Upload TableTransformerForObjectDetection

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/table-transformer-structure-recognition",
+  "_name_or_path": "facebook/detr-resnet-50",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -7,13 +7,13 @@
   ],
   "attention_dropout": 0.0,
   "auxiliary_loss": false,
-  "backbone": "resnet18",
+  "backbone": "resnet50",
   "backbone_config": null,
   "backbone_kwargs": null,
   "bbox_cost": 5,
   "bbox_loss_coefficient": 5,
-  "ce_loss_coefficient": 1,
   "class_cost": 1,
+  "classifier_dropout": 0.0,
   "d_model": 256,
   "decoder_attention_heads": 8,
   "decoder_ffn_dim": 2048,
@@ -26,34 +26,204 @@
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
-  "eos_coefficient": 0.4,
+  "eos_coefficient": 0.1,
   "giou_cost": 2,
   "giou_loss_coefficient": 2,
   "id2label": {
-    "0": "table",
-    "1": "table column",
-    "2": "table row",
-    "3": "table column header",
-    "4": "table projected row header",
-    "5": "table spanning cell"
+    "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"
   },
   "init_std": 0.02,
   "init_xavier_std": 1.0,
   "is_encoder_decoder": true,
   "label2id": {
-    "table": 0,
-    "table column": 1,
-    "table column header": 3,
-    "table projected row header": 4,
-    "table row": 2,
-    "table spanning cell": 5
+    "N/A": 0,
+    "airplane": 5,
+    "apple": 53,
+    "backpack": 27,
+    "banana": 52,
+    "baseball bat": 39,
+    "baseball glove": 40,
+    "bear": 23,
+    "bed": 65,
+    "bench": 15,
+    "bicycle": 2,
+    "bird": 16,
+    "blender": 83,
+    "boat": 9,
+    "book": 84,
+    "bottle": 44,
+    "bowl": 51,
+    "broccoli": 56,
+    "bus": 6,
+    "cake": 61,
+    "car": 3,
+    "carrot": 57,
+    "cat": 17,
+    "cell phone": 77,
+    "chair": 62,
+    "clock": 85,
+    "couch": 63,
+    "cow": 21,
+    "cup": 47,
+    "desk": 69,
+    "dining table": 67,
+    "dog": 18,
+    "donut": 60,
+    "door": 71,
+    "elephant": 22,
+    "eye glasses": 30,
+    "fire hydrant": 11,
+    "fork": 48,
+    "frisbee": 34,
+    "giraffe": 25,
+    "hair drier": 89,
+    "handbag": 31,
+    "hat": 26,
+    "horse": 19,
+    "hot dog": 58,
+    "keyboard": 76,
+    "kite": 38,
+    "knife": 49,
+    "laptop": 73,
+    "microwave": 78,
+    "mirror": 66,
+    "motorcycle": 4,
+    "mouse": 74,
+    "orange": 55,
+    "oven": 79,
+    "parking meter": 14,
+    "person": 1,
+    "pizza": 59,
+    "plate": 45,
+    "potted plant": 64,
+    "refrigerator": 82,
+    "remote": 75,
+    "sandwich": 54,
+    "scissors": 87,
+    "sheep": 20,
+    "shoe": 29,
+    "sink": 81,
+    "skateboard": 41,
+    "skis": 35,
+    "snowboard": 36,
+    "spoon": 50,
+    "sports ball": 37,
+    "stop sign": 13,
+    "street sign": 12,
+    "suitcase": 33,
+    "surfboard": 42,
+    "teddy bear": 88,
+    "tennis racket": 43,
+    "tie": 32,
+    "toaster": 80,
+    "toilet": 70,
+    "toothbrush": 90,
+    "traffic light": 10,
+    "train": 7,
+    "truck": 8,
+    "tv": 72,
+    "umbrella": 28,
+    "vase": 86,
+    "window": 68,
+    "wine glass": 46,
+    "zebra": 24
   },
   "mask_loss_coefficient": 1,
   "max_position_embeddings": 1024,
   "model_type": "table-transformer",
   "num_channels": 3,
   "num_hidden_layers": 6,
-  "num_queries": 125,
+  "num_queries": 100,
   "position_embedding_type": "sine",
   "scale_embedding": false,
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3ff8fba210d0cf46611b78e2934def5c2a306c71eda66adc4be6a2baf49482
-size 115433860
+oid sha256:97e99a6487a58fa25c30faa16e909378e05ffaed7d5bbf6db2192db0e96ff7e5
+size 166589600