Skip to content
VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
correlation_package
doc_fig
experiment
networks add network document graph Apr 16, 2018
scripts add R6 conversion code May 8, 2018
utils reconstruct training Apr 28, 2018
.gitignore se3 Apr 28, 2018
FlowNetC.py
FlowNetCImg.py add network document graph Apr 16, 2018
README.md
flowlib.py update to python3 Apr 8, 2018
main.py
submodules.py first commit Mar 15, 2018

README.md

non-official PyTorch implementation of VINet[1]

(Whole project are still under construction.)

Installation

It's recommand to use docker image to run this project. Docker image installation guide

Training

Log into container

sudo docker exec -it vinet bash
cd /notebooks/vinet

Execute main.py by

python3 main.py

Note

Network detail structure

[1] Clark, Ronald, et al. "VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem." AAAI. 2017.

You can’t perform that action at this time.