Usages of loss_mask, linear_ped, Non_linear_ped in the code

agrimgupta92 / sgan

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018

MIT License

813 stars 261 forks source link

Usages of loss_mask, linear_ped, Non_linear_ped in the code #38

Closed ybpaopao closed 5 years ago

ybpaopao commented 5 years ago

Hi, there are some variables like loss_mask, linear_ped, non_linear_ped but I do not know their usages. I did not find them in your work of sgan. So, what your purpose of using these variables? For example, you calculated disp_error, disp_error_l, and disp_error_nl, what's the difference?

agrimgupta92 commented 5 years ago

I used these variables for tracking different methods, models I tried over the course of the project. Non linear trajectories are harder to model/predict and can give indication if some method is able to better model these non-linear trajectories.