Compatibility

Image semantic segmentation

Datasets:
- Rellis3D
- GOOSE
- Custom GAIA format: Parquet file containing samples and labels relative paths and a JSON file with the dataset ontology.
- Generic: simply assumes a different directory per split, different suffixes for samples and labels, and a JSON file containing the dataset ontology.
Models:
- PyTorch (TorchScript compiled format and native modules):
  - 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>]
      },
      "batch_size": 4
  }
```
- Tensorflow (SavedModel compiled format and native Tensorflow/Keras modules):
  - Input shape: (batch, height, width, channels)
  - Output shape: (batch, height, width, classes)
  - JSON configuration file format:
```
  {
      "image_size": [<height>, <width>],
      "batch_size": 4
  }
```
- ONNX: coming soon
Metrics:
- Intersection over Union (IoU), Accuracy

LiDAR semantic segmentation

Datasets:
- Rellis3D
- GOOSE
- Custom GAIA format: Parquet file containing samples and labels relative paths and a JSON file with the dataset ontology.
- Generic: simply assumes a different directory per split, different suffixes for samples and labels, and a JSON file containing the dataset ontology.

Models:

PyTorch (TorchScript compiled format and native modules). As of now, we have tested RandLA-Net and KPConv from Open3D-ML.

Input shape: defined by the input_format tag.
Output shape: (num_points)
JSON configuration file format:

  {
      "seed": 42,
      "input_format": "o3d_randlanet",
      "sampler": "spatially_regular",
      "recenter": {
          "dims": [
              0,
              1
          ]
      },
      "ignored_classes": [
          "void"
      ],
      "num_points": 45056,
      "grid_size": 0.06,
      "num_neighbors": 16,
      "sub_sampling_ratio": [
          4,
          4,
          4,
          4
      ]
  }

ONNX: coming soon

Metrics:
- Intersection over Union (IoU), Accuracy

Object detection

Coming soon.