Skip to content

moore269/RNNTrajectory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RNN Trajectory This repository provides a reference implementation of RNNs for Trajectory prediction described in the paper:

Using Recurrent Neural Networks in Trajectory Prediction
https://www.cs.purdue.edu/homes/moore269/docs/rnntrajectory.pdf

Prerequisites

Blocks 0.1.1
Theano
Numpy

You can use
pip install git+git://github.com/mila-udem/blocks.git@v0.1.1
-r https://raw.githubusercontent.com/mila-udem/blocks/stable/requirements.txt

Basic Usage

Example

To train an LSTM, execute the following command from the project home directory:
python train.py --rnn-type lstm

To predict using the saved model, execute:
python predict.py --rnn-type lstm

Options

You can check out the other options available using:
python train.py --help
and
python predict.py --help

Configuration

To tune more configuration parameters, simply edit config.py

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages