Skip to content

Video and image modeling in the continuous-time (CT) domain.

Notifications You must be signed in to change notification settings

normal-computing/ct-video-modeling

Repository files navigation

Continuous-Time Neural CDEs

Code release for our paper here: https://arxiv.org/abs/2311.04986

Installation

conda env create -f environment.yaml

Dataset setup

For Moving MNIST (https://www.cs.toronto.edu/~nitish/unsupervised_video/):

cd datasets/MNIST && chmod +x download.sh && ./download.sh

For Kinetics (https://www.crcv.ucf.edu/data/UCF101.php):

cd datasets/UCF101 && chmod +x download.sh && ./download.sh

Running

To start a training run, run the following (leave the comma behind the 0,):

PYTHONPATH=. python main.py --base <path_to_config> --devices 0,

About

Video and image modeling in the continuous-time (CT) domain.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published