agrimgupta92 / sgan

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

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Does the parameter "num_epochs" really work?

a79687417 opened this issue · comments

I set "num_epochs" 200 as default, but the training process usually goes up to 350+. It seems like, in the code, this parameter is only for counting total iterations, and does nothing in actual iterating.

I think it depends on args.num_iterations. So, in line 123, 125 and 227 in train.py, it calculated the number of iterations again which is determined by how large is your dataset, batche_size and d_steps.