Improve preprocess_data.m by greatly decreasing preprocessing times

nachiket92 / conv-social-pooling

Code for model proposed in: Nachiket Deo and Mohan M. Trivedi,"Convolutional Social Pooling for Vehicle Trajectory Prediction." CVPRW, 2018

MIT License

336 stars 102 forks source link

Improve preprocess_data.m by greatly decreasing preprocessing times #22

Closed thelastpolaris closed 4 years ago

thelastpolaris commented 4 years ago

On each iteration, there were repeating queries that could be done in advance before the processing starts. I got rid of the parallel loop and even without it preprocessing was done in ~20 minutes instead of ~40 hours.