Upload folder using huggingface_hub

README.md

@@ -1,3 +1,92 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+tags:
+- object-detection
+- vision
+datasets:
+- coco
+pipeline_tag: object-detection
+library_name: transformers
+---
+
+# LW-DETR (Light-Weight Detection Transformer)
+
+LW-DETR, a Light-Weight DEtection TRansformer model, is designed to be a real-time object detection alternative that outperforms conventional convolutional (YOLO-style) and earlier transformer-based (DETR) methods in terms of speed and accuracy trade-off. It was introduced in the paper [LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection](https://huggingface.co/papers/2406.03459) by Chen et al. and first released in this repository.
+Disclaimer: This model was originally contributed by [stevenbucaille](https://huggingface.co/stevenbucaille) in 🤗 transformers.
+
+## Model description
+
+LW-DETR is an end-to-end object detection model that uses a Vision Transformer (ViT) backbone as its encoder, a simple convolutional projector, and a shallow DETR decoder. The core philosophy is to leverage the power of transformers while implementing several efficiency-focused techniques to achieve real-time performance.
+
+Key Architectural Details:
+- ViT Encoder: Uses a plain ViT architecture. To reduce the quadratic complexity of global self-attention, it adopts interleaved window and global attentions.
+- Window-Major Organization: It employs a highly efficient window-major feature map organization scheme for attention computation, which drastically reduces the costly memory permutation operations required when transitioning between global and window attention modes, leading to lower inference latency.
+- Feature Aggregation: It aggregates features from multiple levels (intermediate and final layers) of the ViT encoder to create richer input for the decoder.
+- Projector: A C2f block (from YOLOv8) connects the encoder and decoder. For larger versions (large/xlarge), it outputs two-scale features ($1/8$ and $1/32$) to the decoder.
+- Shallow DETR Decoder: It uses a computationally efficient 3-layer transformer decoder (instead of the standard 6 layers), incorporating deformable cross-attention for faster convergence and lower latency.
+- Object Queries: It uses a mixed-query selection scheme to form the object queries from both learnable content queries and generated spatial queries (based on top-K features from the Projector).
+
+Training Details:
+- IoU-aware Classification Loss (IA-BCE loss): Enhances the classification branch by incorporating IoU information into the target score $t=s^{\alpha}u^{1-\alpha}$.
+- Group DETR: Uses a Group DETR strategy (13 parallel weight-sharing decoders) for faster training convergence without affecting inference speed.
+- Pretraining: Uses a two-stage pretraining strategy: first, ViT is pretrained on Objects365 using a Masked Image Modeling (MIM) method (CAEv2), followed by supervised retraining of the encoder and training of the projector and decoder on Objects365. This provides a significant performance boost (average of $\approx 5.5\text{ mAP}$).
+  
+### How to use
+
+You can use the raw model for object detection. See the [model hub](https://huggingface.co/models?search=stevenbucaille/lw-detr) to look for all available LW DETR models.
+
+Here is how to use this model:
+
+```python
+from transformers import AutoImageProcessor, LwDetrForObjectDetection
+import torch
+from PIL import Image
+import requests
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+processor = AutoImageProcessor.from_pretrained("stevenbucaille/lwdetr_medium_30e_objects365")
+model = LwDetrForObjectDetection.from_pretrained("stevenbucaille/lwdetr_medium_30e_objects365")
+
+inputs = processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
+
+# convert outputs (bounding boxes and class logits) to COCO API
+# let's only keep detections with score > 0.7
+target_sizes = torch.tensor([image.size[::-1]])
+results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.7)[0]
+
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+            f"Detected {model.config.id2label[label.item()]} with confidence "
+            f"{round(score.item(), 3)} at location {box}"
+    )
+```
+This should output:
+```
+Detected Jug with confidence 0.942 at location [345.8, 23.79, 640.09, 371.73]
+Detected Jug with confidence 0.911 at location [6.84, 55.37, 318.4, 474.02]
+Detected Refrigerator with confidence 0.901 at location [41.0, 72.79, 175.38, 117.24]
+Detected Refrigerator with confidence 0.788 at location [334.38, 76.9, 370.48, 187.82]
+```
+
+Currently, both the feature extractor and model support PyTorch. 
+
+## Training data
+
+The LW-DETR models are trained/finetuned on the following datasets:
+- Pretraining: Primarily conducted on [Objects365](https://www.objects365.org/overview.html), a large-scale, high-quality dataset for object detection.
+- Finetuning: Final training is performed on the standard [COCO 2017 object detection dataset](https://cocodataset.org/#home).
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{chen2024lw,
+        title={LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection},
+        author={Chen, Qiang and Su, Xiangbo and Zhang, Xinyu and Wang, Jian and Chen, Jiahui and Shen, Yunpeng and Han, Chuchu and Chen, Ziliang and Xu, Weixiang and Li, Fanrong and others},
+        journal={arXiv preprint arXiv:2406.03459},
+        year={2024}
+    }
+```

config.json

@@ -0,0 +1,836 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "architectures": [
+    "LwDetrForObjectDetection"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "cae_init_values": 0.1,
+    "dropout_prob": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 1024,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-06,
+    "mlp_ratio": 4,
+    "model_type": "lw_detr_vit",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 10,
+    "num_windows": 16,
+    "num_windows_side": 4,
+    "out_features": [
+      "stage3",
+      "stage5",
+      "stage6",
+      "stage10"
+    ],
+    "out_indices": [
+      3,
+      5,
+      6,
+      10
+    ],
+    "patch_size": 16,
+    "pretrain_image_size": 224,
+    "qkv_bias": true,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10"
+    ],
+    "use_absolute_position_embeddings": true,
+    "window_block_indices": [
+      0,
+      1,
+      3,
+      6,
+      7,
+      9
+    ]
+  },
+  "backbone_kwargs": null,
+  "batch_norm_eps": 1e-05,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 2,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_cross_attention_heads": 16,
+  "decoder_ffn_dim": 2048,
+  "decoder_layers": 3,
+  "decoder_n_points": 2,
+  "decoder_self_attention_heads": 8,
+  "dice_loss_coefficient": 1,
+  "disable_custom_kernels": true,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "group_detr": 13,
+  "hidden_expansion": 0.5,
+  "id2label": {
+    "0": "Person",
+    "1": "Sneakers",
+    "10": "Cup",
+    "100": "Hanger",
+    "101": "Blackboard/Whiteboard",
+    "102": "Napkin",
+    "103": "Other Fish",
+    "104": "Orange/Tangerine",
+    "105": "Toiletry",
+    "106": "Keyboard",
+    "107": "Tomato",
+    "108": "Lantern",
+    "109": "Machinery Vehicle",
+    "11": "Street Lights",
+    "110": "Fan",
+    "111": "Green Vegetables",
+    "112": "Banana",
+    "113": "Baseball Glove",
+    "114": "Airplane",
+    "115": "Mouse",
+    "116": "Train",
+    "117": "Pumpkin",
+    "118": "Soccer",
+    "119": "Skiboard",
+    "12": "Cabinet/shelf",
+    "120": "Luggage",
+    "121": "Nightstand",
+    "122": "Tea pot",
+    "123": "Telephone",
+    "124": "Trolley",
+    "125": "Head Phone",
+    "126": "Sports Car",
+    "127": "Stop Sign",
+    "128": "Dessert",
+    "129": "Scooter",
+    "13": "Handbag/Satchel",
+    "130": "Stroller",
+    "131": "Crane",
+    "132": "Remote",
+    "133": "Refrigerator",
+    "134": "Oven",
+    "135": "Lemon",
+    "136": "Duck",
+    "137": "Baseball Bat",
+    "138": "Surveillance Camera",
+    "139": "Cat",
+    "14": "Bracelet",
+    "140": "Jug",
+    "141": "Broccoli",
+    "142": "Piano",
+    "143": "Pizza",
+    "144": "Elephant",
+    "145": "Skateboard",
+    "146": "Surfboard",
+    "147": "Gun",
+    "148": "Skating and Skiing shoes",
+    "149": "Gas stove",
+    "15": "Plate",
+    "150": "Donut",
+    "151": "Bow Tie",
+    "152": "Carrot",
+    "153": "Toilet",
+    "154": "Kite",
+    "155": "Strawberry",
+    "156": "Other Balls",
+    "157": "Shovel",
+    "158": "Pepper",
+    "159": "Computer Box",
+    "16": "Picture/Frame",
+    "160": "Toilet Paper",
+    "161": "Cleaning Products",
+    "162": "Chopsticks",
+    "163": "Microwave",
+    "164": "Pigeon",
+    "165": "Baseball",
+    "166": "Cutting/chopping Board",
+    "167": "Coffee Table",
+    "168": "Side Table",
+    "169": "Scissors",
+    "17": "Helmet",
+    "170": "Marker",
+    "171": "Pie",
+    "172": "Ladder",
+    "173": "Snowboard",
+    "174": "Cookies",
+    "175": "Radiator",
+    "176": "Fire Hydrant",
+    "177": "Basketball",
+    "178": "Zebra",
+    "179": "Grape",
+    "18": "Book",
+    "180": "Giraffe",
+    "181": "Potato",
+    "182": "Sausage",
+    "183": "Tricycle",
+    "184": "Violin",
+    "185": "Egg",
+    "186": "Fire Extinguisher",
+    "187": "Candy",
+    "188": "Fire Truck",
+    "189": "Billiards",
+    "19": "Gloves",
+    "190": "Converter",
+    "191": "Bathtub",
+    "192": "Wheelchair",
+    "193": "Golf Club",
+    "194": "Briefcase",
+    "195": "Cucumber",
+    "196": "Cigar/Cigarette",
+    "197": "Paint Brush",
+    "198": "Pear",
+    "199": "Heavy Truck",
+    "2": "Chair",
+    "20": "Storage box",
+    "200": "Hamburger",
+    "201": "Extractor",
+    "202": "Extension Cord",
+    "203": "Tong",
+    "204": "Tennis Racket",
+    "205": "Folder",
+    "206": "American Football",
+    "207": "earphone",
+    "208": "Mask",
+    "209": "Kettle",
+    "21": "Boat",
+    "210": "Tennis",
+    "211": "Ship",
+    "212": "Swing",
+    "213": "Coffee Machine",
+    "214": "Slide",
+    "215": "Carriage",
+    "216": "Onion",
+    "217": "Green beans",
+    "218": "Projector",
+    "219": "Frisbee",
+    "22": "Leather Shoes",
+    "220": "Washing Machine/Drying Machine",
+    "221": "Chicken",
+    "222": "Printer",
+    "223": "Watermelon",
+    "224": "Saxophone",
+    "225": "Tissue",
+    "226": "Toothbrush",
+    "227": "Ice cream",
+    "228": "Hot-air balloon",
+    "229": "Cello",
+    "23": "Flower",
+    "230": "French Fries",
+    "231": "Scale",
+    "232": "Trophy",
+    "233": "Cabbage",
+    "234": "Hot dog",
+    "235": "Blender",
+    "236": "Peach",
+    "237": "Rice",
+    "238": "Wallet/Purse",
+    "239": "Volleyball",
+    "24": "Bench",
+    "240": "Deer",
+    "241": "Goose",
+    "242": "Tape",
+    "243": "Tablet",
+    "244": "Cosmetics",
+    "245": "Trumpet",
+    "246": "Pineapple",
+    "247": "Golf Ball",
+    "248": "Ambulance",
+    "249": "Parking meter",
+    "25": "Potted Plant",
+    "250": "Mango",
+    "251": "Key",
+    "252": "Hurdle",
+    "253": "Fishing Rod",
+    "254": "Medal",
+    "255": "Flute",
+    "256": "Brush",
+    "257": "Penguin",
+    "258": "Megaphone",
+    "259": "Corn",
+    "26": "Bowl/Basin",
+    "260": "Lettuce",
+    "261": "Garlic",
+    "262": "Swan",
+    "263": "Helicopter",
+    "264": "Green Onion",
+    "265": "Sandwich",
+    "266": "Nuts",
+    "267": "Speed Limit Sign",
+    "268": "Induction Cooker",
+    "269": "Broom",
+    "27": "Flag",
+    "270": "Trombone",
+    "271": "Plum",
+    "272": "Rickshaw",
+    "273": "Goldfish",
+    "274": "Kiwi fruit",
+    "275": "Router/modem",
+    "276": "Poker Card",
+    "277": "Toaster",
+    "278": "Shrimp",
+    "279": "Sushi",
+    "28": "Pillow",
+    "280": "Cheese",
+    "281": "Notepaper",
+    "282": "Cherry",
+    "283": "Pliers",
+    "284": "CD",
+    "285": "Pasta",
+    "286": "Hammer",
+    "287": "Cue",
+    "288": "Avocado",
+    "289": "Hami melon",
+    "29": "Boots",
+    "290": "Flask",
+    "291": "Mushroom",
+    "292": "Screwdriver",
+    "293": "Soap",
+    "294": "Recorder",
+    "295": "Bear",
+    "296": "Eggplant",
+    "297": "Board Eraser",
+    "298": "Coconut",
+    "299": "Tape Measure/Ruler",
+    "3": "Other Shoes",
+    "30": "Vase",
+    "300": "Pig",
+    "301": "Showerhead",
+    "302": "Globe",
+    "303": "Chips",
+    "304": "Steak",
+    "305": "Crosswalk Sign",
+    "306": "Stapler",
+    "307": "Camel",
+    "308": "Formula 1",
+    "309": "Pomegranate",
+    "31": "Microphone",
+    "310": "Dishwasher",
+    "311": "Crab",
+    "312": "Hoverboard",
+    "313": "Meatball",
+    "314": "Rice Cooker",
+    "315": "Tuba",
+    "316": "Calculator",
+    "317": "Papaya",
+    "318": "Antelope",
+    "319": "Parrot",
+    "32": "Necklace",
+    "320": "Seal",
+    "321": "Butterfly",
+    "322": "Dumbbell",
+    "323": "Donkey",
+    "324": "Lion",
+    "325": "Urinal",
+    "326": "Dolphin",
+    "327": "Electric Drill",
+    "328": "Hair Dryer",
+    "329": "Egg tart",
+    "33": "Ring",
+    "330": "Jellyfish",
+    "331": "Treadmill",
+    "332": "Lighter",
+    "333": "Grapefruit",
+    "334": "Game board",
+    "335": "Mop",
+    "336": "Radish",
+    "337": "Baozi",
+    "338": "Target",
+    "339": "French",
+    "34": "SUV",
+    "340": "Spring Rolls",
+    "341": "Monkey",
+    "342": "Rabbit",
+    "343": "Pencil Case",
+    "344": "Yak",
+    "345": "Red Cabbage",
+    "346": "Binoculars",
+    "347": "Asparagus",
+    "348": "Barbell",
+    "349": "Scallop",
+    "35": "Wine Glass",
+    "350": "Noddles",
+    "351": "Comb",
+    "352": "Dumpling",
+    "353": "Oyster",
+    "354": "Table Tennis paddle",
+    "355": "Cosmetics Brush/Eyeliner Pencil",
+    "356": "Chainsaw",
+    "357": "Eraser",
+    "358": "Lobster",
+    "359": "Durian",
+    "36": "Belt",
+    "360": "Okra",
+    "361": "Lipstick",
+    "362": "Cosmetics Mirror",
+    "363": "Curling",
+    "364": "Table Tennis",
+    "365": "N/A",
+    "37": "Monitor/TV",
+    "38": "Backpack",
+    "39": "Umbrella",
+    "4": "Hat",
+    "40": "Traffic Light",
+    "41": "Speaker",
+    "42": "Watch",
+    "43": "Tie",
+    "44": "Trash bin Can",
+    "45": "Slippers",
+    "46": "Bicycle",
+    "47": "Stool",
+    "48": "Barrel/bucket",
+    "49": "Van",
+    "5": "Car",
+    "50": "Couch",
+    "51": "Sandals",
+    "52": "Basket",
+    "53": "Drum",
+    "54": "Pen/Pencil",
+    "55": "Bus",
+    "56": "Wild Bird",
+    "57": "High Heels",
+    "58": "Motorcycle",
+    "59": "Guitar",
+    "6": "Lamp",
+    "60": "Carpet",
+    "61": "Cell Phone",
+    "62": "Bread",
+    "63": "Camera",
+    "64": "Canned",
+    "65": "Truck",
+    "66": "Traffic cone",
+    "67": "Cymbal",
+    "68": "Lifesaver",
+    "69": "Towel",
+    "7": "Glasses",
+    "70": "Stuffed Toy",
+    "71": "Candle",
+    "72": "Sailboat",
+    "73": "Laptop",
+    "74": "Awning",
+    "75": "Bed",
+    "76": "Faucet",
+    "77": "Tent",
+    "78": "Horse",
+    "79": "Mirror",
+    "8": "Bottle",
+    "80": "Power outlet",
+    "81": "Sink",
+    "82": "Apple",
+    "83": "Air Conditioner",
+    "84": "Knife",
+    "85": "Hockey Stick",
+    "86": "Paddle",
+    "87": "Pickup Truck",
+    "88": "Fork",
+    "89": "Traffic Sign",
+    "9": "Desk",
+    "90": "Balloon",
+    "91": "Tripod",
+    "92": "Dog",
+    "93": "Spoon",
+    "94": "Clock",
+    "95": "Pot",
+    "96": "Cow",
+    "97": "Cake",
+    "98": "Dining Table",
+    "99": "Sheep"
+  },
+  "init_std": 0.02,
+  "label2id": {
+    "Air Conditioner": 83,
+    "Airplane": 114,
+    "Ambulance": 248,
+    "American Football": 206,
+    "Antelope": 318,
+    "Apple": 82,
+    "Asparagus": 347,
+    "Avocado": 288,
+    "Awning": 74,
+    "Backpack": 38,
+    "Balloon": 90,
+    "Banana": 112,
+    "Baozi": 337,
+    "Barbell": 348,
+    "Barrel/bucket": 48,
+    "Baseball": 165,
+    "Baseball Bat": 137,
+    "Baseball Glove": 113,
+    "Basket": 52,
+    "Basketball": 177,
+    "Bathtub": 191,
+    "Bear": 295,
+    "Bed": 75,
+    "Belt": 36,
+    "Bench": 24,
+    "Bicycle": 46,
+    "Billiards": 189,
+    "Binoculars": 346,
+    "Blackboard/Whiteboard": 101,
+    "Blender": 235,
+    "Board Eraser": 297,
+    "Boat": 21,
+    "Book": 18,
+    "Boots": 29,
+    "Bottle": 8,
+    "Bow Tie": 151,
+    "Bowl/Basin": 26,
+    "Bracelet": 14,
+    "Bread": 62,
+    "Briefcase": 194,
+    "Broccoli": 141,
+    "Broom": 269,
+    "Brush": 256,
+    "Bus": 55,
+    "Butterfly": 321,
+    "CD": 284,
+    "Cabbage": 233,
+    "Cabinet/shelf": 12,
+    "Cake": 97,
+    "Calculator": 316,
+    "Camel": 307,
+    "Camera": 63,
+    "Candle": 71,
+    "Candy": 187,
+    "Canned": 64,
+    "Car": 5,
+    "Carpet": 60,
+    "Carriage": 215,
+    "Carrot": 152,
+    "Cat": 139,
+    "Cell Phone": 61,
+    "Cello": 229,
+    "Chainsaw": 356,
+    "Chair": 2,
+    "Cheese": 280,
+    "Cherry": 282,
+    "Chicken": 221,
+    "Chips": 303,
+    "Chopsticks": 162,
+    "Cigar/Cigarette": 196,
+    "Cleaning Products": 161,
+    "Clock": 94,
+    "Coconut": 298,
+    "Coffee Machine": 213,
+    "Coffee Table": 167,
+    "Comb": 351,
+    "Computer Box": 159,
+    "Converter": 190,
+    "Cookies": 174,
+    "Corn": 259,
+    "Cosmetics": 244,
+    "Cosmetics Brush/Eyeliner Pencil": 355,
+    "Cosmetics Mirror": 362,
+    "Couch": 50,
+    "Cow": 96,
+    "Crab": 311,
+    "Crane": 131,
+    "Crosswalk Sign": 305,
+    "Cucumber": 195,
+    "Cue": 287,
+    "Cup": 10,
+    "Curling": 363,
+    "Cutting/chopping Board": 166,
+    "Cymbal": 67,
+    "Deer": 240,
+    "Desk": 9,
+    "Dessert": 128,
+    "Dining Table": 98,
+    "Dishwasher": 310,
+    "Dog": 92,
+    "Dolphin": 326,
+    "Donkey": 323,
+    "Donut": 150,
+    "Drum": 53,
+    "Duck": 136,
+    "Dumbbell": 322,
+    "Dumpling": 352,
+    "Durian": 359,
+    "Egg": 185,
+    "Egg tart": 329,
+    "Eggplant": 296,
+    "Electric Drill": 327,
+    "Elephant": 144,
+    "Eraser": 357,
+    "Extension Cord": 202,
+    "Extractor": 201,
+    "Fan": 110,
+    "Faucet": 76,
+    "Fire Extinguisher": 186,
+    "Fire Hydrant": 176,
+    "Fire Truck": 188,
+    "Fishing Rod": 253,
+    "Flag": 27,
+    "Flask": 290,
+    "Flower": 23,
+    "Flute": 255,
+    "Folder": 205,
+    "Fork": 88,
+    "Formula 1": 308,
+    "French": 339,
+    "French Fries": 230,
+    "Frisbee": 219,
+    "Game board": 334,
+    "Garlic": 261,
+    "Gas stove": 149,
+    "Giraffe": 180,
+    "Glasses": 7,
+    "Globe": 302,
+    "Gloves": 19,
+    "Goldfish": 273,
+    "Golf Ball": 247,
+    "Golf Club": 193,
+    "Goose": 241,
+    "Grape": 179,
+    "Grapefruit": 333,
+    "Green Onion": 264,
+    "Green Vegetables": 111,
+    "Green beans": 217,
+    "Guitar": 59,
+    "Gun": 147,
+    "Hair Dryer": 328,
+    "Hamburger": 200,
+    "Hami melon": 289,
+    "Hammer": 286,
+    "Handbag/Satchel": 13,
+    "Hanger": 100,
+    "Hat": 4,
+    "Head Phone": 125,
+    "Heavy Truck": 199,
+    "Helicopter": 263,
+    "Helmet": 17,
+    "High Heels": 57,
+    "Hockey Stick": 85,
+    "Horse": 78,
+    "Hot dog": 234,
+    "Hot-air balloon": 228,
+    "Hoverboard": 312,
+    "Hurdle": 252,
+    "Ice cream": 227,
+    "Induction Cooker": 268,
+    "Jellyfish": 330,
+    "Jug": 140,
+    "Kettle": 209,
+    "Key": 251,
+    "Keyboard": 106,
+    "Kite": 154,
+    "Kiwi fruit": 274,
+    "Knife": 84,
+    "Ladder": 172,
+    "Lamp": 6,
+    "Lantern": 108,
+    "Laptop": 73,
+    "Leather Shoes": 22,
+    "Lemon": 135,
+    "Lettuce": 260,
+    "Lifesaver": 68,
+    "Lighter": 332,
+    "Lion": 324,
+    "Lipstick": 361,
+    "Lobster": 358,
+    "Luggage": 120,
+    "Machinery Vehicle": 109,
+    "Mango": 250,
+    "Marker": 170,
+    "Mask": 208,
+    "Meatball": 313,
+    "Medal": 254,
+    "Megaphone": 258,
+    "Microphone": 31,
+    "Microwave": 163,
+    "Mirror": 79,
+    "Monitor/TV": 37,
+    "Monkey": 341,
+    "Mop": 335,
+    "Motorcycle": 58,
+    "Mouse": 115,
+    "Mushroom": 291,
+    "N/A": 365,
+    "Napkin": 102,
+    "Necklace": 32,
+    "Nightstand": 121,
+    "Noddles": 350,
+    "Notepaper": 281,
+    "Nuts": 266,
+    "Okra": 360,
+    "Onion": 216,
+    "Orange/Tangerine": 104,
+    "Other Balls": 156,
+    "Other Fish": 103,
+    "Other Shoes": 3,
+    "Oven": 134,
+    "Oyster": 353,
+    "Paddle": 86,
+    "Paint Brush": 197,
+    "Papaya": 317,
+    "Parking meter": 249,
+    "Parrot": 319,
+    "Pasta": 285,
+    "Peach": 236,
+    "Pear": 198,
+    "Pen/Pencil": 54,
+    "Pencil Case": 343,
+    "Penguin": 257,
+    "Pepper": 158,
+    "Person": 0,
+    "Piano": 142,
+    "Pickup Truck": 87,
+    "Picture/Frame": 16,
+    "Pie": 171,
+    "Pig": 300,
+    "Pigeon": 164,
+    "Pillow": 28,
+    "Pineapple": 246,
+    "Pizza": 143,
+    "Plate": 15,
+    "Pliers": 283,
+    "Plum": 271,
+    "Poker Card": 276,
+    "Pomegranate": 309,
+    "Pot": 95,
+    "Potato": 181,
+    "Potted Plant": 25,
+    "Power outlet": 80,
+    "Printer": 222,
+    "Projector": 218,
+    "Pumpkin": 117,
+    "Rabbit": 342,
+    "Radiator": 175,
+    "Radish": 336,
+    "Recorder": 294,
+    "Red Cabbage": 345,
+    "Refrigerator": 133,
+    "Remote": 132,
+    "Rice": 237,
+    "Rice Cooker": 314,
+    "Rickshaw": 272,
+    "Ring": 33,
+    "Router/modem": 275,
+    "SUV": 34,
+    "Sailboat": 72,
+    "Sandals": 51,
+    "Sandwich": 265,
+    "Sausage": 182,
+    "Saxophone": 224,
+    "Scale": 231,
+    "Scallop": 349,
+    "Scissors": 169,
+    "Scooter": 129,
+    "Screwdriver": 292,
+    "Seal": 320,
+    "Sheep": 99,
+    "Ship": 211,
+    "Shovel": 157,
+    "Showerhead": 301,
+    "Shrimp": 278,
+    "Side Table": 168,
+    "Sink": 81,
+    "Skateboard": 145,
+    "Skating and Skiing shoes": 148,
+    "Skiboard": 119,
+    "Slide": 214,
+    "Slippers": 45,
+    "Sneakers": 1,
+    "Snowboard": 173,
+    "Soap": 293,
+    "Soccer": 118,
+    "Speaker": 41,
+    "Speed Limit Sign": 267,
+    "Spoon": 93,
+    "Sports Car": 126,
+    "Spring Rolls": 340,
+    "Stapler": 306,
+    "Steak": 304,
+    "Stool": 47,
+    "Stop Sign": 127,
+    "Storage box": 20,
+    "Strawberry": 155,
+    "Street Lights": 11,
+    "Stroller": 130,
+    "Stuffed Toy": 70,
+    "Surfboard": 146,
+    "Surveillance Camera": 138,
+    "Sushi": 279,
+    "Swan": 262,
+    "Swing": 212,
+    "Table Tennis": 364,
+    "Table Tennis paddle": 354,
+    "Tablet": 243,
+    "Tape": 242,
+    "Tape Measure/Ruler": 299,
+    "Target": 338,
+    "Tea pot": 122,
+    "Telephone": 123,
+    "Tennis": 210,
+    "Tennis Racket": 204,
+    "Tent": 77,
+    "Tie": 43,
+    "Tissue": 225,
+    "Toaster": 277,
+    "Toilet": 153,
+    "Toilet Paper": 160,
+    "Toiletry": 105,
+    "Tomato": 107,
+    "Tong": 203,
+    "Toothbrush": 226,
+    "Towel": 69,
+    "Traffic Light": 40,
+    "Traffic Sign": 89,
+    "Traffic cone": 66,
+    "Train": 116,
+    "Trash bin Can": 44,
+    "Treadmill": 331,
+    "Tricycle": 183,
+    "Tripod": 91,
+    "Trolley": 124,
+    "Trombone": 270,
+    "Trophy": 232,
+    "Truck": 65,
+    "Trumpet": 245,
+    "Tuba": 315,
+    "Umbrella": 39,
+    "Urinal": 325,
+    "Van": 49,
+    "Vase": 30,
+    "Violin": 184,
+    "Volleyball": 239,
+    "Wallet/Purse": 238,
+    "Washing Machine/Drying Machine": 220,
+    "Watch": 42,
+    "Watermelon": 223,
+    "Wheelchair": 192,
+    "Wild Bird": 56,
+    "Wine Glass": 35,
+    "Yak": 344,
+    "Zebra": 178,
+    "earphone": 207
+  },
+  "model_type": "lw_detr",
+  "num_feature_levels": 1,
+  "num_queries": 300,
+  "projector_in_channels": [
+    256
+  ],
+  "projector_out_channels": 256,
+  "projector_scale_factors": [
+    1.0
+  ],
+  "transformers_version": "5.0.0.dev0",
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de07cea05915e84d8505e7412389d7cf94faa24f4c5a4ae12cc299581998418
+size 116974744

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DeformableDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 640,
+    "width": 640
+  }
+}