config.json

{
  "_name_or_path": "google/owlvit-base-patch32",
  "architectures": [
    "OwlViTForObjectDetection"
  ],
  "id2label": {
    "0": 1,
    "1": 3,
    "10": 21,
    "11": 22,
    "12": 23,
    "13": 24,
    "14": 26,
    "15": 27,
    "16": 28,
    "17": 29,
    "18": 30,
    "19": 31,
    "2": 7,
    "20": 32,
    "21": 33,
    "22": 34,
    "23": 35,
    "24": 36,
    "25": 37,
    "26": 38,
    "27": 39,
    "28": 40,
    "29": 41,
    "3": 9,
    "30": 42,
    "31": 43,
    "32": 44,
    "33": 45,
    "34": 46,
    "35": 47,
    "36": 48,
    "37": 49,
    "38": 50,
    "39": 51,
    "4": 11,
    "40": 52,
    "41": 53,
    "42": 54,
    "43": 55,
    "44": 56,
    "45": 57,
    "46": 58,
    "47": 59,
    "48": 60,
    "49": 61,
    "5": 13,
    "50": 62,
    "51": 63,
    "52": 64,
    "53": 66,
    "54": 67,
    "55": 68,
    "56": 69,
    "57": 70,
    "58": 71,
    "59": 72,
    "6": 14,
    "60": 73,
    "61": 74,
    "62": 75,
    "63": 76,
    "64": 77,
    "65": 78,
    "66": 79,
    "67": 80,
    "68": 81,
    "69": 82,
    "7": 16,
    "70": 83,
    "71": 87,
    "72": 88,
    "73": 90,
    "74": 91,
    "75": 92,
    "76": 93,
    "77": 94,
    "78": 95,
    "79": 96,
    "8": 19,
    "80": 97,
    "81": 98,
    "82": 99,
    "83": 100,
    "84": 101,
    "85": 102,
    "86": 103,
    "87": 104,
    "88": 105,
    "9": 20
  },
  "initializer_factor": 1.0,
  "label2id": {
    "1": "0",
    "3": "1",
    "7": "2",
    "9": "3",
    "11": "4",
    "13": "5",
    "14": "6",
    "16": "7",
    "19": "8",
    "20": "9",
    "21": "10",
    "22": "11",
    "23": "12",
    "24": "13",
    "26": "14",
    "27": "15",
    "28": "16",
    "29": "17",
    "30": "18",
    "31": "19",
    "32": "20",
    "33": "21",
    "34": "22",
    "35": "23",
    "36": "24",
    "37": "25",
    "38": "26",
    "39": "27",
    "40": "28",
    "41": "29",
    "42": "30",
    "43": "31",
    "44": "32",
    "45": "33",
    "46": "34",
    "47": "35",
    "48": "36",
    "49": "37",
    "50": "38",
    "51": "39",
    "52": "40",
    "53": "41",
    "54": "42",
    "55": "43",
    "56": "44",
    "57": "45",
    "58": "46",
    "59": "47",
    "60": "48",
    "61": "49",
    "62": "50",
    "63": "51",
    "64": "52",
    "66": "53",
    "67": "54",
    "68": "55",
    "69": "56",
    "70": "57",
    "71": "58",
    "72": "59",
    "73": "60",
    "74": "61",
    "75": "62",
    "76": "63",
    "77": "64",
    "78": "65",
    "79": "66",
    "80": "67",
    "81": "68",
    "82": "69",
    "83": "70",
    "87": "71",
    "88": "72",
    "90": "73",
    "91": "74",
    "92": "75",
    "93": "76",
    "94": "77",
    "95": "78",
    "96": "79",
    "97": "80",
    "98": "81",
    "99": "82",
    "100": "83",
    "101": "84",
    "102": "85",
    "103": "86",
    "104": "87",
    "105": "88"
  },
  "logit_scale_init_value": 2.6592,
  "model_type": "owlvit",
  "projection_dim": 512,
  "text_config": {
    "bos_token_id": 0,
    "dropout": 0.0,
    "eos_token_id": 2,
    "max_length": 16,
    "model_type": "owlvit_text_model",
    "pad_token_id": 1
  },
  "text_config_dict": null,
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "vision_config": {
    "dropout": 0.0,
    "model_type": "owlvit_vision_model"
  },
  "vision_config_dict": null
}