Upload RelationDetrForObjectDetection

config.json

@@ -15,125 +15,127 @@
       4
     ]
   },
+  "bbox_cost": 5,
   "bbox_loss_coefficient": 5,
   "box_noise_scale": 1.0,
+  "class_cost": 2,
   "class_loss_coefficient": 1,
-  "cost_bbox": 5,
-  "cost_class": 2,
-  "cost_giou": 2,
   "d_model": 256,
+  "d_relation": 16,
   "decoder_attention_heads": 8,
   "decoder_ffn_dim": 2048,
   "decoder_layers": 6,
   "decoder_n_points": 4,
-  "denoising_nums": 100,
   "dilation": false,
   "disable_custom_kernels": false,
   "dropout": 0.0,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "encoder_n_points": 4,
   "focal_alpha": 0.25,
   "focal_gamma": 2.0,
+  "giou_cost": 2,
   "giou_loss_coefficient": 2,
   "hybrid_assign": 6,
   "hybrid_queries": 1500,
   "id2label": {
-    "0": "none",
-    "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": "none",
-    "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": "none",
-    "27": "backpack",
-    "28": "umbrella",
-    "29": "none",
-    "30": "none",
-    "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": "none",
-    "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": "none",
-    "67": "dining table",
-    "68": "none",
-    "69": "none",
-    "70": "toilet",
-    "71": "none",
-    "72": "tv",
-    "73": "laptop",
-    "74": "mouse",
-    "75": "remote",
-    "76": "keyboard",
-    "77": "cell phone",
-    "78": "microwave",
-    "79": "oven",
-    "80": "toaster",
-    "81": "sink",
-    "82": "refrigerator",
-    "83": "none",
-    "84": "book",
-    "85": "clock",
-    "86": "vase",
-    "87": "scissors",
-    "88": "teddy bear",
-    "89": "hair drier",
-    "90": "toothbrush"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90"
   },
   "init_std": 0.02,
   "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -227,16 +229,23 @@
     "LABEL_9": 9,
     "LABEL_90": 90
   },
-  "label_noise_prob": 0.5,
-  "loss_alpha": 0.25,
-  "loss_gamma": 2.0,
+  "label_noise_ratio": 0.5,
+  "max_position_embeddings": 2048,
   "model_type": "relation_detr",
   "num_channels": 3,
+  "num_denoising": 100,
   "num_feature_levels": 4,
   "num_queries": 900,
-  "relation_embed": 16,
+  "position_embedding_type": "sine",
+  "rel_scale": 100,
+  "rel_temperature": 10000,
+  "sin_cos_normalize": true,
+  "sin_cos_offset": -0.5,
+  "sin_cos_scale": 6.283185307179586,
+  "sin_cos_temperature": 10000,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
-  "use_pretrained_backbone": true,
+  "transformers_version": "4.47.0.dev0",
+  "two_stage_binary_cls": false,
+  "use_pretrained_backbone": false,
   "use_timm_backbone": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edfbb1cee860a5b3f0b2477642adac6c3881a81db1387de3cfb521f15378eed9
-size 195967416
+oid sha256:f952797b9a02e29a81dcb3e71ae204adfe59785da0fb9bcf8f426614e092e36b
+size 195972272