config.json

{
    "architectures": [
      "CerberusDetForObjectDetection"
    ],
    "auto_map": {
      "AutoConfig": "configuration_cerberus.CerberusDetConfig",
      "AutoModel": "modeling_cerberus.CerberusDetForObjectDetection",
      "AutoImageProcessor": "cerberus_image_processor.CerberusDetImageProcessor"
    },

    "init_device": "cpu",
    "model_type": "cerberus_v8x",
    "torch_dtype": "float16",
    "transformers_version": "4.50.0",
    "verbose": 0,
    "initializer_range": 0.02,
    "stride": [ 8, 16, 32],

    "agnostic_nms": false,
    "conf_thres": 0.3,
    "iou_thres": 0.45,
    "iou_thres_between_tasks": 0.8,

    "tasks_names": {
      "voc": [
        "aeroplane",
        "bicycle",
        "bird",
        "boat",
        "bottle",
        "bus",
        "car",
        "cat",
        "chair",
        "cow",
        "diningtable",
        "dog",
        "horse",
        "motorbike",
        "person",
        "pottedplant",
        "sheep",
        "sofa",
        "train",
        "tvmonitor"
      ],
      "objects365_animals": [
        "Monkey",
        "Rabbit",
        "Yak",
        "Antelope",
        "Pig",
        "Bear",
        "Deer",
        "Giraffe",
        "Zebra",
        "Elephant",
        "Lion",
        "Donkey",
        "Camel",
        "Jellyfish",
        "Other Fish",
        "Dolphin",
        "Crab",
        "Seal",
        "Goldfish"
      ]
    },
    "tasks_nc": [
      20,
      19
    ],
    "config_name": "voc_obj365_animals.yaml",
    "cfg": {
      "depth_multiple": 1.0,
      "width_multiple": 1.25,
      "backbone": [
        [
          -1,
          1,
          "Conv",
          [
            64,
            3,
            2
          ]
        ],
        [
          -1,
          1,
          "Conv",
          [
            128,
            3,
            2
          ]
        ],
        [
          -1,
          3,
          "C2f",
          [
            128,
            true
          ]
        ],
        [
          -1,
          1,
          "Conv",
          [
            256,
            3,
            2
          ]
        ],
        [
          -1,
          6,
          "C2f",
          [
            256,
            true
          ]
        ],
        [
          -1,
          1,
          "Conv",
          [
            512,
            3,
            2
          ]
        ],
        [
          -1,
          6,
          "C2f",
          [
            512,
            true
          ]
        ],
        [
          -1,
          1,
          "Conv",
          [
            512,
            3,
            2
          ]
        ],
        [
          -1,
          3,
          "C2f",
          [
            512,
            true
          ]
        ],
        [
          -1,
          1,
          "SPPF",
          [
            512,
            5
          ]
        ]
      ],
      "neck": [
        [
          9,
          1,
          "nn.Upsample",
          [
            "None",
            2,
            "nearest"
          ]
        ],
        [
          [
            -1,
            6
          ],
          1,
          "Concat",
          [
            1
          ]
        ],
        [
          -1,
          3,
          "C2f",
          [
            512
          ]
        ],
        [
          -1,
          1,
          "nn.Upsample",
          [
            "None",
            2,
            "nearest"
          ]
        ],
        [
          [
            -1,
            4
          ],
          1,
          "Concat",
          [
            1
          ]
        ],
        [
          -1,
          3,
          "C2f",
          [
            256
          ]
        ],
        [
          -1,
          1,
          "Conv",
          [
            256,
            3,
            2
          ]
        ],
        [
          [
            -1,
            12
          ],
          1,
          "Concat",
          [
            1
          ]
        ],
        [
          -1,
          3,
          "C2f",
          [
            512
          ]
        ],
        [
          -1,
          1,
          "Conv",
          [
            512,
            3,
            2
          ]
        ],
        [
          [
            -1,
            9
          ],
          1,
          "Concat",
          [
            1
          ]
        ],
        [
          -1,
          3,
          "C2f",
          [
            512
          ]
        ]
      ],
      "head": [
        [
          [
            15,
            18,
            21
          ],
          1,
          "Detect",
          []
        ]
      ],
      "cerber": [
        [
          2,
          [
            [
              13
            ],
            [
              14
            ]
          ]
        ]
      ],
      "ch": 3,
      "nc": [
        20,
        19
      ]
    }
  }