search

agrimgupta92 / sgan

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
MIT License
810 stars 259 forks source link

How to reproduce S-LSTM with your code? #80

Open sanmin0312 opened 4 years ago

sanmin0312 commented 4 years ago

Hello, Thank you for sharing your code. In your paper, I think you trained S-LSTM model by yourself with your own code. But S-LSTM is not the generative model. So can you explain how did you reproduce it (maybe how to deactivate the discriminator) and can you share hyperparameters of S-LSTM that you used for the result of the paper?

vidaadl commented 4 years ago

@sanmin0312 Hi, I have the same question. Could you find out any solution?

theDebugger811 commented 3 years ago

Hi, You can find another implementation of S-LSTM here. The README describes the command-line as well.