Deep learning with 4D spatio-temporal data representations for OCT-based force estimation

Here, we will publish our code for our paper on 4D deep learning for vision-based force estimation.

You can find the paper here: https://doi.org/10.1016/j.media.2020.101730

Preprint on arxiv: https://arxiv.org/abs/2005.10033

You can find all the models in the models.py file. The definition of 4D convolutional layers can be found in conv4d.py.

This repository also contains an entire environment for training and evaluating models. Some example configs for that are given in the cfgs folder. If you are interesting in training some models with our data, plase feel free to contact me.