Compatibility

Image semantic segmentation

  • Datasets:
  • Models:
    • PyTorch (TorchScript format):
      • Input shape: (batch, channels, height, width)
      • Output shape: (batch, classes, height, width)
      • JSON configuration file format:
        {
            "normalization": {
                "mean": [<r>, <g>, <b>],
                "std": [<r>, <g>, <b>]
            }
        }
      
    • Tensorflow (SavedModel format):
      • Input shape: (batch, height, width, channels)
      • Output shape: (batch, height, width, classes)
      • JSON configuration file format:
        {
            "image_size": [<height>, <width>]
        }
      
    • ONNX: coming soon
  • Metrics:
    • Intersection over Union (IoU)

LiDAR semantic segmentation

Coming soon.

Object detection

Coming soon.