configs/metadata.json

{
    "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
    "version": "0.2.0",
    "changelog": {
        "0.2.0": "update license files",
        "0.1.0": "complete the first version model package",
        "0.0.1": "initialize the model package structure"
    },
    "monai_version": "1.0.0",
    "pytorch_version": "1.12.0",
    "numpy_version": "1.22.4",
    "optional_packages_version": {
        "nibabel": "4.0.1",
        "pytorch-ignite": "0.4.9"
    },
    "task": "endoscopic tool segmentation",
    "description": "A pre-trained binary segmentation model for endoscopic tool segmentation",
    "authors": "NVIDIA DLMED team",
    "copyright": "Copyright (c) 2021-2022, NVIDIA CORPORATION",
    "data_source": "private dataset",
    "data_type": "RGB",
    "image_classes": "three channel data, intensity [0-255]",
    "label_classes": "single channel data, 1/255 is tool, 0 is background",
    "pred_classes": "2 channels OneHot data, channel 1 is tool, channel 0 is background",
    "eval_metrics": {
        "mean_iou": 0.87
    },
    "references": [
        "Tan, M. and Le, Q. V. Efficientnet: Rethinking model scaling for convolutional neural networks. ICML, 2019a. https://arxiv.org/pdf/1905.11946.pdf",
        "O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234\u2013241. Springer, 2015. https://arxiv.org/pdf/1505.04597.pdf"
    ],
    "network_data_format": {
        "inputs": {
            "image": {
                "type": "magnitude",
                "format": "RGB",
                "modality": "regular",
                "num_channels": 3,
                "spatial_shape": [
                    736,
                    480
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "R",
                    "1": "G",
                    "2": "B"
                }
            }
        },
        "outputs": {
            "pred": {
                "type": "image",
                "format": "segmentation",
                "num_channels": 2,
                "spatial_shape": [
                    736,
                    480
                ],
                "dtype": "float32",
                "value_range": [
                    0,
                    1
                ],
                "is_patch_data": false,
                "channel_def": {
                    "0": "background",
                    "1": "tools"
                }
            }
        }
    }
}