This is the Pytorch implementation of DeepILS Model. DeepILS is a lightweight model that uses only IMU data and performs pedestrian inertial navigation on the edge.

DeepILS with other ResNet18-based model architectures are presented for comparative analysis. IMUNet, MobileNet, MobileNetV2, MnasNet, and EfficientNetB0 models have been re-implemented to work with one-dimensional Inertial data.

1. DeepILS is evaluated on six inertial odometry datssets.
2. You can download the proposed datasets from KIOD, INAIOD
3. IMUNet dataset can be downloaded from IMUNet
4. OxIOD dataset can be downloaded from OxIOD
5. RoNIN dataset can be downloaded from RoNIN
6. RIDI dataset can be downloaded from RIDI

The inertial trajectories and checkpoints for 6 datasets evaluated on DeepILS are available in the folder /results

The DeepILS Mobile application is available at DeepILS-Mobile.

Dependencies can be installed using the following command:

conda env create -f DeepILS.yml