search

umautobots / bidirection-trajectory-predicter

The code for Bi-directional Trajectory Prediction (BiTraP).
Other
78 stars 23 forks source link

About reproduce the result #8

Closed guoyage closed 2 years ago

guoyage commented 3 years ago

Hi, I'm trying to reproduce your experiment and i had some problems.

The results for the datasets (eth/hotel/univ) are similar to the results in the paper, but the testing results of the dataset (zara1 and zara2) are quite different from the results in the paper. I am curious what might be caused by this.

My testing results on zara1 are 0.15/0.35, zara2 are 0.14/0.26.

MoonBlvd commented 3 years ago

Hi @guoyage , thank you for your interest. Have you tried the trained model provided in the repo? Can you reproduce results using those weights?