Add `detr-resnet-50-panoptic` for image-segmentation

NOTE: This is actually the unquantized model. The quantized model is very inaccurate. However, the way the library currently works, I can't specify to use the unquantized version by default.

quantized/facebook/detr-resnet-50-panoptic/image-segmentation/config.json

@@ -0,0 +1,550 @@
+{
+  "_commit_hash": "060ed34a4a3501c5e8a328c69862871c2e242016",
+  "_name_or_path": "facebook/detr-resnet-50-panoptic",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForSegmentation"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "N/A",
+    "1": "person",
+    "2": "bicycle",
+    "3": "car",
+    "4": "motorcycle",
+    "5": "airplane",
+    "6": "bus",
+    "7": "train",
+    "8": "truck",
+    "9": "boat",
+    "10": "traffic light",
+    "11": "fire hydrant",
+    "12": "street sign",
+    "13": "stop sign",
+    "14": "parking meter",
+    "15": "bench",
+    "16": "bird",
+    "17": "cat",
+    "18": "dog",
+    "19": "horse",
+    "20": "sheep",
+    "21": "cow",
+    "22": "elephant",
+    "23": "bear",
+    "24": "zebra",
+    "25": "giraffe",
+    "26": "hat",
+    "27": "backpack",
+    "28": "umbrella",
+    "29": "shoe",
+    "30": "eye glasses",
+    "31": "handbag",
+    "32": "tie",
+    "33": "suitcase",
+    "34": "frisbee",
+    "35": "skis",
+    "36": "snowboard",
+    "37": "sports ball",
+    "38": "kite",
+    "39": "baseball bat",
+    "40": "baseball glove",
+    "41": "skateboard",
+    "42": "surfboard",
+    "43": "tennis racket",
+    "44": "bottle",
+    "45": "plate",
+    "46": "wine glass",
+    "47": "cup",
+    "48": "fork",
+    "49": "knife",
+    "50": "spoon",
+    "51": "bowl",
+    "52": "banana",
+    "53": "apple",
+    "54": "sandwich",
+    "55": "orange",
+    "56": "broccoli",
+    "57": "carrot",
+    "58": "hot dog",
+    "59": "pizza",
+    "60": "donut",
+    "61": "cake",
+    "62": "chair",
+    "63": "couch",
+    "64": "potted plant",
+    "65": "bed",
+    "66": "mirror",
+    "67": "dining table",
+    "68": "window",
+    "69": "desk",
+    "70": "toilet",
+    "71": "door",
+    "72": "tv",
+    "73": "laptop",
+    "74": "mouse",
+    "75": "remote",
+    "76": "keyboard",
+    "77": "cell phone",
+    "78": "microwave",
+    "79": "oven",
+    "80": "toaster",
+    "81": "sink",
+    "82": "refrigerator",
+    "83": "blender",
+    "84": "book",
+    "85": "clock",
+    "86": "vase",
+    "87": "scissors",
+    "88": "teddy bear",
+    "89": "hair drier",
+    "90": "toothbrush",
+    "91": "hair brush",
+    "92": "banner",
+    "93": "blanket",
+    "94": "branch",
+    "95": "bridge",
+    "96": "building-other",
+    "97": "bush",
+    "98": "cabinet",
+    "99": "cage",
+    "100": "cardboard",
+    "101": "carpet",
+    "102": "ceiling-other",
+    "103": "ceiling-tile",
+    "104": "cloth",
+    "105": "clothes",
+    "106": "clouds",
+    "107": "counter",
+    "108": "cupboard",
+    "109": "curtain",
+    "110": "desk-stuff",
+    "111": "dirt",
+    "112": "door-stuff",
+    "113": "fence",
+    "114": "floor-marble",
+    "115": "floor-other",
+    "116": "floor-stone",
+    "117": "floor-tile",
+    "118": "floor-wood",
+    "119": "flower",
+    "120": "fog",
+    "121": "food-other",
+    "122": "fruit",
+    "123": "furniture-other",
+    "124": "grass",
+    "125": "gravel",
+    "126": "ground-other",
+    "127": "hill",
+    "128": "house",
+    "129": "leaves",
+    "130": "light",
+    "131": "mat",
+    "132": "metal",
+    "133": "mirror-stuff",
+    "134": "moss",
+    "135": "mountain",
+    "136": "mud",
+    "137": "napkin",
+    "138": "net",
+    "139": "paper",
+    "140": "pavement",
+    "141": "pillow",
+    "142": "plant-other",
+    "143": "plastic",
+    "144": "platform",
+    "145": "playingfield",
+    "146": "railing",
+    "147": "railroad",
+    "148": "river",
+    "149": "road",
+    "150": "rock",
+    "151": "roof",
+    "152": "rug",
+    "153": "salad",
+    "154": "sand",
+    "155": "sea",
+    "156": "shelf",
+    "157": "sky-other",
+    "158": "skyscraper",
+    "159": "snow",
+    "160": "solid-other",
+    "161": "stairs",
+    "162": "stone",
+    "163": "straw",
+    "164": "structural-other",
+    "165": "table",
+    "166": "tent",
+    "167": "textile-other",
+    "168": "towel",
+    "169": "tree",
+    "170": "vegetable",
+    "171": "wall-brick",
+    "172": "wall-concrete",
+    "173": "wall-other",
+    "174": "wall-panel",
+    "175": "wall-stone",
+    "176": "wall-tile",
+    "177": "wall-wood",
+    "178": "water-other",
+    "179": "waterdrops",
+    "180": "window-blind",
+    "181": "window-other",
+    "182": "wood",
+    "183": "LABEL_183",
+    "184": "LABEL_184",
+    "185": "LABEL_185",
+    "186": "LABEL_186",
+    "187": "LABEL_187",
+    "188": "LABEL_188",
+    "189": "LABEL_189",
+    "190": "LABEL_190",
+    "191": "LABEL_191",
+    "192": "LABEL_192",
+    "193": "LABEL_193",
+    "194": "LABEL_194",
+    "195": "LABEL_195",
+    "196": "LABEL_196",
+    "197": "LABEL_197",
+    "198": "LABEL_198",
+    "199": "LABEL_199",
+    "200": "LABEL_200",
+    "201": "LABEL_201",
+    "202": "LABEL_202",
+    "203": "LABEL_203",
+    "204": "LABEL_204",
+    "205": "LABEL_205",
+    "206": "LABEL_206",
+    "207": "LABEL_207",
+    "208": "LABEL_208",
+    "209": "LABEL_209",
+    "210": "LABEL_210",
+    "211": "LABEL_211",
+    "212": "LABEL_212",
+    "213": "LABEL_213",
+    "214": "LABEL_214",
+    "215": "LABEL_215",
+    "216": "LABEL_216",
+    "217": "LABEL_217",
+    "218": "LABEL_218",
+    "219": "LABEL_219",
+    "220": "LABEL_220",
+    "221": "LABEL_221",
+    "222": "LABEL_222",
+    "223": "LABEL_223",
+    "224": "LABEL_224",
+    "225": "LABEL_225",
+    "226": "LABEL_226",
+    "227": "LABEL_227",
+    "228": "LABEL_228",
+    "229": "LABEL_229",
+    "230": "LABEL_230",
+    "231": "LABEL_231",
+    "232": "LABEL_232",
+    "233": "LABEL_233",
+    "234": "LABEL_234",
+    "235": "LABEL_235",
+    "236": "LABEL_236",
+    "237": "LABEL_237",
+    "238": "LABEL_238",
+    "239": "LABEL_239",
+    "240": "LABEL_240",
+    "241": "LABEL_241",
+    "242": "LABEL_242",
+    "243": "LABEL_243",
+    "244": "LABEL_244",
+    "245": "LABEL_245",
+    "246": "LABEL_246",
+    "247": "LABEL_247",
+    "248": "LABEL_248",
+    "249": "LABEL_249"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_183": 183,
+    "LABEL_184": 184,
+    "LABEL_185": 185,
+    "LABEL_186": 186,
+    "LABEL_187": 187,
+    "LABEL_188": 188,
+    "LABEL_189": 189,
+    "LABEL_190": 190,
+    "LABEL_191": 191,
+    "LABEL_192": 192,
+    "LABEL_193": 193,
+    "LABEL_194": 194,
+    "LABEL_195": 195,
+    "LABEL_196": 196,
+    "LABEL_197": 197,
+    "LABEL_198": 198,
+    "LABEL_199": 199,
+    "LABEL_200": 200,
+    "LABEL_201": 201,
+    "LABEL_202": 202,
+    "LABEL_203": 203,
+    "LABEL_204": 204,
+    "LABEL_205": 205,
+    "LABEL_206": 206,
+    "LABEL_207": 207,
+    "LABEL_208": 208,
+    "LABEL_209": 209,
+    "LABEL_210": 210,
+    "LABEL_211": 211,
+    "LABEL_212": 212,
+    "LABEL_213": 213,
+    "LABEL_214": 214,
+    "LABEL_215": 215,
+    "LABEL_216": 216,
+    "LABEL_217": 217,
+    "LABEL_218": 218,
+    "LABEL_219": 219,
+    "LABEL_220": 220,
+    "LABEL_221": 221,
+    "LABEL_222": 222,
+    "LABEL_223": 223,
+    "LABEL_224": 224,
+    "LABEL_225": 225,
+    "LABEL_226": 226,
+    "LABEL_227": 227,
+    "LABEL_228": 228,
+    "LABEL_229": 229,
+    "LABEL_230": 230,
+    "LABEL_231": 231,
+    "LABEL_232": 232,
+    "LABEL_233": 233,
+    "LABEL_234": 234,
+    "LABEL_235": 235,
+    "LABEL_236": 236,
+    "LABEL_237": 237,
+    "LABEL_238": 238,
+    "LABEL_239": 239,
+    "LABEL_240": 240,
+    "LABEL_241": 241,
+    "LABEL_242": 242,
+    "LABEL_243": 243,
+    "LABEL_244": 244,
+    "LABEL_245": 245,
+    "LABEL_246": 246,
+    "LABEL_247": 247,
+    "LABEL_248": 248,
+    "LABEL_249": 249,
+    "N/A": 0,
+    "airplane": 5,
+    "apple": 53,
+    "backpack": 27,
+    "banana": 52,
+    "banner": 92,
+    "baseball bat": 39,
+    "baseball glove": 40,
+    "bear": 23,
+    "bed": 65,
+    "bench": 15,
+    "bicycle": 2,
+    "bird": 16,
+    "blanket": 93,
+    "blender": 83,
+    "boat": 9,
+    "book": 84,
+    "bottle": 44,
+    "bowl": 51,
+    "branch": 94,
+    "bridge": 95,
+    "broccoli": 56,
+    "building-other": 96,
+    "bus": 6,
+    "bush": 97,
+    "cabinet": 98,
+    "cage": 99,
+    "cake": 61,
+    "car": 3,
+    "cardboard": 100,
+    "carpet": 101,
+    "carrot": 57,
+    "cat": 17,
+    "ceiling-other": 102,
+    "ceiling-tile": 103,
+    "cell phone": 77,
+    "chair": 62,
+    "clock": 85,
+    "cloth": 104,
+    "clothes": 105,
+    "clouds": 106,
+    "couch": 63,
+    "counter": 107,
+    "cow": 21,
+    "cup": 47,
+    "cupboard": 108,
+    "curtain": 109,
+    "desk": 69,
+    "desk-stuff": 110,
+    "dining table": 67,
+    "dirt": 111,
+    "dog": 18,
+    "donut": 60,
+    "door": 71,
+    "door-stuff": 112,
+    "elephant": 22,
+    "eye glasses": 30,
+    "fence": 113,
+    "fire hydrant": 11,
+    "floor-marble": 114,
+    "floor-other": 115,
+    "floor-stone": 116,
+    "floor-tile": 117,
+    "floor-wood": 118,
+    "flower": 119,
+    "fog": 120,
+    "food-other": 121,
+    "fork": 48,
+    "frisbee": 34,
+    "fruit": 122,
+    "furniture-other": 123,
+    "giraffe": 25,
+    "grass": 124,
+    "gravel": 125,
+    "ground-other": 126,
+    "hair brush": 91,
+    "hair drier": 89,
+    "handbag": 31,
+    "hat": 26,
+    "hill": 127,
+    "horse": 19,
+    "hot dog": 58,
+    "house": 128,
+    "keyboard": 76,
+    "kite": 38,
+    "knife": 49,
+    "laptop": 73,
+    "leaves": 129,
+    "light": 130,
+    "mat": 131,
+    "metal": 132,
+    "microwave": 78,
+    "mirror": 66,
+    "mirror-stuff": 133,
+    "moss": 134,
+    "motorcycle": 4,
+    "mountain": 135,
+    "mouse": 74,
+    "mud": 136,
+    "napkin": 137,
+    "net": 138,
+    "orange": 55,
+    "oven": 79,
+    "paper": 139,
+    "parking meter": 14,
+    "pavement": 140,
+    "person": 1,
+    "pillow": 141,
+    "pizza": 59,
+    "plant-other": 142,
+    "plastic": 143,
+    "plate": 45,
+    "platform": 144,
+    "playingfield": 145,
+    "potted plant": 64,
+    "railing": 146,
+    "railroad": 147,
+    "refrigerator": 82,
+    "remote": 75,
+    "river": 148,
+    "road": 149,
+    "rock": 150,
+    "roof": 151,
+    "rug": 152,
+    "salad": 153,
+    "sand": 154,
+    "sandwich": 54,
+    "scissors": 87,
+    "sea": 155,
+    "sheep": 20,
+    "shelf": 156,
+    "shoe": 29,
+    "sink": 81,
+    "skateboard": 41,
+    "skis": 35,
+    "sky-other": 157,
+    "skyscraper": 158,
+    "snow": 159,
+    "snowboard": 36,
+    "solid-other": 160,
+    "spoon": 50,
+    "sports ball": 37,
+    "stairs": 161,
+    "stone": 162,
+    "stop sign": 13,
+    "straw": 163,
+    "street sign": 12,
+    "structural-other": 164,
+    "suitcase": 33,
+    "surfboard": 42,
+    "table": 165,
+    "teddy bear": 88,
+    "tennis racket": 43,
+    "tent": 166,
+    "textile-other": 167,
+    "tie": 32,
+    "toaster": 80,
+    "toilet": 70,
+    "toothbrush": 90,
+    "towel": 168,
+    "traffic light": 10,
+    "train": 7,
+    "tree": 169,
+    "truck": 8,
+    "tv": 72,
+    "umbrella": 28,
+    "vase": 86,
+    "vegetable": 170,
+    "wall-brick": 171,
+    "wall-concrete": 172,
+    "wall-other": 173,
+    "wall-panel": 174,
+    "wall-stone": 175,
+    "wall-tile": 176,
+    "wall-wood": 177,
+    "water-other": 178,
+    "waterdrops": 179,
+    "window": 68,
+    "window-blind": 180,
+    "window-other": 181,
+    "wine glass": 46,
+    "wood": 182,
+    "zebra": 24
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "transformers_version": "4.7.0.dev0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

quantized/facebook/detr-resnet-50-panoptic/image-segmentation/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca23bd2f604c3866222e658b7c239660fad4abd77e72b1027c6e80d339db09c6
+size 172282718

quantized/facebook/detr-resnet-50-panoptic/image-segmentation/preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "DetrFeatureExtractor",
+  "format": "coco_panoptic",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "max_size": 1333,
+  "size": 800
+}