{
    "metainfo":
    {
      "dataset_type": "test_dataset",
      "task_name": "test_task",
      "empty_list": []
    },
    "data_list":
    [
      {
        "img_path": "test_img.jpg",
        "height": 604,
        "width": 640,
        "instances":
        [
          {
            "bbox": [0, 0, 10, 20],
            "bbox_label": 1,
            "mask": [[0,0],[0,10],[10,20],[20,0]],
            "extra_anns": [1,2,3]
          },
          {
            "bbox": [10, 10, 110, 120],
            "bbox_label": 2,
            "mask": [[10,10],[10,110],[110,120],[120,10]],
            "extra_anns": [4,5,6]
          }
        ]
      },
      {
        "img_path": "gray.jpg",
        "height": 288,
        "width": 512,
        "instances":
        [
          {
            "bbox": [0, 0, 10, 20],
            "bbox_label": 1,
            "mask": [[0,0],[0,10],[10,20],[20,0]],
            "extra_anns": [1,2,3]
          },
          {
            "bbox": [10, 10, 110, 120],
            "bbox_label": 2,
            "mask": [[10,10],[10,110],[110,120],[120,10]],
            "extra_anns": [4,5,6]
          }
        ]
      },
      {
        "img_path": "gray.jpg",
        "height": 512,
        "width": 512,
        "instances":
        [
          {
            "bbox": [0, 0, 10, 20],
            "bbox_label": 1,
            "mask": [[0,0],[0,10],[10,20],[20,0]],
            "extra_anns": [1,2,3]
          },
          {
            "bbox": [10, 10, 110, 120],
            "bbox_label": 2,
            "mask": [[10,10],[10,110],[110,120],[120,10]],
            "extra_anns": [4,5,6]
          }
        ]
      }
    ]
  }