facebook
/
detr-resnet-50-panoptic
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: facebook:060ed34a4a3501c5e8a328c69862871c2e242016
Branches Tags
facebook:main
..
compare: facebook:cabb45ce89285a0f7cdad5a4b483e164fa3a6d66
Branches Tags
facebook:main

No commits in common. "060ed34a4a3501c5e8a328c69862871c2e242016" and "cabb45ce89285a0f7cdad5a4b483e164fa3a6d66" have entirely different histories.
060ed34a4a ... cabb45ce89

3 changed files with 382 additions and 407 deletions
Show Stats Expand all files Collapse all files

46
README.md
View File

@ -2,21 +2,11 @@
license: apache-2.0 license: apache-2.0
tags: tags:
- image-segmentation - image-segmentation
- vision
datasets: datasets:
- coco - 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-50 backbone # DETR (End-to-End Object Detection) model with ResNet-101 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). 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).
@ -30,8 +20,6 @@ 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. 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 ## 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. 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.
@ -41,36 +29,22 @@ You can use the raw model for panoptic segmentation. See the [model hub](https:/
Here is how to use this model: Here is how to use this model:
```python ```python
import io
import requests
from PIL import Image
import torch
import numpy
from transformers import DetrFeatureExtractor, DetrForSegmentation from transformers import DetrFeatureExtractor, DetrForSegmentation
from transformers.models.detr.feature_extraction_detr import rgb_to_id from PIL import Image
import requests
url = "http://images.cocodataset.org/val2017/000000039769.jpg" url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw) 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") inputs = feature_extractor(images=image, return_tensors="pt")
# forward pass
outputs = model(**inputs) outputs = model(**inputs)
# model predicts COCO classes, bounding boxes, and masks
# use the `post_process_panoptic` method of `DetrFeatureExtractor` to convert to COCO format logits = outputs.logits
processed_sizes = torch.as_tensor(inputs["pixel_values"].shape[-2:]).unsqueeze(0) bboxes = outputs.pred_boxes
result = feature_extractor.post_process_panoptic(outputs, processed_sizes)[0] masks = outputs.pred_masks
# 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. Currently, both the feature extractor and model support PyTorch.

739
config.json
View File

@ -27,100 +27,189 @@
"giou_cost": 2, "giou_cost": 2,
"giou_loss_coefficient": 2, "giou_loss_coefficient": 2,
"id2label": { "id2label": {
"0": "N/A", "0": "LABEL_0",
"1": "person", "1": "LABEL_1",
"10": "traffic light", "2": "LABEL_2",
"100": "cardboard", "3": "LABEL_3",
"101": "carpet", "4": "LABEL_4",
"102": "ceiling-other", "5": "LABEL_5",
"103": "ceiling-tile", "6": "LABEL_6",
"104": "cloth", "7": "LABEL_7",
"105": "clothes", "8": "LABEL_8",
"106": "clouds", "9": "LABEL_9",
"107": "counter", "10": "LABEL_10",
"108": "cupboard", "11": "LABEL_11",
"109": "curtain", "12": "LABEL_12",
"11": "fire hydrant", "13": "LABEL_13",
"110": "desk-stuff", "14": "LABEL_14",
"111": "dirt", "15": "LABEL_15",
"112": "door-stuff", "16": "LABEL_16",
"113": "fence", "17": "LABEL_17",
"114": "floor-marble", "18": "LABEL_18",
"115": "floor-other", "19": "LABEL_19",
"116": "floor-stone", "20": "LABEL_20",
"117": "floor-tile", "21": "LABEL_21",
"118": "floor-wood", "22": "LABEL_22",
"119": "flower", "23": "LABEL_23",
"12": "street sign", "24": "LABEL_24",
"120": "fog", "25": "LABEL_25",
"121": "food-other", "26": "LABEL_26",
"122": "fruit", "27": "LABEL_27",
"123": "furniture-other", "28": "LABEL_28",
"124": "grass", "29": "LABEL_29",
"125": "gravel", "30": "LABEL_30",
"126": "ground-other", "31": "LABEL_31",
"127": "hill", "32": "LABEL_32",
"128": "house", "33": "LABEL_33",
"129": "leaves", "34": "LABEL_34",
"13": "stop sign", "35": "LABEL_35",
"130": "light", "36": "LABEL_36",
"131": "mat", "37": "LABEL_37",
"132": "metal", "38": "LABEL_38",
"133": "mirror-stuff", "39": "LABEL_39",
"134": "moss", "40": "LABEL_40",
"135": "mountain", "41": "LABEL_41",
"136": "mud", "42": "LABEL_42",
"137": "napkin", "43": "LABEL_43",
"138": "net", "44": "LABEL_44",
"139": "paper", "45": "LABEL_45",
"14": "parking meter", "46": "LABEL_46",
"140": "pavement", "47": "LABEL_47",
"141": "pillow", "48": "LABEL_48",
"142": "plant-other", "49": "LABEL_49",
"143": "plastic", "50": "LABEL_50",
"144": "platform", "51": "LABEL_51",
"145": "playingfield", "52": "LABEL_52",
"146": "railing", "53": "LABEL_53",
"147": "railroad", "54": "LABEL_54",
"148": "river", "55": "LABEL_55",
"149": "road", "56": "LABEL_56",
"15": "bench", "57": "LABEL_57",
"150": "rock", "58": "LABEL_58",
"151": "roof", "59": "LABEL_59",
"152": "rug", "60": "LABEL_60",
"153": "salad", "61": "LABEL_61",
"154": "sand", "62": "LABEL_62",
"155": "sea", "63": "LABEL_63",
"156": "shelf", "64": "LABEL_64",
"157": "sky-other", "65": "LABEL_65",
"158": "skyscraper", "66": "LABEL_66",
"159": "snow", "67": "LABEL_67",
"16": "bird", "68": "LABEL_68",
"160": "solid-other", "69": "LABEL_69",
"161": "stairs", "70": "LABEL_70",
"162": "stone", "71": "LABEL_71",
"163": "straw", "72": "LABEL_72",
"164": "structural-other", "73": "LABEL_73",
"165": "table", "74": "LABEL_74",
"166": "tent", "75": "LABEL_75",
"167": "textile-other", "76": "LABEL_76",
"168": "towel", "77": "LABEL_77",
"169": "tree", "78": "LABEL_78",
"17": "cat", "79": "LABEL_79",
"170": "vegetable", "80": "LABEL_80",
"171": "wall-brick", "81": "LABEL_81",
"172": "wall-concrete", "82": "LABEL_82",
"173": "wall-other", "83": "LABEL_83",
"174": "wall-panel", "84": "LABEL_84",
"175": "wall-stone", "85": "LABEL_85",
"176": "wall-tile", "86": "LABEL_86",
"177": "wall-wood", "87": "LABEL_87",
"178": "water-other", "88": "LABEL_88",
"179": "waterdrops", "89": "LABEL_89",
"18": "dog", "90": "LABEL_90",
"180": "window-blind", "91": "LABEL_91",
"181": "window-other", "92": "LABEL_92",
"182": "wood", "93": "LABEL_93",
"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", "183": "LABEL_183",
"184": "LABEL_184", "184": "LABEL_184",
"185": "LABEL_185", "185": "LABEL_185",
@ -128,7 +217,6 @@
"187": "LABEL_187", "187": "LABEL_187",
"188": "LABEL_188", "188": "LABEL_188",
"189": "LABEL_189", "189": "LABEL_189",
"19": "horse",
"190": "LABEL_190", "190": "LABEL_190",
"191": "LABEL_191", "191": "LABEL_191",
"192": "LABEL_192", "192": "LABEL_192",
@ -139,8 +227,6 @@
"197": "LABEL_197", "197": "LABEL_197",
"198": "LABEL_198", "198": "LABEL_198",
"199": "LABEL_199", "199": "LABEL_199",
"2": "bicycle",
"20": "sheep",
"200": "LABEL_200", "200": "LABEL_200",
"201": "LABEL_201", "201": "LABEL_201",
"202": "LABEL_202", "202": "LABEL_202",
@ -151,7 +237,6 @@
"207": "LABEL_207", "207": "LABEL_207",
"208": "LABEL_208", "208": "LABEL_208",
"209": "LABEL_209", "209": "LABEL_209",
"21": "cow",
"210": "LABEL_210", "210": "LABEL_210",
"211": "LABEL_211", "211": "LABEL_211",
"212": "LABEL_212", "212": "LABEL_212",
@ -162,7 +247,6 @@
"217": "LABEL_217", "217": "LABEL_217",
"218": "LABEL_218", "218": "LABEL_218",
"219": "LABEL_219", "219": "LABEL_219",
"22": "elephant",
"220": "LABEL_220", "220": "LABEL_220",
"221": "LABEL_221", "221": "LABEL_221",
"222": "LABEL_222", "222": "LABEL_222",
@ -173,7 +257,6 @@
"227": "LABEL_227", "227": "LABEL_227",
"228": "LABEL_228", "228": "LABEL_228",
"229": "LABEL_229", "229": "LABEL_229",
"23": "bear",
"230": "LABEL_230", "230": "LABEL_230",
"231": "LABEL_231", "231": "LABEL_231",
"232": "LABEL_232", "232": "LABEL_232",
@ -184,7 +267,6 @@
"237": "LABEL_237", "237": "LABEL_237",
"238": "LABEL_238", "238": "LABEL_238",
"239": "LABEL_239", "239": "LABEL_239",
"24": "zebra",
"240": "LABEL_240", "240": "LABEL_240",
"241": "LABEL_241", "241": "LABEL_241",
"242": "LABEL_242", "242": "LABEL_242",
@ -194,94 +276,106 @@
"246": "LABEL_246", "246": "LABEL_246",
"247": "LABEL_247", "247": "LABEL_247",
"248": "LABEL_248", "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_std": 0.02,
"init_xavier_std": 1.0, "init_xavier_std": 1.0,
"is_encoder_decoder": true, "is_encoder_decoder": true,
"label2id": { "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_183": 183,
"LABEL_184": 184, "LABEL_184": 184,
"LABEL_185": 185, "LABEL_185": 185,
@ -289,6 +383,7 @@
"LABEL_187": 187, "LABEL_187": 187,
"LABEL_188": 188, "LABEL_188": 188,
"LABEL_189": 189, "LABEL_189": 189,
"LABEL_19": 19,
"LABEL_190": 190, "LABEL_190": 190,
"LABEL_191": 191, "LABEL_191": 191,
"LABEL_192": 192, "LABEL_192": 192,
@ -299,6 +394,8 @@
"LABEL_197": 197, "LABEL_197": 197,
"LABEL_198": 198, "LABEL_198": 198,
"LABEL_199": 199, "LABEL_199": 199,
"LABEL_2": 2,
"LABEL_20": 20,
"LABEL_200": 200, "LABEL_200": 200,
"LABEL_201": 201, "LABEL_201": 201,
"LABEL_202": 202, "LABEL_202": 202,
@ -309,6 +406,7 @@
"LABEL_207": 207, "LABEL_207": 207,
"LABEL_208": 208, "LABEL_208": 208,
"LABEL_209": 209, "LABEL_209": 209,
"LABEL_21": 21,
"LABEL_210": 210, "LABEL_210": 210,
"LABEL_211": 211, "LABEL_211": 211,
"LABEL_212": 212, "LABEL_212": 212,
@ -319,6 +417,7 @@
"LABEL_217": 217, "LABEL_217": 217,
"LABEL_218": 218, "LABEL_218": 218,
"LABEL_219": 219, "LABEL_219": 219,
"LABEL_22": 22,
"LABEL_220": 220, "LABEL_220": 220,
"LABEL_221": 221, "LABEL_221": 221,
"LABEL_222": 222, "LABEL_222": 222,
@ -329,6 +428,7 @@
"LABEL_227": 227, "LABEL_227": 227,
"LABEL_228": 228, "LABEL_228": 228,
"LABEL_229": 229, "LABEL_229": 229,
"LABEL_23": 23,
"LABEL_230": 230, "LABEL_230": 230,
"LABEL_231": 231, "LABEL_231": 231,
"LABEL_232": 232, "LABEL_232": 232,
@ -339,6 +439,7 @@
"LABEL_237": 237, "LABEL_237": 237,
"LABEL_238": 238, "LABEL_238": 238,
"LABEL_239": 239, "LABEL_239": 239,
"LABEL_24": 24,
"LABEL_240": 240, "LABEL_240": 240,
"LABEL_241": 241, "LABEL_241": 241,
"LABEL_242": 242, "LABEL_242": 242,
@ -349,196 +450,96 @@
"LABEL_247": 247, "LABEL_247": 247,
"LABEL_248": 248, "LABEL_248": 248,
"LABEL_249": 249, "LABEL_249": 249,
"N/A": 0, "LABEL_25": 25,
"airplane": 5, "LABEL_26": 26,
"apple": 53, "LABEL_27": 27,
"backpack": 27, "LABEL_28": 28,
"banana": 52, "LABEL_29": 29,
"banner": 92, "LABEL_3": 3,
"baseball bat": 39, "LABEL_30": 30,
"baseball glove": 40, "LABEL_31": 31,
"bear": 23, "LABEL_32": 32,
"bed": 65, "LABEL_33": 33,
"bench": 15, "LABEL_34": 34,
"bicycle": 2, "LABEL_35": 35,
"bird": 16, "LABEL_36": 36,
"blanket": 93, "LABEL_37": 37,
"blender": 83, "LABEL_38": 38,
"boat": 9, "LABEL_39": 39,
"book": 84, "LABEL_4": 4,
"bottle": 44, "LABEL_40": 40,
"bowl": 51, "LABEL_41": 41,
"branch": 94, "LABEL_42": 42,
"bridge": 95, "LABEL_43": 43,
"broccoli": 56, "LABEL_44": 44,
"building-other": 96, "LABEL_45": 45,
"bus": 6, "LABEL_46": 46,
"bush": 97, "LABEL_47": 47,
"cabinet": 98, "LABEL_48": 48,
"cage": 99, "LABEL_49": 49,
"cake": 61, "LABEL_5": 5,
"car": 3, "LABEL_50": 50,
"cardboard": 100, "LABEL_51": 51,
"carpet": 101, "LABEL_52": 52,
"carrot": 57, "LABEL_53": 53,
"cat": 17, "LABEL_54": 54,
"ceiling-other": 102, "LABEL_55": 55,
"ceiling-tile": 103, "LABEL_56": 56,
"cell phone": 77, "LABEL_57": 57,
"chair": 62, "LABEL_58": 58,
"clock": 85, "LABEL_59": 59,
"cloth": 104, "LABEL_6": 6,
"clothes": 105, "LABEL_60": 60,
"clouds": 106, "LABEL_61": 61,
"couch": 63, "LABEL_62": 62,
"counter": 107, "LABEL_63": 63,
"cow": 21, "LABEL_64": 64,
"cup": 47, "LABEL_65": 65,
"cupboard": 108, "LABEL_66": 66,
"curtain": 109, "LABEL_67": 67,
"desk": 69, "LABEL_68": 68,
"desk-stuff": 110, "LABEL_69": 69,
"dining table": 67, "LABEL_7": 7,
"dirt": 111, "LABEL_70": 70,
"dog": 18, "LABEL_71": 71,
"donut": 60, "LABEL_72": 72,
"door": 71, "LABEL_73": 73,
"door-stuff": 112, "LABEL_74": 74,
"elephant": 22, "LABEL_75": 75,
"eye glasses": 30, "LABEL_76": 76,
"fence": 113, "LABEL_77": 77,
"fire hydrant": 11, "LABEL_78": 78,
"floor-marble": 114, "LABEL_79": 79,
"floor-other": 115, "LABEL_8": 8,
"floor-stone": 116, "LABEL_80": 80,
"floor-tile": 117, "LABEL_81": 81,
"floor-wood": 118, "LABEL_82": 82,
"flower": 119, "LABEL_83": 83,
"fog": 120, "LABEL_84": 84,
"food-other": 121, "LABEL_85": 85,
"fork": 48, "LABEL_86": 86,
"frisbee": 34, "LABEL_87": 87,
"fruit": 122, "LABEL_88": 88,
"furniture-other": 123, "LABEL_89": 89,
"giraffe": 25, "LABEL_9": 9,
"grass": 124, "LABEL_90": 90,
"gravel": 125, "LABEL_91": 91,
"ground-other": 126, "LABEL_92": 92,
"hair brush": 91, "LABEL_93": 93,
"hair drier": 89, "LABEL_94": 94,
"handbag": 31, "LABEL_95": 95,
"hat": 26, "LABEL_96": 96,
"hill": 127, "LABEL_97": 97,
"horse": 19, "LABEL_98": 98,
"hot dog": 58, "LABEL_99": 99
"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, "mask_loss_coefficient": 1,
"max_position_embeddings": 1024, "max_position_embeddings": 1024,
"model_type": "detr", "model_type": "detr",
"num_hidden_layers": 6, "num_hidden_layers": 6,
"num_queries": 100, "num_queries": 100,
"position_embedding_type": "sine", "position_embedding_type": "sine",
"return_intermediate_layers": true,
"scale_embedding": false, "scale_embedding": false,
"transformers_version": "4.7.0.dev0" "transformers_version": "4.7.0.dev0"
} }

BIN
pytorch_model.bin (Stored with Git LFS)
View File

Binary file not shown.