add model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "perceiver_image_classifier",
+  "_name_or_path": "deepmind/vision-perceiver-learned",
   "architectures": [
     "PerceiverForImageClassificationLearned"
   ],
@@ -11,30 +11,210 @@
   "d_model": 512,
   "hidden_act": "gelu",
   "id2label": {
-    "0": "airplane",
-    "1": "automobile",
-    "2": "bird",
-    "3": "cat",
-    "4": "deer",
-    "5": "dog",
-    "6": "frog",
-    "7": "horse",
-    "8": "ship",
-    "9": "truck"
+    "0": "apple",
+    "1": "aquarium_fish",
+    "2": "baby",
+    "3": "bear",
+    "4": "beaver",
+    "5": "bed",
+    "6": "bee",
+    "7": "beetle",
+    "8": "bicycle",
+    "9": "bottle",
+    "10": "bowl",
+    "11": "boy",
+    "12": "bridge",
+    "13": "bus",
+    "14": "butterfly",
+    "15": "camel",
+    "16": "can",
+    "17": "castle",
+    "18": "caterpillar",
+    "19": "cattle",
+    "20": "chair",
+    "21": "chimpanzee",
+    "22": "clock",
+    "23": "cloud",
+    "24": "cockroach",
+    "25": "couch",
+    "26": "cra",
+    "27": "crocodile",
+    "28": "cup",
+    "29": "dinosaur",
+    "30": "dolphin",
+    "31": "elephant",
+    "32": "flatfish",
+    "33": "forest",
+    "34": "fox",
+    "35": "girl",
+    "36": "hamster",
+    "37": "house",
+    "38": "kangaroo",
+    "39": "keyboard",
+    "40": "lamp",
+    "41": "lawn_mower",
+    "42": "leopard",
+    "43": "lion",
+    "44": "lizard",
+    "45": "lobster",
+    "46": "man",
+    "47": "maple_tree",
+    "48": "motorcycle",
+    "49": "mountain",
+    "50": "mouse",
+    "51": "mushroom",
+    "52": "oak_tree",
+    "53": "orange",
+    "54": "orchid",
+    "55": "otter",
+    "56": "palm_tree",
+    "57": "pear",
+    "58": "pickup_truck",
+    "59": "pine_tree",
+    "60": "plain",
+    "61": "plate",
+    "62": "poppy",
+    "63": "porcupine",
+    "64": "possum",
+    "65": "rabbit",
+    "66": "raccoon",
+    "67": "ray",
+    "68": "road",
+    "69": "rocket",
+    "70": "rose",
+    "71": "sea",
+    "72": "seal",
+    "73": "shark",
+    "74": "shrew",
+    "75": "skunk",
+    "76": "skyscraper",
+    "77": "snail",
+    "78": "snake",
+    "79": "spider",
+    "80": "squirrel",
+    "81": "streetcar",
+    "82": "sunflower",
+    "83": "sweet_pepper",
+    "84": "table",
+    "85": "tank",
+    "86": "telephone",
+    "87": "television",
+    "88": "tiger",
+    "89": "tractor",
+    "90": "train",
+    "91": "trout",
+    "92": "tulip",
+    "93": "turtle",
+    "94": "wardrobe",
+    "95": "whale",
+    "96": "willow_tree",
+    "97": "wolf",
+    "98": "woman",
+    "99": "worm"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "label2id": {
-    "airplane": 0,
-    "automobile": 1,
-    "bird": 2,
-    "cat": 3,
-    "deer": 4,
-    "dog": 5,
-    "frog": 6,
-    "horse": 7,
-    "ship": 8,
-    "truck": 9
+    "apple": 0,
+    "aquarium_fish": 1,
+    "baby": 2,
+    "bear": 3,
+    "beaver": 4,
+    "bed": 5,
+    "bee": 6,
+    "beetle": 7,
+    "bicycle": 8,
+    "bottle": 9,
+    "bowl": 10,
+    "boy": 11,
+    "bridge": 12,
+    "bus": 13,
+    "butterfly": 14,
+    "camel": 15,
+    "can": 16,
+    "castle": 17,
+    "caterpillar": 18,
+    "cattle": 19,
+    "chair": 20,
+    "chimpanzee": 21,
+    "clock": 22,
+    "cloud": 23,
+    "cockroach": 24,
+    "couch": 25,
+    "cra": 26,
+    "crocodile": 27,
+    "cup": 28,
+    "dinosaur": 29,
+    "dolphin": 30,
+    "elephant": 31,
+    "flatfish": 32,
+    "forest": 33,
+    "fox": 34,
+    "girl": 35,
+    "hamster": 36,
+    "house": 37,
+    "kangaroo": 38,
+    "keyboard": 39,
+    "lamp": 40,
+    "lawn_mower": 41,
+    "leopard": 42,
+    "lion": 43,
+    "lizard": 44,
+    "lobster": 45,
+    "man": 46,
+    "maple_tree": 47,
+    "motorcycle": 48,
+    "mountain": 49,
+    "mouse": 50,
+    "mushroom": 51,
+    "oak_tree": 52,
+    "orange": 53,
+    "orchid": 54,
+    "otter": 55,
+    "palm_tree": 56,
+    "pear": 57,
+    "pickup_truck": 58,
+    "pine_tree": 59,
+    "plain": 60,
+    "plate": 61,
+    "poppy": 62,
+    "porcupine": 63,
+    "possum": 64,
+    "rabbit": 65,
+    "raccoon": 66,
+    "ray": 67,
+    "road": 68,
+    "rocket": 69,
+    "rose": 70,
+    "sea": 71,
+    "seal": 72,
+    "shark": 73,
+    "shrew": 74,
+    "skunk": 75,
+    "skyscraper": 76,
+    "snail": 77,
+    "snake": 78,
+    "spider": 79,
+    "squirrel": 80,
+    "streetcar": 81,
+    "sunflower": 82,
+    "sweet_pepper": 83,
+    "table": 84,
+    "tank": 85,
+    "telephone": 86,
+    "television": 87,
+    "tiger": 88,
+    "tractor": 89,
+    "train": 90,
+    "trout": 91,
+    "tulip": 92,
+    "turtle": 93,
+    "wardrobe": 94,
+    "whale": 95,
+    "willow_tree": 96,
+    "wolf": 97,
+    "woman": 98,
+    "worm": 99
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 2048,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18e7e40540325f333416d062615ad5ad9bb90f8cc42376d0255c0734e481197
-size 245020327
+oid sha256:01c1d823859c7caadaa5e5be26a15c9189979bae1fff689f5d494fa90b5bf45b
+size 245391335