# trajnetplusplusbaselines

**Repository Path**: herolin12/trajnetplusplusbaselines

## Basic Information

- **Project Name**: trajnetplusplusbaselines
- **Description**: Baselines for TrajNet++ 
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-07-23
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

Link to the Challenge: `Trajnet++Challenge <https://www.aicrowd.com/challenges/trajnet-a-trajectory-forecasting-challenge>`_

Starter Guide (NEW): `IntroducingTrajnet++Framework <https://thedebugger811.github.io/posts/2020/03/intro_trajnetpp/>`_

Data Setup
==========

Data Directory Setup
--------------------

All Datasets are stored in DATA_BLOCK

All Models after training are stored in OUTPUT_BLOCK: ``mkdir OUTPUT_BLOCK``

Data Conversion
---------------

For data conversion, refer to trajnetplusplusdataset.

After conversion, copy the converted dataset to DATA_BLOCK

Training LSTMs
==============

The training script and its help menu:
``python -m trajnetbaselines.lstm.trainer --help``

Training GANs
==============

The training script and its help menu:
``python -m trajnetbaselines.sgan.trainer --help``

Evaluation
==========

The evaluation script and its help menu: ``python -m evaluator.trajnet_evaluator --help``

Evaluation on datasplits is based on the following categorization:

.. image:: docs/train/Categorize.png