Improve README

README.md

@@ -2,11 +2,21 @@
 license: apache-2.0
 tags:
 - image-segmentation
+- vision
 datasets:
 - coco
+widget:
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
+  example_title: Football Match
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/dog-cat.jpg
+  example_title: Dog & Cat
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/construction-site.jpg
+  example_title: Construction Site
+- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/apple-orange.jpg
+  example_title: Apple & Orange
 ---
 
-# DETR (End-to-End Object Detection) model with ResNet-101 backbone
+# DETR (End-to-End Object Detection) model with ResNet-50 backbone
 
 DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 panoptic (118k annotated images). It was introduced in the paper [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872) by Carion et al. and first released in [this repository](https://github.com/facebookresearch/detr). 
 
@@ -20,6 +30,8 @@ The model is trained using a "bipartite matching loss": one compares the predict
 
 DETR can be naturally extended to perform panoptic segmentation, by adding a mask head on top of the decoder outputs.
 
+![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/detr_architecture.png)
+
 ## Intended uses & limitations
 
 You can use the raw model for panoptic segmentation. See the [model hub](https://huggingface.co/models?search=facebook/detr) to look for all available DETR models.
@@ -29,22 +41,36 @@ You can use the raw model for panoptic segmentation. See the [model hub](https:/
 Here is how to use this model:
 
 ```python
-from transformers import DetrFeatureExtractor, DetrForSegmentation
+import io
-from PIL import Image
 import requests
+from PIL import Image
+import torch
+import numpy
 
-url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+from transformers import DetrFeatureExtractor, DetrForSegmentation
+from transformers.models.detr.feature_extraction_detr import rgb_to_id
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 
-feature_extractor = DetrFeatureExtractor.from_pretrained('facebook/detr-resnet-50-panoptic')
+feature_extractor = DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-50-panoptic")
-model = DetrForSegmentation.from_pretrained('facebook/detr-resnet-50-panoptic')
+model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic")
 
+# prepare image for the model
 inputs = feature_extractor(images=image, return_tensors="pt")
+
+# forward pass
 outputs = model(**inputs)
-# model predicts COCO classes, bounding boxes, and masks
+
-logits = outputs.logits
+# use the `post_process_panoptic` method of `DetrFeatureExtractor` to convert to COCO format
-bboxes = outputs.pred_boxes
+processed_sizes = torch.as_tensor(inputs["pixel_values"].shape[-2:]).unsqueeze(0)
-masks = outputs.pred_masks
+result = feature_extractor.post_process_panoptic(outputs, processed_sizes)[0]
+
+# the segmentation is stored in a special-format png
+panoptic_seg = Image.open(io.BytesIO(result["png_string"]))
+panoptic_seg = numpy.array(panoptic_seg, dtype=numpy.uint8)
+# retrieve the ids corresponding to each mask
+panoptic_seg_id = rgb_to_id(panoptic_seg)
 ```
 
 Currently, both the feature extractor and model support PyTorch. 

config.json

@@ -27,189 +27,100 @@
   "giou_cost": 2,
   "giou_loss_coefficient": 2,
   "id2label": {
-    "0": "LABEL_0",
+    "0": "N/A",
-    "1": "LABEL_1",
+    "1": "person",
-    "2": "LABEL_2",
+    "10": "traffic light",
-    "3": "LABEL_3",
+    "100": "cardboard",
-    "4": "LABEL_4",
+    "101": "carpet",
-    "5": "LABEL_5",
+    "102": "ceiling-other",
-    "6": "LABEL_6",
+    "103": "ceiling-tile",
-    "7": "LABEL_7",
+    "104": "cloth",
-    "8": "LABEL_8",
+    "105": "clothes",
-    "9": "LABEL_9",
+    "106": "clouds",
-    "10": "LABEL_10",
+    "107": "counter",
-    "11": "LABEL_11",
+    "108": "cupboard",
-    "12": "LABEL_12",
+    "109": "curtain",
-    "13": "LABEL_13",
+    "11": "fire hydrant",
-    "14": "LABEL_14",
+    "110": "desk-stuff",
-    "15": "LABEL_15",
+    "111": "dirt",
-    "16": "LABEL_16",
+    "112": "door-stuff",
-    "17": "LABEL_17",
+    "113": "fence",
-    "18": "LABEL_18",
+    "114": "floor-marble",
-    "19": "LABEL_19",
+    "115": "floor-other",
-    "20": "LABEL_20",
+    "116": "floor-stone",
-    "21": "LABEL_21",
+    "117": "floor-tile",
-    "22": "LABEL_22",
+    "118": "floor-wood",
-    "23": "LABEL_23",
+    "119": "flower",
-    "24": "LABEL_24",
+    "12": "street sign",
-    "25": "LABEL_25",
+    "120": "fog",
-    "26": "LABEL_26",
+    "121": "food-other",
-    "27": "LABEL_27",
+    "122": "fruit",
-    "28": "LABEL_28",
+    "123": "furniture-other",
-    "29": "LABEL_29",
+    "124": "grass",
-    "30": "LABEL_30",
+    "125": "gravel",
-    "31": "LABEL_31",
+    "126": "ground-other",
-    "32": "LABEL_32",
+    "127": "hill",
-    "33": "LABEL_33",
+    "128": "house",
-    "34": "LABEL_34",
+    "129": "leaves",
-    "35": "LABEL_35",
+    "13": "stop sign",
-    "36": "LABEL_36",
+    "130": "light",
-    "37": "LABEL_37",
+    "131": "mat",
-    "38": "LABEL_38",
+    "132": "metal",
-    "39": "LABEL_39",
+    "133": "mirror-stuff",
-    "40": "LABEL_40",
+    "134": "moss",
-    "41": "LABEL_41",
+    "135": "mountain",
-    "42": "LABEL_42",
+    "136": "mud",
-    "43": "LABEL_43",
+    "137": "napkin",
-    "44": "LABEL_44",
+    "138": "net",
-    "45": "LABEL_45",
+    "139": "paper",
-    "46": "LABEL_46",
+    "14": "parking meter",
-    "47": "LABEL_47",
+    "140": "pavement",
-    "48": "LABEL_48",
+    "141": "pillow",
-    "49": "LABEL_49",
+    "142": "plant-other",
-    "50": "LABEL_50",
+    "143": "plastic",
-    "51": "LABEL_51",
+    "144": "platform",
-    "52": "LABEL_52",
+    "145": "playingfield",
-    "53": "LABEL_53",
+    "146": "railing",
-    "54": "LABEL_54",
+    "147": "railroad",
-    "55": "LABEL_55",
+    "148": "river",
-    "56": "LABEL_56",
+    "149": "road",
-    "57": "LABEL_57",
+    "15": "bench",
-    "58": "LABEL_58",
+    "150": "rock",
-    "59": "LABEL_59",
+    "151": "roof",
-    "60": "LABEL_60",
+    "152": "rug",
-    "61": "LABEL_61",
+    "153": "salad",
-    "62": "LABEL_62",
+    "154": "sand",
-    "63": "LABEL_63",
+    "155": "sea",
-    "64": "LABEL_64",
+    "156": "shelf",
-    "65": "LABEL_65",
+    "157": "sky-other",
-    "66": "LABEL_66",
+    "158": "skyscraper",
-    "67": "LABEL_67",
+    "159": "snow",
-    "68": "LABEL_68",
+    "16": "bird",
-    "69": "LABEL_69",
+    "160": "solid-other",
-    "70": "LABEL_70",
+    "161": "stairs",
-    "71": "LABEL_71",
+    "162": "stone",
-    "72": "LABEL_72",
+    "163": "straw",
-    "73": "LABEL_73",
+    "164": "structural-other",
-    "74": "LABEL_74",
+    "165": "table",
-    "75": "LABEL_75",
+    "166": "tent",
-    "76": "LABEL_76",
+    "167": "textile-other",
-    "77": "LABEL_77",
+    "168": "towel",
-    "78": "LABEL_78",
+    "169": "tree",
-    "79": "LABEL_79",
+    "17": "cat",
-    "80": "LABEL_80",
+    "170": "vegetable",
-    "81": "LABEL_81",
+    "171": "wall-brick",
-    "82": "LABEL_82",
+    "172": "wall-concrete",
-    "83": "LABEL_83",
+    "173": "wall-other",
-    "84": "LABEL_84",
+    "174": "wall-panel",
-    "85": "LABEL_85",
+    "175": "wall-stone",
-    "86": "LABEL_86",
+    "176": "wall-tile",
-    "87": "LABEL_87",
+    "177": "wall-wood",
-    "88": "LABEL_88",
+    "178": "water-other",
-    "89": "LABEL_89",
+    "179": "waterdrops",
-    "90": "LABEL_90",
+    "18": "dog",
-    "91": "LABEL_91",
+    "180": "window-blind",
-    "92": "LABEL_92",
+    "181": "window-other",
-    "93": "LABEL_93",
+    "182": "wood",
-    "94": "LABEL_94",
-    "95": "LABEL_95",
-    "96": "LABEL_96",
-    "97": "LABEL_97",
-    "98": "LABEL_98",
-    "99": "LABEL_99",
-    "100": "LABEL_100",
-    "101": "LABEL_101",
-    "102": "LABEL_102",
-    "103": "LABEL_103",
-    "104": "LABEL_104",
-    "105": "LABEL_105",
-    "106": "LABEL_106",
-    "107": "LABEL_107",
-    "108": "LABEL_108",
-    "109": "LABEL_109",
-    "110": "LABEL_110",
-    "111": "LABEL_111",
-    "112": "LABEL_112",
-    "113": "LABEL_113",
-    "114": "LABEL_114",
-    "115": "LABEL_115",
-    "116": "LABEL_116",
-    "117": "LABEL_117",
-    "118": "LABEL_118",
-    "119": "LABEL_119",
-    "120": "LABEL_120",
-    "121": "LABEL_121",
-    "122": "LABEL_122",
-    "123": "LABEL_123",
-    "124": "LABEL_124",
-    "125": "LABEL_125",
-    "126": "LABEL_126",
-    "127": "LABEL_127",
-    "128": "LABEL_128",
-    "129": "LABEL_129",
-    "130": "LABEL_130",
-    "131": "LABEL_131",
-    "132": "LABEL_132",
-    "133": "LABEL_133",
-    "134": "LABEL_134",
-    "135": "LABEL_135",
-    "136": "LABEL_136",
-    "137": "LABEL_137",
-    "138": "LABEL_138",
-    "139": "LABEL_139",
-    "140": "LABEL_140",
-    "141": "LABEL_141",
-    "142": "LABEL_142",
-    "143": "LABEL_143",
-    "144": "LABEL_144",
-    "145": "LABEL_145",
-    "146": "LABEL_146",
-    "147": "LABEL_147",
-    "148": "LABEL_148",
-    "149": "LABEL_149",
-    "150": "LABEL_150",
-    "151": "LABEL_151",
-    "152": "LABEL_152",
-    "153": "LABEL_153",
-    "154": "LABEL_154",
-    "155": "LABEL_155",
-    "156": "LABEL_156",
-    "157": "LABEL_157",
-    "158": "LABEL_158",
-    "159": "LABEL_159",
-    "160": "LABEL_160",
-    "161": "LABEL_161",
-    "162": "LABEL_162",
-    "163": "LABEL_163",
-    "164": "LABEL_164",
-    "165": "LABEL_165",
-    "166": "LABEL_166",
-    "167": "LABEL_167",
-    "168": "LABEL_168",
-    "169": "LABEL_169",
-    "170": "LABEL_170",
-    "171": "LABEL_171",
-    "172": "LABEL_172",
-    "173": "LABEL_173",
-    "174": "LABEL_174",
-    "175": "LABEL_175",
-    "176": "LABEL_176",
-    "177": "LABEL_177",
-    "178": "LABEL_178",
-    "179": "LABEL_179",
-    "180": "LABEL_180",
-    "181": "LABEL_181",
-    "182": "LABEL_182",
     "183": "LABEL_183",
     "184": "LABEL_184",
     "185": "LABEL_185",
@@ -217,6 +128,7 @@
     "187": "LABEL_187",
     "188": "LABEL_188",
     "189": "LABEL_189",
+    "19": "horse",
     "190": "LABEL_190",
     "191": "LABEL_191",
     "192": "LABEL_192",
@@ -227,6 +139,8 @@
     "197": "LABEL_197",
     "198": "LABEL_198",
     "199": "LABEL_199",
+    "2": "bicycle",
+    "20": "sheep",
     "200": "LABEL_200",
     "201": "LABEL_201",
     "202": "LABEL_202",
@@ -237,6 +151,7 @@
     "207": "LABEL_207",
     "208": "LABEL_208",
     "209": "LABEL_209",
+    "21": "cow",
     "210": "LABEL_210",
     "211": "LABEL_211",
     "212": "LABEL_212",
@@ -247,6 +162,7 @@
     "217": "LABEL_217",
     "218": "LABEL_218",
     "219": "LABEL_219",
+    "22": "elephant",
     "220": "LABEL_220",
     "221": "LABEL_221",
     "222": "LABEL_222",
@@ -257,6 +173,7 @@
     "227": "LABEL_227",
     "228": "LABEL_228",
     "229": "LABEL_229",
+    "23": "bear",
     "230": "LABEL_230",
     "231": "LABEL_231",
     "232": "LABEL_232",
@@ -267,6 +184,7 @@
     "237": "LABEL_237",
     "238": "LABEL_238",
     "239": "LABEL_239",
+    "24": "zebra",
     "240": "LABEL_240",
     "241": "LABEL_241",
     "242": "LABEL_242",
@@ -276,106 +194,94 @@
     "246": "LABEL_246",
     "247": "LABEL_247",
     "248": "LABEL_248",
-    "249": "LABEL_249"
+    "249": "LABEL_249",
+    "25": "giraffe",
+    "26": "hat",
+    "27": "backpack",
+    "28": "umbrella",
+    "29": "shoe",
+    "3": "car",
+    "30": "eye glasses",
+    "31": "handbag",
+    "32": "tie",
+    "33": "suitcase",
+    "34": "frisbee",
+    "35": "skis",
+    "36": "snowboard",
+    "37": "sports ball",
+    "38": "kite",
+    "39": "baseball bat",
+    "4": "motorcycle",
+    "40": "baseball glove",
+    "41": "skateboard",
+    "42": "surfboard",
+    "43": "tennis racket",
+    "44": "bottle",
+    "45": "plate",
+    "46": "wine glass",
+    "47": "cup",
+    "48": "fork",
+    "49": "knife",
+    "5": "airplane",
+    "50": "spoon",
+    "51": "bowl",
+    "52": "banana",
+    "53": "apple",
+    "54": "sandwich",
+    "55": "orange",
+    "56": "broccoli",
+    "57": "carrot",
+    "58": "hot dog",
+    "59": "pizza",
+    "6": "bus",
+    "60": "donut",
+    "61": "cake",
+    "62": "chair",
+    "63": "couch",
+    "64": "potted plant",
+    "65": "bed",
+    "66": "mirror",
+    "67": "dining table",
+    "68": "window",
+    "69": "desk",
+    "7": "train",
+    "70": "toilet",
+    "71": "door",
+    "72": "tv",
+    "73": "laptop",
+    "74": "mouse",
+    "75": "remote",
+    "76": "keyboard",
+    "77": "cell phone",
+    "78": "microwave",
+    "79": "oven",
+    "8": "truck",
+    "80": "toaster",
+    "81": "sink",
+    "82": "refrigerator",
+    "83": "blender",
+    "84": "book",
+    "85": "clock",
+    "86": "vase",
+    "87": "scissors",
+    "88": "teddy bear",
+    "89": "hair drier",
+    "9": "boat",
+    "90": "toothbrush",
+    "91": "hair brush",
+    "92": "banner",
+    "93": "blanket",
+    "94": "branch",
+    "95": "bridge",
+    "96": "building-other",
+    "97": "bush",
+    "98": "cabinet",
+    "99": "cage"
    },
   "init_std": 0.02,
   "init_xavier_std": 1.0,
   "is_encoder_decoder": true,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_10": 10,
-    "LABEL_100": 100,
-    "LABEL_101": 101,
-    "LABEL_102": 102,
-    "LABEL_103": 103,
-    "LABEL_104": 104,
-    "LABEL_105": 105,
-    "LABEL_106": 106,
-    "LABEL_107": 107,
-    "LABEL_108": 108,
-    "LABEL_109": 109,
-    "LABEL_11": 11,
-    "LABEL_110": 110,
-    "LABEL_111": 111,
-    "LABEL_112": 112,
-    "LABEL_113": 113,
-    "LABEL_114": 114,
-    "LABEL_115": 115,
-    "LABEL_116": 116,
-    "LABEL_117": 117,
-    "LABEL_118": 118,
-    "LABEL_119": 119,
-    "LABEL_12": 12,
-    "LABEL_120": 120,
-    "LABEL_121": 121,
-    "LABEL_122": 122,
-    "LABEL_123": 123,
-    "LABEL_124": 124,
-    "LABEL_125": 125,
-    "LABEL_126": 126,
-    "LABEL_127": 127,
-    "LABEL_128": 128,
-    "LABEL_129": 129,
-    "LABEL_13": 13,
-    "LABEL_130": 130,
-    "LABEL_131": 131,
-    "LABEL_132": 132,
-    "LABEL_133": 133,
-    "LABEL_134": 134,
-    "LABEL_135": 135,
-    "LABEL_136": 136,
-    "LABEL_137": 137,
-    "LABEL_138": 138,
-    "LABEL_139": 139,
-    "LABEL_14": 14,
-    "LABEL_140": 140,
-    "LABEL_141": 141,
-    "LABEL_142": 142,
-    "LABEL_143": 143,
-    "LABEL_144": 144,
-    "LABEL_145": 145,
-    "LABEL_146": 146,
-    "LABEL_147": 147,
-    "LABEL_148": 148,
-    "LABEL_149": 149,
-    "LABEL_15": 15,
-    "LABEL_150": 150,
-    "LABEL_151": 151,
-    "LABEL_152": 152,
-    "LABEL_153": 153,
-    "LABEL_154": 154,
-    "LABEL_155": 155,
-    "LABEL_156": 156,
-    "LABEL_157": 157,
-    "LABEL_158": 158,
-    "LABEL_159": 159,
-    "LABEL_16": 16,
-    "LABEL_160": 160,
-    "LABEL_161": 161,
-    "LABEL_162": 162,
-    "LABEL_163": 163,
-    "LABEL_164": 164,
-    "LABEL_165": 165,
-    "LABEL_166": 166,
-    "LABEL_167": 167,
-    "LABEL_168": 168,
-    "LABEL_169": 169,
-    "LABEL_17": 17,
-    "LABEL_170": 170,
-    "LABEL_171": 171,
-    "LABEL_172": 172,
-    "LABEL_173": 173,
-    "LABEL_174": 174,
-    "LABEL_175": 175,
-    "LABEL_176": 176,
-    "LABEL_177": 177,
-    "LABEL_178": 178,
-    "LABEL_179": 179,
-    "LABEL_18": 18,
-    "LABEL_180": 180,
-    "LABEL_181": 181,
-    "LABEL_182": 182,
     "LABEL_183": 183,
     "LABEL_184": 184,
     "LABEL_185": 185,
@@ -383,7 +289,6 @@
     "LABEL_187": 187,
     "LABEL_188": 188,
     "LABEL_189": 189,
-    "LABEL_19": 19,
     "LABEL_190": 190,
     "LABEL_191": 191,
     "LABEL_192": 192,
@@ -394,8 +299,6 @@
     "LABEL_197": 197,
     "LABEL_198": 198,
     "LABEL_199": 199,
-    "LABEL_2": 2,
-    "LABEL_20": 20,
     "LABEL_200": 200,
     "LABEL_201": 201,
     "LABEL_202": 202,
@@ -406,7 +309,6 @@
     "LABEL_207": 207,
     "LABEL_208": 208,
     "LABEL_209": 209,
-    "LABEL_21": 21,
     "LABEL_210": 210,
     "LABEL_211": 211,
     "LABEL_212": 212,
@@ -417,7 +319,6 @@
     "LABEL_217": 217,
     "LABEL_218": 218,
     "LABEL_219": 219,
-    "LABEL_22": 22,
     "LABEL_220": 220,
     "LABEL_221": 221,
     "LABEL_222": 222,
@@ -428,7 +329,6 @@
     "LABEL_227": 227,
     "LABEL_228": 228,
     "LABEL_229": 229,
-    "LABEL_23": 23,
     "LABEL_230": 230,
     "LABEL_231": 231,
     "LABEL_232": 232,
@@ -439,7 +339,6 @@
     "LABEL_237": 237,
     "LABEL_238": 238,
     "LABEL_239": 239,
-    "LABEL_24": 24,
     "LABEL_240": 240,
     "LABEL_241": 241,
     "LABEL_242": 242,
@@ -450,88 +349,189 @@
     "LABEL_247": 247,
     "LABEL_248": 248,
     "LABEL_249": 249,
-    "LABEL_25": 25,
+    "N/A": 0,
-    "LABEL_26": 26,
+    "airplane": 5,
-    "LABEL_27": 27,
+    "apple": 53,
-    "LABEL_28": 28,
+    "backpack": 27,
-    "LABEL_29": 29,
+    "banana": 52,
-    "LABEL_3": 3,
+    "banner": 92,
-    "LABEL_30": 30,
+    "baseball bat": 39,
-    "LABEL_31": 31,
+    "baseball glove": 40,
-    "LABEL_32": 32,
+    "bear": 23,
-    "LABEL_33": 33,
+    "bed": 65,
-    "LABEL_34": 34,
+    "bench": 15,
-    "LABEL_35": 35,
+    "bicycle": 2,
-    "LABEL_36": 36,
+    "bird": 16,
-    "LABEL_37": 37,
+    "blanket": 93,
-    "LABEL_38": 38,
+    "blender": 83,
-    "LABEL_39": 39,
+    "boat": 9,
-    "LABEL_4": 4,
+    "book": 84,
-    "LABEL_40": 40,
+    "bottle": 44,
-    "LABEL_41": 41,
+    "bowl": 51,
-    "LABEL_42": 42,
+    "branch": 94,
-    "LABEL_43": 43,
+    "bridge": 95,
-    "LABEL_44": 44,
+    "broccoli": 56,
-    "LABEL_45": 45,
+    "building-other": 96,
-    "LABEL_46": 46,
+    "bus": 6,
-    "LABEL_47": 47,
+    "bush": 97,
-    "LABEL_48": 48,
+    "cabinet": 98,
-    "LABEL_49": 49,
+    "cage": 99,
-    "LABEL_5": 5,
+    "cake": 61,
-    "LABEL_50": 50,
+    "car": 3,
-    "LABEL_51": 51,
+    "cardboard": 100,
-    "LABEL_52": 52,
+    "carpet": 101,
-    "LABEL_53": 53,
+    "carrot": 57,
-    "LABEL_54": 54,
+    "cat": 17,
-    "LABEL_55": 55,
+    "ceiling-other": 102,
-    "LABEL_56": 56,
+    "ceiling-tile": 103,
-    "LABEL_57": 57,
+    "cell phone": 77,
-    "LABEL_58": 58,
+    "chair": 62,
-    "LABEL_59": 59,
+    "clock": 85,
-    "LABEL_6": 6,
+    "cloth": 104,
-    "LABEL_60": 60,
+    "clothes": 105,
-    "LABEL_61": 61,
+    "clouds": 106,
-    "LABEL_62": 62,
+    "couch": 63,
-    "LABEL_63": 63,
+    "counter": 107,
-    "LABEL_64": 64,
+    "cow": 21,
-    "LABEL_65": 65,
+    "cup": 47,
-    "LABEL_66": 66,
+    "cupboard": 108,
-    "LABEL_67": 67,
+    "curtain": 109,
-    "LABEL_68": 68,
+    "desk": 69,
-    "LABEL_69": 69,
+    "desk-stuff": 110,
-    "LABEL_7": 7,
+    "dining table": 67,
-    "LABEL_70": 70,
+    "dirt": 111,
-    "LABEL_71": 71,
+    "dog": 18,
-    "LABEL_72": 72,
+    "donut": 60,
-    "LABEL_73": 73,
+    "door": 71,
-    "LABEL_74": 74,
+    "door-stuff": 112,
-    "LABEL_75": 75,
+    "elephant": 22,
-    "LABEL_76": 76,
+    "eye glasses": 30,
-    "LABEL_77": 77,
+    "fence": 113,
-    "LABEL_78": 78,
+    "fire hydrant": 11,
-    "LABEL_79": 79,
+    "floor-marble": 114,
-    "LABEL_8": 8,
+    "floor-other": 115,
-    "LABEL_80": 80,
+    "floor-stone": 116,
-    "LABEL_81": 81,
+    "floor-tile": 117,
-    "LABEL_82": 82,
+    "floor-wood": 118,
-    "LABEL_83": 83,
+    "flower": 119,
-    "LABEL_84": 84,
+    "fog": 120,
-    "LABEL_85": 85,
+    "food-other": 121,
-    "LABEL_86": 86,
+    "fork": 48,
-    "LABEL_87": 87,
+    "frisbee": 34,
-    "LABEL_88": 88,
+    "fruit": 122,
-    "LABEL_89": 89,
+    "furniture-other": 123,
-    "LABEL_9": 9,
+    "giraffe": 25,
-    "LABEL_90": 90,
+    "grass": 124,
-    "LABEL_91": 91,
+    "gravel": 125,
-    "LABEL_92": 92,
+    "ground-other": 126,
-    "LABEL_93": 93,
+    "hair brush": 91,
-    "LABEL_94": 94,
+    "hair drier": 89,
-    "LABEL_95": 95,
+    "handbag": 31,
-    "LABEL_96": 96,
+    "hat": 26,
-    "LABEL_97": 97,
+    "hill": 127,
-    "LABEL_98": 98,
+    "horse": 19,
-    "LABEL_99": 99
+    "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,
@@ -539,7 +539,6 @@
   "num_hidden_layers": 6,
   "num_queries": 100,
   "position_embedding_type": "sine",
-  "return_intermediate_layers": true,
   "scale_embedding": false,
   "transformers_version": "4.7.0.dev0"
 }