179,
+    "Sussex spaniel": 220,
+    "Tibetan mastiff": 244,
+    "Tibetan terrier, chrysanthemum dog": 200,
+    "Walker hound, Walker foxhound": 166,
+    "Weimaraner": 178,
+    "Welsh springer spaniel": 218,
+    "West Highland white terrier": 203,
+    "Windsor tie": 906,
+    "Yorkshire terrier": 187,
+    "abacus": 398,
+    "abaya": 399,
+    "academic gown, academic robe, judge's robe": 400,
+    "accordion, piano accordion, squeeze box": 401,
+    "acorn": 988,
+    "acorn squash": 941,
+    "acoustic guitar": 402,
+    "admiral": 321,
+    "affenpinscher, monkey pinscher, monkey dog": 252,
+    "agama": 42,
+    "agaric": 992,
+    "aircraft carrier, carrier, flattop, attack aircraft carrier": 403,
+    "airliner": 404,
+    "airship, dirigible": 405,
+    "albatross, mollymawk": 146,
+    "alligator lizard": 44,
+    "alp": 970,
+    "altar": 406,
+    "ambulance": 407,
+    "amphibian, amphibious vehicle": 408,
+    "analog clock": 409,
+    "anemone fish": 393,
+    "ant, emmet, pismire": 310,
+    "apiary, bee house": 410,
+    "apron": 411,
+    "armadillo": 363,
+    "artichoke, globe artichoke": 944,
+    "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin": 412,
+    "assault rifle, assault gun": 413,
+    "axolotl, mud puppy, Ambystoma mexicanum": 29,
+    "baboon": 372,
+    "backpack, back pack, knapsack, packsack, rucksack, haversack": 414,
+    "badger": 362,
+    "bagel, beigel": 931,
+    "bakery, bakeshop, bakehouse": 415,
+    "balance beam, beam": 416,
+    "bald eagle, American eagle, Haliaeetus leucocephalus": 22,
+    "balloon": 417,
+    "ballplayer, baseball player": 981,
+    "ballpoint, ballpoint pen, ballpen, Biro": 418,
+    "banana": 954,
+    "banded gecko": 38,
+    "banjo": 420,
+    "bannister, banister, balustrade, balusters, handrail": 421,
+    "barbell": 422,
+    "barber chair": 423,
+    "barbershop": 424,
+    "barn": 425,
+    "barn spider, Araneus cavaticus": 73,
+    "barometer": 426,
+    "barracouta, snoek": 389,
+    "barrel, cask": 427,
+    "barrow, garden cart, lawn cart, wheelbarrow": 428,
+    "baseball": 429,
+    "basenji": 253,
+    "basketball": 430,
+    "basset, basset hound": 161,
+    "bassinet": 431,
+    "bassoon": 432,
+    "bath towel": 434,
+    "bathing cap, swimming cap": 433,
+    "bathtub, bathing tub, bath, tub": 435,
+    "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon": 436,
+    "beacon, lighthouse, beacon light, pharos": 437,
+    "beagle": 162,
+    "beaker": 438,
+    "bearskin, busby, shako": 439,
+    "beaver": 337,
+    "bee": 309,
+    "bee eater": 92,
+    "beer bottle": 440,
+    "beer glass": 441,
+    "bell cote, bell cot": 442,
+    "bell pepper": 945,
+    "bib": 443,
+    "bicycle-built-for-two, tandem bicycle, tandem": 444,
+    "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis": 349,
+    "bikini, two-piece": 445,
+    "binder, ring-binder": 446,
+    "binoculars, field glasses, opera glasses": 447,
+    "birdhouse": 448,
+    "bison": 347,
+    "bittern": 133,
+    "black and gold garden spider, Argiope aurantia": 72,
+    "black grouse": 80,
+    "black stork, Ciconia nigra": 128,
+    "black swan, Cygnus atratus": 100,
+    "black widow, Latrodectus mactans": 75,
+    "black-and-tan coonhound": 165,
+    "black-footed ferret, ferret, Mustela nigripes": 359,
+    "bloodhound, sleuthhound": 163,
+    "bluetick": 164,
+    "boa constrictor, Constrictor constrictor": 61,
+    "boathouse": 449,
+    "bobsled, bobsleigh, bob": 450,
+    "bolete": 997,
+    "bolo tie, bolo, bola tie, bola": 451,
+    "bonnet, poke bonnet": 452,
+    "book jacket, dust cover, dust jacket, dust wrapper": 921,
+    "bookcase": 453,
+    "bookshop, bookstore, bookstall": 454,
+    "borzoi, Russian wolfhound": 169,
+    "bottlecap": 455,
+    "bow": 456,
+    "bow tie, bow-tie, bowtie": 457,
+    "box turtle, box tortoise": 37,
+    "boxer": 242,
+    "brain coral": 109,
+    "brambling, Fringilla montifringilla": 10,
+    "brass, memorial tablet, plaque": 458,
+    "brassiere, bra, bandeau": 459,
+    "breakwater, groin, groyne, mole, bulwark, seawall, jetty": 460,
+    "breastplate, aegis, egis": 461,
+    "briard": 226,
+    "broccoli": 937,
+    "broom": 462,
+    "brown bear, bruin, Ursus arctos": 294,
+    "bubble": 971,
+    "bucket, pail": 463,
+    "buckeye, horse chestnut, conker": 990,
+    "buckle": 464,
+    "bulbul": 16,
+    "bull mastiff": 243,
+    "bullet train, bullet": 466,
+    "bulletproof vest": 465,
+    "bullfrog, Rana catesbeiana": 30,
+    "burrito": 965,
+    "bustard": 138,
+    "butcher shop, meat market": 467,
+    "butternut squash": 942,
+    "cab, hack, taxi, taxicab": 468,
+    "cabbage butterfly": 324,
+    "cairn, cairn terrier": 192,
+    "caldron, cauldron": 469,
+    "can opener, tin opener": 473,
+    "candle, taper, wax light": 470,
+    "cannon": 471,
+    "canoe": 472,
+    "capuchin, ringtail, Cebus capucinus": 378,
+    "car mirror": 475,
+    "car wheel": 479,
+    "carbonara": 959,
+    "cardigan": 474,
+    "cardoon": 946,
+    "carousel, carrousel, merry-go-round, roundabout, whirligig": 476,
+    "carpenter's kit, tool kit": 477,
+    "carton": 478,
+    "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM": 480,
+    "cassette": 481,
+    "cassette player": 482,
+    "castle": 483,
+    "catamaran": 484,
+    "cauliflower": 938,
+    "cello, violoncello": 486,
+    "cellular telephone, cellular phone, cellphone, cell, mobile phone": 487,
+    "centipede": 79,
+    "chain": 488,
+    "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour": 490,
+    "chain saw, chainsaw": 491,
+    "chainlink fence": 489,
+    "chambered nautilus, pearly nautilus, nautilus": 117,
+    "cheeseburger": 933,
+    "cheetah, chetah, Acinonyx jubatus": 293,
+    "chest": 492,
+    "chickadee": 19,
+    "chiffonier, commode": 493,
+    "chime, bell, gong": 494,
+    "chimpanzee, chimp, Pan troglodytes": 367,
+    "china cabinet, china closet": 495,
+    "chiton, coat-of-mail shell, sea cradle, polyplacophore": 116,
+    "chocolate sauce, chocolate syrup": 960,
+    "chow, chow chow": 260,
+    "church, church building": 497,
+    "cicada, cicala": 316,
+    "cinema, movie theater, movie theatre, movie house, picture palace": 498,
+    "cleaver, meat cleaver, chopper": 499,
+    "cliff dwelling": 500,
+    "cliff, drop, drop-off": 972,
+    "cloak": 501,
+    "clog, geta, patten, sabot": 502,
+    "clumber, clumber spaniel": 216,
+    "cock": 7,
+    "cocker spaniel, English cocker spaniel, cocker": 219,
+    "cockroach, roach": 314,
+    "cocktail shaker": 503,
+    "coffee mug": 504,
+    "coffeepot": 505,
+    "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch": 391,
+    "coil, spiral, volute, whorl, helix": 506,
+    "collie": 231,
+    "colobus, colobus monkey": 375,
+    "combination lock": 507,
+    "comic book": 917,
+    "common iguana, iguana, Iguana iguana": 39,
+    "common newt, Triturus vulgaris": 26,
+    "computer keyboard, keypad": 508,
+    "conch": 112,
+    "confectionery, confectionary, candy store": 509,
+    "consomme": 925,
+    "container ship, containership, container vessel": 510,
+    "convertible": 511,
+    "coral fungus": 991,
+    "coral reef": 973,
+    "corkscrew, bottle screw": 512,
+    "corn": 987,
+    "cornet, horn, trumpet, trump": 513,
+    "coucal": 91,
+    "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor": 286,
+    "cowboy boot": 514,
+    "cowboy hat, ten-gallon hat": 515,
+    "coyote, prairie wolf, brush wolf, Canis latrans": 272,
+    "cradle": 516,
+    "crane": 517,
+    "crash helmet": 518,
+    "crate": 519,
+    "crayfish, crawfish, crawdad, crawdaddy": 124,
+    "crib, cot": 520,
+    "cricket": 312,
+    "croquet ball": 522,
+    "crossword puzzle, crossword": 918,
+    "crutch": 523,
+    "cucumber, cuke": 943,
+    "cuirass": 524,
+    "cup": 968,
+    "curly-coated retriever": 206,
+    "custard apple": 956,
+    "daisy": 985,
+    "dalmatian, coach dog, carriage dog": 251,
+    "dam, dike, dyke": 525,
+    "damselfly": 320,
+    "desk": 526,
+    "desktop computer": 527,
+    "dhole, Cuon alpinus": 274,
+    "dial telephone, dial phone": 528,
+    "diamondback, diamondback rattlesnake, Crotalus adamanteus": 67,
+    "diaper, nappy, napkin": 529,
+    "digital clock": 530,
+    "digital watch": 531,
+    "dingo, warrigal, warragal, Canis dingo": 273,
+    "dining table, board": 532,
+    "dishrag, dishcloth": 533,
+    "dishwasher, dish washer, dishwashing machine": 534,
+    "disk brake, disc brake": 535,
+    "dock, dockage, docking facility": 536,
+    "dogsled, dog sled, dog sleigh": 537,
+    "dome": 538,
+    "doormat, welcome mat": 539,
+    "dough": 961,
+    "dowitcher": 142,
+    "dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk": 319,
+    "drake": 97,
+    "drilling platform, offshore rig": 540,
+    "drum, membranophone, tympan": 541,
+    "drumstick": 542,
+    "dugong, Dugong dugon": 149,
+    "dumbbell": 543,
+    "dung beetle": 305,
+    "ear, spike, capitulum": 998,
+    "earthstar": 995,
+    "echidna, spiny anteater, anteater": 102,
+    "eel": 390,
+    "eft": 27,
+    "eggnog": 969,
+    "electric fan, blower": 545,
+    "electric guitar": 546,
+    "electric locomotive": 547,
+    "electric ray, crampfish, numbfish, torpedo": 5,
+    "entertainment center": 548,
+    "envelope": 549,
+    "espresso": 967,
+    "espresso maker": 550,
+    "face powder": 551,
+    "feather boa, boa": 552,
+    "fiddler crab": 120,
+    "fig": 952,
+    "file, file cabinet, filing cabinet": 553,
+    "fire engine, fire truck": 555,
+    "fire screen, fireguard": 556,
+    "fireboat": 554,
+    "flagpole, flagstaff": 557,
+    "flamingo": 130,
+    "flat-coated retriever": 205,
+    "flatworm, platyhelminth": 110,
+    "flute, transverse flute": 558,
+    "fly": 308,
+    "folding chair": 559,
+    "football helmet": 560,
+    "forklift": 561,
+    "fountain": 562,
+    "fountain pen": 563,
+    "four-poster": 564,
+    "fox squirrel, eastern fox squirrel, Sciurus niger": 335,
+    "freight car": 565,
+    "frilled lizard, Chlamydosaurus kingi": 43,
+    "frying pan, frypan, skillet": 567,
+    "fur coat": 568,
+    "gar, garfish, garpike, billfish, Lepisosteus osseus": 395,
+    "garbage truck, dustcart": 569,
+    "garden spider, Aranea diademata": 74,
+    "garter snake, grass snake": 57,
+    "gas pump, gasoline pump, petrol pump, island dispenser": 571,
+    "gasmask, respirator, gas helmet": 570,
+    "gazelle": 353,
+    "geyser": 974,
+    "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca": 388,
+    "giant schnauzer": 197,
+    "gibbon, Hylobates lar": 368,
+    "go-kart": 573,
+    "goblet": 572,
+    "golden retriever": 207,
+    "goldfinch, Carduelis carduelis": 11,
+    "goldfish, Carassius auratus": 1,
+    "golf ball": 574,
+    "golfcart, golf cart": 575,
+    "gondola": 576,
+    "gong, tam-tam": 577,
+    "goose": 99,
+    "gorilla, Gorilla gorilla": 366,
+    "gown": 578,
+    "grand piano, grand": 579,
+    "grasshopper, hopper": 311,
+    "great grey owl, great gray owl, Strix nebulosa": 24,
+    "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias": 2,
+    "green lizard, Lacerta viridis": 46,
+    "green mamba": 64,
+    "green snake, grass snake": 55,
+    "greenhouse, nursery, glasshouse": 580,
+    "grey fox, gray fox, Urocyon cinereoargenteus": 280,
+    "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus": 147,
+    "grille, radiator grille": 581,
+    "grocery store, grocery, food market, market": 582,
+    "groenendael": 224,
+    "groom, bridegroom": 982,
+    "ground beetle, carabid beetle": 302,
+    "guacamole": 924,
+    "guenon, guenon monkey": 370,
+    "guillotine": 583,
+    "guinea pig, Cavia cobaya": 338,
+    "gyromitra": 993,
+    "hair slide": 584,
+    "hair spray": 585,
+    "half track": 586,
+    "hammer": 587,
+    "hammerhead, hammerhead shark": 4,
+    "hamper": 588,
+    "hamster": 333,
+    "hand blower, blow dryer, blow drier, hair dryer, hair drier": 589,
+    "hand-held computer, hand-held microcomputer": 590,
+    "handkerchief, hankie, hanky, hankey": 591,
+    "hard disc, hard disk, fixed disk": 592,
+    "hare": 331,
+    "harmonica, mouth organ, harp, mouth harp": 593,
+    "harp": 594,
+    "hartebeest": 351,
+    "harvester, reaper": 595,
+    "harvestman, daddy longlegs, Phalangium opilio": 70,
+    "hatchet": 596,
+    "hay": 958,
+    "head cabbage": 936,
+    "hen": 8,
+    "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa": 996,
+    "hermit crab": 125,
+    "hip, rose hip, rosehip": 989,
+    "hippopotamus, hippo, river horse, Hippopotamus amphibius": 344,
+    "hog, pig, grunter, squealer, Sus scrofa": 341,
+    "hognose snake, puff adder, sand viper": 54,
+    "holster": 597,
+    "home theater, home theatre": 598,
+    "honeycomb": 599,
+    "hook, claw": 600,
+    "hoopskirt, crinoline": 601,
+    "horizontal bar, high bar": 602,
+    "hornbill": 93,
+    "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus": 66,
+    "horse cart, horse-cart": 603,
+    "hot pot, hotpot": 926,
+    "hotdog, hot dog, red hot": 934,
+    "hourglass": 604,
+    "house finch, linnet, Carpodacus mexicanus": 12,
+    "howler monkey, howler": 379,
+    "hummingbird": 94,
+    "hyena, hyaena": 276,
+    "iPod": 605,
+    "ibex, Capra ibex": 350,
+    "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus": 296,
+    "ice cream, icecream": 928,
+    "ice lolly, lolly, lollipop, popsicle": 929,
+    "impala, Aepyceros melampus": 352,
+    "indigo bunting, indigo finch, indigo bird, Passerina cyanea": 14,
+    "indri, indris, Indri indri, Indri brevicaudatus": 384,
+    "iron, smoothing iron": 606,
+    "isopod": 126,
+    "jacamar": 95,
+    "jack-o'-lantern": 607,
+    "jackfruit, jak, jack": 955,
+    "jaguar, panther, Panthera onca, Felis onca": 290,
+    "jay": 17,
+    "jean, blue jean, denim": 608,
+    "jeep, landrover": 609,
+    "jellyfish": 107,
+    "jersey, T-shirt, tee shirt": 610,
+    "jigsaw puzzle": 611,
+    "jinrikisha, ricksha, rickshaw": 612,
+    "joystick": 613,
+    "junco, snowbird": 13,
+    "keeshond": 261,
+    "kelpie": 227,
+    "killer whale, killer, orca, grampus, sea wolf, Orcinus orca": 148,
+    "kimono": 614,
+    "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica": 121,
+    "king penguin, Aptenodytes patagonica": 145,
+    "king snake, kingsnake": 56,
+    "kit fox, Vulpes macrotis": 278,
+    "kite": 21,
+    "knee pad": 615,
+    "knot": 616,
+    "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus": 105,
+    "komondor": 228,
+    "kuvasz": 222,
+    "lab coat, laboratory coat": 617,
+    "lacewing, lacewing fly": 318,
+    "ladle": 618,
+    "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle": 301,
+    "lakeside, lakeshore": 975,
+    "lampshade, lamp shade": 619,
+    "langur": 374,
+    "laptop, laptop computer": 620,
+    "lawn mower, mower": 621,
+    "leaf beetle, chrysomelid": 304,
+    "leafhopper": 317,
+    "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea": 34,
+    "lemon": 951,
+    "lens cap, lens cover": 622,
+    "leopard, Panthera pardus": 288,
+    "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens": 387,
+    "letter opener, paper knife, paperknife": 623,
+    "library": 624,
+    "lifeboat": 625,
+    "lighter, light, igniter, ignitor": 626,
+    "limousine, limo": 627,
+    "limpkin, Aramus pictus": 135,
+    "liner, ocean liner": 628,
+    "lion, king of beasts, Panthera leo": 291,
+    "lionfish": 396,
+    "lipstick, lip rouge": 629,
+    "little blue heron, Egretta caerulea": 131,
+    "llama": 355,
+    "loggerhead, loggerhead turtle, Caretta caretta": 33,
+    "long-horned beetle, longicorn, longicorn beetle": 303,
+    "lorikeet": 90,
+    "lotion": 631,
+    "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system": 632,
+    "loupe, jeweler's loupe": 633,
+    "lumbermill, sawmill": 634,
+    "lycaenid, lycaenid butterfly": 326,
+    "lynx, catamount": 287,
+    "macaque": 373,
+    "macaw": 88,
+    "magnetic compass": 635,
+    "magpie": 18,
+    "mailbag, postbag": 636,
+    "mailbox, letter box": 637,
+    "maillot": 638,
+    "maillot, tank suit": 639,
+    "malamute, malemute, Alaskan malamute": 249,
+    "malinois": 225,
+    "manhole cover": 640,
+    "mantis, mantid": 315,
+    "maraca": 641,
+    "marimba, xylophone": 642,
+    "marmoset": 377,
+    "marmot": 336,
+    "mashed potato": 935,
+    "mask": 643,
+    "matchstick": 644,
+    "maypole": 645,
+    "maze, labyrinth": 646,
+    "measuring cup": 647,
+    "meat loaf, meatloaf": 962,
+    "medicine chest, medicine cabinet": 648,
+    "meerkat, mierkat": 299,
+    "megalith, megalithic structure": 649,
+    "menu": 922,
+    "microphone, mike": 650,
+    "microwave, microwave oven": 651,
+    "military uniform": 652,
+    "milk can": 653,
+    "miniature pinscher": 237,
+    "miniature poodle": 266,
+    "miniature schnauzer": 196,
+    "minibus": 654,
+    "miniskirt, mini": 655,
+    "minivan": 656,
+    "mink": 357,
+    "missile": 657,
+    "mitten": 658,
+    "mixing bowl": 659,
+    "mobile home, manufactured home": 660,
+    "modem": 662,
+    "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus": 323,
+    "monastery": 663,
+    "mongoose": 298,
+    "monitor": 664,
+    "moped": 665,
+    "mortar": 666,
+    "mortarboard": 667,
+    "mosque": 668,
+    "mosquito net": 669,
+    "motor scooter, scooter": 670,
+    "mountain bike, all-terrain bike, off-roader": 671,
+    "mountain tent": 672,
+    "mouse, computer mouse": 673,
+    "mousetrap": 674,
+    "moving van": 675,
+    "mud turtle": 35,
+    "mushroom": 947,
+    "muzzle": 676,
+    "nail": 677,
+    "neck brace": 678,
+    "necklace": 679,
+    "nematode, nematode worm, roundworm": 111,
+    "night snake, Hypsiglena torquata": 60,
+    "nipple": 680,
+    "notebook, notebook computer": 681,
+    "obelisk": 682,
+    "oboe, hautboy, hautbois": 683,
+    "ocarina, sweet potato": 684,
+    "odometer, hodometer, mileometer, milometer": 685,
+    "oil filter": 686,
+    "orange": 950,
+    "orangutan, orang, orangutang, Pongo pygmaeus": 365,
+    "organ, pipe organ": 687,
+    "oscilloscope, scope, cathode-ray oscilloscope, CRO": 688,
+    "ostrich, Struthio camelus": 9,
+    "otter": 360,
+    "otterhound, otter hound": 175,
+    "overskirt": 689,
+    "ox": 345,
+    "oxcart": 690,
+    "oxygen mask": 691,
+    "oystercatcher, oyster catcher": 143,
+    "packet": 692,
+    "paddle, boat paddle": 693,
+    "paddlewheel, paddle wheel": 694,
+    "padlock": 695,
+    "paintbrush": 696,
+    "pajama, pyjama, pj's, jammies": 697,
+    "palace": 698,
+    "panpipe, pandean pipe, syrinx": 699,
+    "paper towel": 700,
+    "papillon": 157,
+    "parachute, chute": 701,
+    "parallel bars, bars": 702,
+    "park bench": 703,
+    "parking meter": 704,
+    "partridge": 86,
+    "passenger car, coach, carriage": 705,
+    "patas, hussar monkey, Erythrocebus patas": 371,
+    "patio, terrace": 706,
+    "pay-phone, pay-station": 707,
+    "peacock": 84,
+    "pedestal, plinth, footstall": 708,
+    "pelican": 144,
+    "pencil box, pencil case": 709,
+    "pencil sharpener": 710,
+    "perfume, essence": 711,
+    "photocopier": 713,
+    "pick, plectrum, plectron": 714,
+    "pickelhaube": 715,
+    "picket fence, paling": 716,
+    "pickup, pickup truck": 717,
+    "pier": 718,
+    "piggy bank, penny bank": 719,
+    "pill bottle": 720,
+    "pillow": 721,
+    "pineapple, ananas": 953,
+    "ping-pong ball": 722,
+    "pinwheel": 723,
+    "pirate, pirate ship": 724,
+    "pitcher, ewer": 725,
+    "pizza, pizza pie": 963,
+    "plane, carpenter's plane, woodworking plane": 726,
+    "planetarium": 727,
+    "plastic bag": 728,
+    "plate": 923,
+    "plate rack": 729,
+    "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus": 103,
+    "plow, plough": 730,
+    "plunger, plumber's helper": 731,
+    "pole": 733,
+    "polecat, fitch, foulmart, foumart, Mustela putorius": 358,
+    "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria": 734,
+    "pomegranate": 957,
+    "poncho": 735,
+    "pool table, billiard table, snooker table": 736,
+    "pop bottle, soda bottle": 737,
+    "porcupine, hedgehog": 334,
+    "pot, flowerpot": 738,
+    "potpie": 964,
+    "potter's wheel": 739,
+    "power drill": 740,
+    "prairie chicken, prairie grouse, prairie fowl": 83,
+    "prayer rug, prayer mat": 741,
+    "pretzel": 932,
+    "printer": 742,
+    "prison, prison house": 743,
+    "proboscis monkey, Nasalis larvatus": 376,
+    "projectile, missile": 744,
+    "projector": 745,
+    "promontory, headland, head, foreland": 976,
+    "ptarmigan": 81,
+    "puck, hockey puck": 746,
+    "puffer, pufferfish, blowfish, globefish": 397,
+    "pug, pug-dog": 254,
+    "punching bag, punch bag, punching ball, punchball": 747,
+    "purse": 748,
+    "quail": 85,
+    "quill, quill pen": 749,
+    "quilt, comforter, comfort, puff": 750,
+    "racer, race car, racing car": 751,
+    "racket, racquet": 752,
+    "radiator": 753,
+    "radio telescope, radio reflector": 755,
+    "radio, wireless": 754,
+    "rain barrel": 756,
+    "ram, tup": 348,
+    "rapeseed": 984,
+    "recreational vehicle, RV, R.V.": 757,
+    "red fox, Vulpes vulpes": 277,
+    "red wine": 966,
+    "red wolf, maned wolf, Canis rufus, Canis niger": 271,
+    "red-backed sandpiper, dunlin, Erolia alpina": 140,
+    "red-breasted merganser, Mergus serrator": 98,
+    "redbone": 168,
+    "redshank, Tringa totanus": 141,
+    "reel": 758,
+    "reflex camera": 759,
+    "refrigerator, icebox": 760,
+    "remote control, remote": 761,
+    "restaurant, eating house, eating place, eatery": 762,
+    "revolver, six-gun, six-shooter": 763,
+    "rhinoceros beetle": 306,
+    "rifle": 764,
+    "ringlet, ringlet butterfly": 322,
+    "ringneck snake, ring-necked snake, ring snake": 53,
+    "robin, American robin, Turdus migratorius": 15,
+    "rock beauty, Holocanthus tricolor": 392,
+    "rock crab, Cancer irroratus": 119,
+    "rock python, rock snake, Python sebae": 62,
+    "rocking chair, rocker": 765,
+    "rotisserie": 766,
+    "rubber eraser, rubber, pencil eraser": 767,
+    "ruddy turnstone, Arenaria interpres": 139,
+    "ruffed grouse, partridge, Bonasa umbellus": 82,
+    "rugby ball": 768,
+    "rule, ruler": 769,
+    "running shoe": 770,
+    "safe": 771,
+    "safety pin": 772,
+    "saltshaker, salt shaker": 773,
+    "sandal": 774,
+    "sandbar, sand bar": 977,
+    "sarong": 775,
+    "sax, saxophone": 776,
+    "scabbard": 777,
+    "scale, weighing machine": 778,
+    "schipperke": 223,
+    "school bus": 779,
+    "schooner": 780,
+    "scoreboard": 781,
+    "scorpion": 71,
+    "screen, CRT screen": 782,
+    "screw": 783,
+    "screwdriver": 784,
+    "scuba diver": 983,
+    "sea anemone, anemone": 108,
+    "sea cucumber, holothurian": 329,
+    "sea lion": 150,
+    "sea slug, nudibranch": 115,
+    "sea snake": 65,
+    "sea urchin": 328,
+    "seashore, coast, seacoast, sea-coast": 978,
+    "seat belt, seatbelt": 785,
+    "sewing machine": 786,
+    "shield, buckler": 787,
+    "shoe shop, shoe-shop, shoe store": 788,
+    "shoji": 789,
+    "shopping basket": 790,
+    "shopping cart": 791,
+    "shovel": 792,
+    "shower cap": 793,
+    "shower curtain": 794,
+    "siamang, Hylobates syndactylus, Symphalangus syndactylus": 369,
+    "sidewinder, horned rattlesnake, Crotalus cerastes": 68,
+    "silky terrier, Sydney silky": 201,
+    "ski": 795,
+    "ski mask": 796,
+    "skunk, polecat, wood pussy": 361,
+    "sleeping bag": 797,
+    "slide rule, slipstick": 798,
+    "sliding door": 799,
+    "slot, one-armed bandit": 800,
+    "sloth bear, Melursus ursinus, Ursus ursinus": 297,
+    "slug": 114,
+    "snail": 113,
+    "snorkel": 801,
+    "snow leopard, ounce, Panthera uncia": 289,
+    "snowmobile": 802,
+    "snowplow, snowplough": 803,
+    "soap dispenser": 804,
+    "soccer ball": 805,
+    "sock": 806,
+    "soft-coated wheaten terrier": 202,
+    "solar dish, solar collector, solar furnace": 807,
+    "sombrero": 808,
+    "sorrel": 339,
+    "soup bowl": 809,
+    "space bar": 810,
+    "space heater": 811,
+    "space shuttle": 812,
+    "spaghetti squash": 940,
+    "spatula": 813,
+    "speedboat": 814,
+    "spider monkey, Ateles geoffroyi": 381,
+    "spider web, spider's web": 815,
+    "spindle": 816,
+    "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish": 123,
+    "spoonbill": 129,
+    "sports car, sport car": 817,
+    "spotlight, spot": 818,
+    "spotted salamander, Ambystoma maculatum": 28,
+    "squirrel monkey, Saimiri sciureus": 382,
+    "stage": 819,
+    "standard poodle": 267,
+    "standard schnauzer": 198,
+    "starfish, sea star": 327,
+    "steam locomotive": 820,
+    "steel arch bridge": 821,
+    "steel drum": 822,
+    "stethoscope": 823,
+    "stingray": 6,
+    "stinkhorn, carrion fungus": 994,
+    "stole": 824,
+    "stone wall": 825,
+    "stopwatch, stop watch": 826,
+    "stove": 827,
+    "strainer": 828,
+    "strawberry": 949,
+    "street sign": 919,
+    "streetcar, tram, tramcar, trolley, trolley car": 829,
+    "stretcher": 830,
+    "studio couch, day bed": 831,
+    "stupa, tope": 832,
+    "sturgeon": 394,
+    "submarine, pigboat, sub, U-boat": 833,
+    "suit, suit of clothes": 834,
+    "sulphur butterfly, sulfur butterfly": 325,
+    "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita": 89,
+    "sundial": 835,
+    "sunglass": 836,
+    "sunglasses, dark glasses, shades": 837,
+    "sunscreen, sunblock, sun blocker": 838,
+    "suspension bridge": 839,
+    "swab, swob, mop": 840,
+    "sweatshirt": 841,
+    "swimming trunks, bathing trunks": 842,
+    "swing": 843,
+    "switch, electric switch, electrical switch": 844,
+    "syringe": 845,
+    "tabby, tabby cat": 281,
+    "table lamp": 846,
+    "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui": 32,
+    "tank, army tank, armored combat vehicle, armoured combat vehicle": 847,
+    "tape player": 848,
+    "tarantula": 76,
+    "teapot": 849,
+    "teddy, teddy bear": 850,
+    "television, television system": 851,
+    "tench, Tinca tinca": 0,
+    "tennis ball": 852,
+    "terrapin": 36,
+    "thatch, thatched roof": 853,
+    "theater curtain, theatre curtain": 854,
+    "thimble": 855,
+    "three-toed sloth, ai, Bradypus tridactylus": 364,
+    "thresher, thrasher, threshing machine": 856,
+    "throne": 857,
+    "thunder snake, worm snake, Carphophis amoenus": 52,
+    "tick": 78,
+    "tiger beetle": 300,
+    "tiger cat": 282,
+    "tiger shark, Galeocerdo cuvieri": 3,
+    "tiger, Panthera tigris": 292,
+    "tile roof": 858,
+    "timber wolf, grey wolf, gray wolf, Canis lupus": 269,
+    "titi, titi monkey": 380,
+    "toaster": 859,
+    "tobacco shop, tobacconist shop, tobacconist": 860,
+    "toilet seat": 861,
+    "toilet tissue, toilet paper, bathroom tissue": 999,
+    "torch": 862,
+    "totem pole": 863,
+    "toucan": 96,
+    "tow truck, tow car, wrecker": 864,
+    "toy poodle": 265,
+    "toy terrier": 158,
+    "toyshop": 865,
+    "tractor": 866,
+    "traffic light, traffic signal, stoplight": 920,
+    "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi": 867,
+    "tray": 868,
+    "tree frog, tree-frog": 31,
+    "trench coat": 869,
+    "triceratops": 51,
+    "tricycle, trike, velocipede": 870,
+    "trifle": 927,
+    "trilobite": 69,
+    "trimaran": 871,
+    "tripod": 872,
+    "triumphal arch": 873,
+    "trolleybus, trolley coach, trackless trolley": 874,
+    "trombone": 875,
+    "tub, vat": 876,
+    "turnstile": 877,
+    "tusker": 101,
+    "typewriter keyboard": 878,
+    "umbrella": 879,
+    "unicycle, monocycle": 880,
+    "upright, upright piano": 881,
+    "vacuum, vacuum cleaner": 882,
+    "valley, vale": 979,
+    "vase": 883,
+    "vault": 884,
+    "velvet": 885,
+    "vending machine": 886,
+    "vestment": 887,
+    "viaduct": 888,
+    "vine snake": 59,
+    "violin, fiddle": 889,
+    "vizsla, Hungarian pointer": 211,
+    "volcano": 980,
+    "volleyball": 890,
+    "vulture": 23,
+    "waffle iron": 891,
+    "walking stick, walkingstick, stick insect": 313,
+    "wall clock": 892,
+    "wallaby, brush kangaroo": 104,
+    "wallet, billfold, notecase, pocketbook": 893,
+    "wardrobe, closet, press": 894,
+    "warplane, military plane": 895,
+    "warthog": 343,
+    "washbasin, handbasin, washbowl, lavabo, wash-hand basin": 896,
+    "washer, automatic washer, washing machine": 897,
+    "water bottle": 898,
+    "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis": 346,
+    "water jug": 899,
+    "water ouzel, dipper": 20,
+    "water snake": 58,
+    "water tower": 900,
+    "weasel": 356,
+    "web site, website, internet site, site": 916,
+    "weevil": 307,
+    "whippet": 172,
+    "whiptail, whiptail lizard": 41,
+    "whiskey jug": 901,
+    "whistle": 902,
+    "white stork, Ciconia ciconia": 127,
+    "white wolf, Arctic wolf, Canis lupus tundrarum": 270,
+    "wig": 903,
+    "wild boar, boar, Sus scrofa": 342,
+    "window screen": 904,
+    "window shade": 905,
+    "wine bottle": 907,
+    "wing": 908,
+    "wire-haired fox terrier": 188,
+    "wok": 909,
+    "wolf spider, hunting spider": 77,
+    "wombat": 106,
+    "wood rabbit, cottontail, cottontail rabbit": 330,
+    "wooden spoon": 910,
+    "wool, woolen, woollen": 911,
+    "worm fence, snake fence, snake-rail fence, Virginia fence": 912,
+    "wreck": 913,
+    "yawl": 914,
+    "yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum": 986,
+    "yurt": 915,
+    "zebra": 340,
+    "zucchini, courgette": 939
+  },
+  "num_classes": 1000,
+  "mlp_ratio": 4.0,
+  "model_type": "fdvit",
+  "in_channels": 3,
+  "out_size": [
+    31,
+    22,
+    16,
+    11,
+    8
+  ],
+  "patch_size": 14,
+  "channels": [
+    256,
+    360,
+    512,
+    720,
+    1024
+  ],
+  "stride": 7,
+  "base_dims": [
+    64,
+    45,
+    64,
+    45,
+    64
+  ],
+  "attn_drop_rate": 0.0,
+  "drop_rate": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_cache": true,
+  "use_layer_scale": true
+}

configuration_fdvit.py

@@ -0,0 +1,136 @@
+# Copyright (c) 2024 Advanced Micro Devices, Inc. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License") and the MIT License (the "License2");
+
+""" FDViT model configuration"""
+
+from collections import OrderedDict
+from typing import Mapping
+
+from packaging import version
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.onnx import OnnxConfig
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+
+#from ..deprecated._archive_maps import VIT_PRETRAINED_CONFIG_ARCHIVE_MAP  # noqa: F401, E402
+
+
+class FDViTConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`FDViTModel`]. It is used to instantiate an FDViT
+    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
+    defaults will yield a similar configuration to that of the FDViT
+    [amd/fdvit_ti](https://huggingface.co/amd/fdvit_ti) architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+
+    Args:
+        image_size (`int`, *optional*, defaults to 224):
+            The size (resolution) of each image.
+        patch_size (`int`, *optional*, defaults to 16):
+            The size of the input patch.
+        stride (`int`, *optional*, defaults to 16):
+            The stride of the input patch.
+        base_dims (`list`, *optional*, defaults to `[32, 23, 21, 23, 26]`):
+            The basic dimension of each encoder block.
+        depth (`list`, *optional*, defaults to `[2, 3, 3, 2, 2]`):
+            The depth of each encoder block.
+        heads (`list`, *optional*, defaults to `[2, 4, 6, 8, 10]`):
+            The depth of each encoder block.
+        channels (`list`, *optional*, defaults to `[64, 92, 126, 184, 260]`):
+            The depth of each encoder block.
+        out_size (`list`, *optional*, defaults to `[27, 19, 14, 10, 7]`):
+            The output size of each encoder block.
+        mlp_ratio (`float`, *optional*, defaults to 4.0):
+            The ratio of the number of channels in the output of the MLP to the number of channels in the input.
+        num_classes (`int`, *optional*, defaults to 1000):
+            The number of classes of the dataset.
+        in_chans (`int`, *optional*, defaults to 3):
+            The number of channels in the input image.
+        attn_drop_rate (`float`, *optional*, defaults to 0.0):
+            The attention drop rate for the attention dropout layers.
+        drop_rate (`float`, *optional*, defaults to 0.0):
+            The dropout rate for the dropout layers.
+        drop_path_rate (`float`, *optional*, defaults to 0.1):
+            The droppath rate for the droppath layers.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The initializer range for the weights.
+
+
+    Example:
+
+    ```python
+    >>> from transformers import FDViTConfig, FDViTModel
+
+    >>> # Initializing a FDViT fdvit_ti style configuration
+    >>> configuration = FDViTConfig()
+
+    >>> # Initializing a model (with random weights) from the fdvit_ti style configuration
+    >>> model = FDViTModel(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "fdvit"
+
+    def __init__(
+        self,
+        image_size=224,
+        patch_size=16,
+        stride=8,
+        base_dims=[32, 23, 21, 23, 26],
+        depth=[2, 3, 3, 2, 2],
+        heads=[2, 4, 6, 8, 10],
+        channels=[64,92,126,184,260],
+        out_size=[27, 19, 14, 10, 7],
+        mlp_ratio=4,
+        num_classes=1000,
+        in_chans=3,
+        attn_drop_rate=0.0,
+        drop_rate=0.0,
+        drop_path_rate=0.1,
+        initializer_range=0.02,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.image_size = image_size
+        self.patch_size = patch_size
+        self.stride = stride
+        self.base_dims = base_dims
+        self.depth = depth
+        self.heads = heads
+        self.channels = channels
+        self.out_size = out_size
+        self.mlp_ratio = mlp_ratio
+        self.num_classes = num_classes
+        self.in_chans = in_chans
+        self.attn_drop_rate = attn_drop_rate
+        self.drop_rate = drop_rate
+        self.drop_path_rate = drop_path_rate
+        self.initializer_range = initializer_range
+        
+
+
+class FDViTOnnxConfig(OnnxConfig):
+    torch_onnx_minimum_version = version.parse("1.11")
+
+    @property
+    def inputs(self) -> Mapping[str, Mapping[int, str]]:
+        return OrderedDict(
+            [
+                ("pixel_values", {0: "batch", 1: "num_channels", 2: "height", 3: "width"}),
+            ]
+        )
+
+    @property
+    def atol_for_validation(self) -> float:
+        return 1e-4

modeling_fdvit.py

@@ -0,0 +1,519 @@
+# Copyright (c) 2024 Advanced Micro Devices, Inc. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License") and the MIT License (the "License2");
+
+""" PyTorch ViT model."""
+
+
+from functools import partial
+from einops import rearrange
+import torch.nn.functional as F
+
+import collections.abc
+import math
+from typing import Dict, List, Optional, Set, Tuple, Union
+
+import torch
+import torch.utils.checkpoint
+from torch import nn
+from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
+
+from transformers.activations import ACT2FN
+from transformers.modeling_outputs import (
+    BaseModelOutput,
+    BaseModelOutputWithPooling,
+    ImageClassifierOutput,
+    MaskedImageModelingOutput,
+    BaseModelOutputWithNoAttention,
+    ImageClassifierOutputWithNoAttention,
+)
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import (
+    add_code_sample_docstrings,
+    add_start_docstrings,
+    add_start_docstrings_to_model_forward,
+    logging,
+    replace_return_docstrings,
+)
+from .configuration_fdvit import FDViTConfig
+
+
+logger = logging.get_logger(__name__)
+
+# General docstring
+_CONFIG_FOR_DOC = "FDViTConfig"
+
+# Base docstring
+_CHECKPOINT_FOR_DOC = "amd/fdvit_ti"
+_EXPECTED_OUTPUT_SHAPE = [1, 49, 260]
+
+# Image classification docstring
+_IMAGE_CLASS_CHECKPOINT = "amd/fdvit_ti"
+_IMAGE_CLASS_EXPECTED_OUTPUT = "Egyptian cat"
+
+
+#from ..deprecated._archive_maps import VIT_PRETRAINED_MODEL_ARCHIVE_LIST  # noqa: F401, E402
+
+def drop_path(x, drop_prob: float = 0., training: bool = False, scale_by_keep: bool = True):
+    """Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
+
+    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
+    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
+    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
+    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
+    'survival rate' as the argument.
+
+    """
+    if drop_prob == 0. or not training:
+        return x
+    keep_prob = 1 - drop_prob
+    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
+    random_tensor = x.new_empty(shape).bernoulli_(keep_prob)
+    if keep_prob > 0.0 and scale_by_keep:
+        random_tensor.div_(keep_prob)
+    return x * random_tensor
+
+
+class FDViTDropPath(nn.Module):
+    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
+    """
+    def __init__(self, drop_prob: float = 0., scale_by_keep: bool = True):
+        super().__init__()
+        self.drop_prob = drop_prob
+        self.scale_by_keep = scale_by_keep
+
+    def forward(self, x):
+        return drop_path(x, self.drop_prob, self.training, self.scale_by_keep)
+
+    def extra_repr(self):
+        return f'drop_prob={round(self.drop_prob,3):0.3f}'
+
+
+class FDViTEmbeddings(nn.Module):
+    """
+    Construct Patch Embeddings.
+    """
+
+    def __init__(self, in_channels, out_channels, patch_size, stride, padding):
+        super().__init__()
+        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=patch_size,
+                              stride=stride, padding=padding, bias=True)
+
+    def forward(self, x):
+        x = self.conv(x)
+        return x
+
+
+class FDViTAttention(nn.Module):
+    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.):
+        super().__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
+        self.scale = qk_scale or head_dim ** -0.5
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+        self.get_v = nn.Conv2d(dim, dim, kernel_size=3, stride=1, padding=1, groups=dim)
+
+    def get_lepe(self, x):
+        B, Head, N, C_p = x.shape
+        H = W = int(math.sqrt(N))
+        x = x.transpose(-2,-1).contiguous().view(B, C_p*Head, H, W)
+
+        lepe = self.get_v(x)
+        lepe = lepe.reshape(B, Head, C_p, N).permute(0, 1, 3, 2).contiguous()
+        x = x.reshape(B, Head, C_p, N).permute(0, 1, 3, 2).contiguous()
+        return x, lepe
+
+    def forward(self, x):
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]   # make torchscript happy (cannot use tensor as tuple)
+        v, lepe = self.get_lepe(v)
+
+        attn = (q @ k.transpose(-2, -1)) * self.scale
+        attn = attn.softmax(dim=-1)
+        attn = self.attn_drop(attn)
+
+        x = (attn @ v) + lepe
+        x = x.transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+
+class FDViTOutput(nn.Module):
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class Block(nn.Module):
+
+    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
+                 drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm):
+        super().__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = FDViTAttention(
+            dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
+        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
+        self.drop_path = FDViTDropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = FDViTOutput(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+    def forward(self, x):
+        x = x + self.drop_path(self.attn(self.norm1(x)))
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+        return x
+
+
+class FDViTLayer(nn.Module):
+    def __init__(self, base_dim, depth, heads, mlp_ratio,
+                 drop_rate=.0, attn_drop_rate=.0, drop_path_prob=None):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        embed_dim = base_dim * heads
+
+        if drop_path_prob is None:
+            drop_path_prob = [0.0 for _ in range(depth)]
+
+        self.blocks = nn.ModuleList([
+            Block(
+                dim=embed_dim,
+                num_heads=heads,
+                mlp_ratio=mlp_ratio,
+                qkv_bias=True,
+                drop=drop_rate,
+                attn_drop=attn_drop_rate,
+                drop_path=drop_path_prob[i],
+                norm_layer=partial(nn.LayerNorm, eps=1e-6)
+            )
+            for i in range(depth)])
+
+    def forward(self, x):
+        h, w = x.shape[2:4]
+        x = rearrange(x, 'b c h w -> b (h w) c')
+        for blk in self.blocks:
+            x = blk(x)
+
+        return x
+
+
+class FDViTPooling(nn.Module):
+    def __init__(self, in_feature, out_feature, out_size):
+        super().__init__()
+
+        d = torch.linspace(-1, 1, out_size)
+        meshx, meshy = torch.meshgrid((d, d))
+        self.grid = torch.stack((meshy, meshx), 2)
+
+        self.conv = nn.Conv2d(in_feature, out_feature, kernel_size=3,
+                              padding=1, stride=1)
+        self.ln = nn.LayerNorm(in_feature)
+
+    def forward(self, x):
+        h = w = int(math.sqrt(x.shape[1]))
+        x = self.ln(x)
+        x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w)
+
+        grid = self.grid.expand(x.shape[0], -1, -1, -1)
+        x = F.grid_sample(x, grid.to(x.device).type_as(x),align_corners=True)
+        x = self.conv(x)
+
+
+        return x
+
+class FDViTEncoder(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+   
+        self.config = config
+        image_size, patch_size, stride, base_dims, depth, heads, channels, out_size, mlp_ratio = config.image_size, config.patch_size, config.stride, config.base_dims, config.depth, config.heads, config.channels, config.out_size, config.mlp_ratio
+        num_classes = config.num_classes if config.num_classes is not None else 1000
+        in_chans = config.in_chans if config.in_chans is not None else 3
+        attn_drop_rate = config.attn_drop_rate if config.attn_drop_rate is not None else .0
+        drop_rate = config.drop_rate if config.drop_rate is not None else .0
+        drop_path_rate = config.drop_path_rate if config.drop_path_rate is not None else .0
+
+
+        total_block = sum(depth)
+        padding = 0
+        block_idx = 0
+
+        width = math.floor(
+            (image_size + 2 * padding - patch_size) / stride + 1)
+
+        self.base_dims = base_dims
+        self.heads = heads
+        self.num_classes = num_classes
+
+        self.patch_size = patch_size
+        self.pos_embed = nn.Parameter(
+            torch.randn(1, base_dims[0] * heads[0], width, width),
+            requires_grad=True
+        )
+        self.patch_embed = FDViTEmbeddings(in_chans, base_dims[0] * heads[0],
+                                          patch_size, stride, padding)
+
+        self.pos_drop = nn.Dropout(p=drop_rate)
+
+        self.transformers = nn.ModuleList([])
+        self.pools = nn.ModuleList([])
+        self.decoders = nn.ModuleList([])
+
+        for stage in range(len(depth)):
+            drop_path_prob = [drop_path_rate * i / total_block
+                              for i in range(block_idx, block_idx + depth[stage])]
+            block_idx += depth[stage]
+
+            self.transformers.append(
+                FDViTLayer(base_dims[stage], depth[stage], heads[stage],
+                            mlp_ratio,
+                            drop_rate, attn_drop_rate, drop_path_prob)
+            )
+            if stage < len(heads) - 1:
+                self.pools.append(
+                    FDViTPooling(channels[stage],
+                                      channels[stage+1],
+                                      out_size[stage+1]
+                                      )
+                )
+
+        self.embed_dim = base_dims[-1] * heads[-1]
+
+
+    def forward(self, x, output_hidden_states=False, return_dict=True):
+        all_hidden_states = () if output_hidden_states else None
+
+        x = self.patch_embed(x)
+
+        pos_embed = self.pos_embed
+        x = self.pos_drop(x + pos_embed)
+
+        for stage in range(len(self.pools)):
+            xt = self.transformers[stage](x)
+            x = self.pools[stage](xt)
+
+            if output_hidden_states:
+                all_hidden_states = all_hidden_states + (xt,)
+
+        x = self.transformers[-1](x)
+        if output_hidden_states:
+            all_hidden_states = all_hidden_states + (x,)
+
+        if not return_dict:
+            return tuple(v for v in [x, all_hidden_states] if v is not None)
+
+        return BaseModelOutputWithNoAttention(last_hidden_state=x, hidden_states=all_hidden_states)
+        # x = self.norm(x)
+        # return x.mean(dim=1)
+
+
+class FDViTPreTrainedModel(PreTrainedModel):
+    """
+    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
+    models.
+    """
+
+    config_class = FDViTConfig
+    base_model_prefix = "fdvit"
+    main_input_name = "pixel_values"
+
+    def _init_weights(self, module):
+        """Initialize the weights"""
+        if isinstance(module, (nn.Linear, nn.Conv2d)):
+            module.weight.data.normal_(mean=0.0, std=self.config.initializer_range)
+            if module.bias is not None:
+                module.bias.data.zero_()
+        elif isinstance(module, nn.LayerNorm):
+            module.bias.data.zero_()
+            module.weight.data.fill_(1.0)
+
+
+FDVIT_START_DOCSTRING = r"""
+    This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it
+    as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and
+    behavior.
+
+    Parameters:
+        config ([`FDViTConfig`]): Model configuration class with all the parameters of the model.
+            Initializing with a config file does not load the weights associated with the model, only the
+            configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.
+"""
+
+FDVIT_INPUTS_DOCSTRING = r"""
+    Args:
+        pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
+            Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See [`FDViTImageProcessor.__call__`]
+            for details.
+"""
+
+
+@add_start_docstrings(
+    "The bare FDViT Model transformer outputting raw hidden-states without any specific head on top.",
+    FDVIT_START_DOCSTRING,
+)
+class FDViTModel(FDViTPreTrainedModel):
+    def __init__(self, config: FDViTConfig):
+        super().__init__(config)
+        self.config = config
+
+        self.encoder = FDViTEncoder(config)
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @add_start_docstrings_to_model_forward(FDVIT_INPUTS_DOCSTRING)
+    @add_code_sample_docstrings(
+        checkpoint=_CHECKPOINT_FOR_DOC,
+        output_type=BaseModelOutputWithNoAttention,
+        config_class=_CONFIG_FOR_DOC,
+        modality="vision",
+        expected_output=_EXPECTED_OUTPUT_SHAPE,
+    )
+    def forward(
+        self,
+        pixel_values: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, BaseModelOutputWithNoAttention]:
+
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if pixel_values is None:
+            raise ValueError("You have to specify pixel_values")
+
+        encoder_outputs = self.encoder(
+            pixel_values,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+        sequence_output = encoder_outputs[0]
+
+        if not return_dict:
+            return (sequence_output, None) + encoder_outputs[1:]
+
+        return BaseModelOutputWithNoAttention(
+            last_hidden_state=sequence_output,
+            hidden_states=encoder_outputs.hidden_states,
+        )
+
+
+class FDViTPooler(nn.Module):
+    def __init__(self, config: FDViTConfig):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.activation = nn.Tanh()
+
+    def forward(self, hidden_states):
+        # We "pool" the model by simply taking the hidden state corresponding
+        # to the first token.
+        pooled_output = self.dense(first_token_tensor)
+        pooled_output = self.activation(pooled_output)
+        return pooled_output
+
+
+@add_start_docstrings(
+    """
+    FDViT Model transformer with an image classification head on top (a linear layer on top of the final hidden state of
+    the [CLS] token) e.g. for ImageNet.
+    """,
+    FDVIT_START_DOCSTRING,
+)
+class FDViTForImageClassification(FDViTPreTrainedModel):
+    def __init__(self, config: FDViTConfig) -> None:
+        super().__init__(config)
+
+        self.num_labels = config.num_labels
+        self.fdvit = FDViTModel(config)
+
+        # Final norm
+        self.norm = nn.LayerNorm(config.base_dims[-1] * config.heads[-1], eps=1e-6)
+        # Classifier head
+        self.classifier = nn.Linear(config.base_dims[-1] * config.heads[-1], config.num_classes) if config.num_classes > 0 else nn.Identity()
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @add_start_docstrings_to_model_forward(FDVIT_INPUTS_DOCSTRING)
+    @add_code_sample_docstrings(
+        checkpoint=_IMAGE_CLASS_CHECKPOINT,
+        output_type=ImageClassifierOutputWithNoAttention,
+        config_class=_CONFIG_FOR_DOC,
+        expected_output=_IMAGE_CLASS_EXPECTED_OUTPUT,
+    )
+    def forward(
+        self,
+        pixel_values: Optional[torch.Tensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[tuple, ImageClassifierOutputWithNoAttention]:
+        r"""
+        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
+            Labels for computing the image classification/regression loss. Indices should be in `[0, ...,
+            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
+            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
+        """
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        outputs = self.fdvit(
+            pixel_values,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+
+        sequence_output = outputs[0]
+
+        logits = self.classifier(self.norm(sequence_output).mean(dim=1))
+
+        loss = None
+        if labels is not None:
+            # move labels to correct device to enable model parallelism
+            labels = labels.to(logits.device)
+            if self.config.problem_type is None:
+                if self.num_labels == 1:
+                    self.config.problem_type = "regression"
+                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
+                    self.config.problem_type = "single_label_classification"
+                else:
+                    self.config.problem_type = "multi_label_classification"
+
+            if self.config.problem_type == "regression":
+                loss_fct = MSELoss()
+                if self.num_labels == 1:
+                    loss = loss_fct(logits.squeeze(), labels.squeeze())
+                else:
+                    loss = loss_fct(logits, labels)
+            elif self.config.problem_type == "single_label_classification":
+                loss_fct = CrossEntropyLoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
+            elif self.config.problem_type == "multi_label_classification":
+                loss_fct = BCEWithLogitsLoss()
+                loss = loss_fct(logits, labels)
+
+        if not return_dict:
+            output = (logits,) + outputs[1:]
+            return ((loss,) + output) if loss is not None else output
+
+        return ImageClassifierOutputWithNoAttention(loss=loss, logits=logits, hidden_states=outputs.hidden_states)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4659658be88a4434422ccaed9384093d03c9a398c92f3d0ba7ae7a5aeeeeb51
+size 272463523