Pre-trained Models

We provide some models for Core ML and ML modules.

If you installed SDK with the packages/installer, the link to download those models was shared during the sign-up. If you are compiling OpenEB or SDK from source, the models can be found in <SRC_DIR>/sdk/modules/core_ml/python/models, <SRC_DIR>/sdk/modules/ml/python/models and <SRC_DIR>/sdk/modules/ml/python/models.

Event-to-Video Model

  • e2v.ckpt: Pytorch Event to Video pre-trained model which can be used in event to video inference sample The model was trained on a dataset of synthetic events sequences generated by simulation on randomly moving images.

Object Detection Models

  • Object detection TorchScript models. Those models that can be used with the C++ Detection & Tracking sample and the Python Detection & Tracking sample. Those models were trained on a dataset recorded by a camera positioned on top of a car facing forward, thus the performance of the model can be degraded in other settings.

    • Object Detection TorchScript model, trained with histogram preprocessing method

    • Object Detection TorchScript model, trained with event_cube preprocessing method

  • red_event_cube_all_classes.ckpt: Pytorch object detection model, which can be exported to torchjit model using export_detector Python sample. Note that this model was not trained as much as the TorchScript models listed above, and is mostly delivered to try-out the our export sample.

Flow Models

Classification Models

Pre-Trained models for rock-paper-scissors classification dataset: