| { | |
| "architectures": [ | |
| "YolosForObjectDetection" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "auxiliary_loss": false, | |
| "bbox_cost": 5, | |
| "bbox_loss_coefficient": 5, | |
| "class_cost": 1, | |
| "eos_coefficient": 0.1, | |
| "giou_cost": 2, | |
| "giou_loss_coefficient": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 384, | |
| "id2label": { | |
| "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": "N/A", | |
| "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": "N/A", | |
| "27": "backpack", | |
| "28": "umbrella", | |
| "29": "N/A", | |
| "30": "N/A", | |
| "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": "N/A", | |
| "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": "N/A", | |
| "67": "dining table", | |
| "68": "N/A", | |
| "69": "N/A", | |
| "70": "toilet", | |
| "71": "N/A", | |
| "72": "tv", | |
| "73": "laptop", | |
| "74": "mouse", | |
| "75": "remote", | |
| "76": "keyboard", | |
| "77": "cell phone", | |
| "78": "microwave", | |
| "79": "oven", | |
| "80": "toaster", | |
| "81": "sink", | |
| "82": "refrigerator", | |
| "83": "N/A", | |
| "84": "book", | |
| "85": "clock", | |
| "86": "vase", | |
| "87": "scissors", | |
| "88": "teddy bear", | |
| "89": "hair drier", | |
| "90": "toothbrush" | |
| }, | |
| "image_size": [ | |
| 512, | |
| 864 | |
| ], | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "label2id": { | |
| "N/A": 83, | |
| "airplane": 5, | |
| "apple": 53, | |
| "backpack": 27, | |
| "banana": 52, | |
| "baseball bat": 39, | |
| "baseball glove": 40, | |
| "bear": 23, | |
| "bed": 65, | |
| "bench": 15, | |
| "bicycle": 2, | |
| "bird": 16, | |
| "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, | |
| "dining table": 67, | |
| "dog": 18, | |
| "donut": 60, | |
| "elephant": 22, | |
| "fire hydrant": 11, | |
| "fork": 48, | |
| "frisbee": 34, | |
| "giraffe": 25, | |
| "hair drier": 89, | |
| "handbag": 31, | |
| "horse": 19, | |
| "hot dog": 58, | |
| "keyboard": 76, | |
| "kite": 38, | |
| "knife": 49, | |
| "laptop": 73, | |
| "microwave": 78, | |
| "motorcycle": 4, | |
| "mouse": 74, | |
| "orange": 55, | |
| "oven": 79, | |
| "parking meter": 14, | |
| "person": 1, | |
| "pizza": 59, | |
| "potted plant": 64, | |
| "refrigerator": 82, | |
| "remote": 75, | |
| "sandwich": 54, | |
| "scissors": 87, | |
| "sheep": 20, | |
| "sink": 81, | |
| "skateboard": 41, | |
| "skis": 35, | |
| "snowboard": 36, | |
| "spoon": 50, | |
| "sports ball": 37, | |
| "stop sign": 13, | |
| "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, | |
| "wine glass": 46, | |
| "zebra": 24 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "model_type": "yolos", | |
| "num_attention_heads": 6, | |
| "num_channels": 3, | |
| "num_detection_tokens": 100, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "qkv_bias": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.19.0.dev0", | |
| "use_mid_position_embeddings": true | |
| } | |