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
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.
red_histogram_05_2020.zip: Object Detection TorchScript model, trained with
red_event_cube_05_2020.zip: Object Detection TorchScript model, trained with
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.
Pre-Trained models for rock-paper-scissors classification dataset:
convRNN_chifoumi.zip: ConvRNN TorchScript classification which can be used in Classification Inference sample
mobilenetv2_chifoumi_fp32.zip: Mobilenetv2 TorchScript classification model which can be used in Classification Inference sample
chifoumi_rnn.ckpt: ConvRNN Pytorch classification model, which can be exported to torchjit model using export_classifier Python sample.