seuqaj114 / paig Goto Github PK

You might want to consider adding a License to your project (such as the MIT License), to allow others to build on your project: https://help.github.com/en/articles/licensing-a-repository#what-happens-if-i-dont-choose-a-license

Hi there, could you point me in the code where the spatial transformer is? it doesn't seem like i could find it.

Thanks for the code! Will there be a pytorch version?

Hi, nice work, i have checked you dataset in Google drive and got confused. For example the data Datasets/3bp_color/color_3bp_vx2_vy2_sl40_r2_g60_m1_dt05.npz.
The size of train_x is <class 'tuple'>: (10, 40, 36, 36, 3) which means the training set contains only 10 samples. Shouldn't is have more like 5000?

Hi Miguel,

Thanks for your code. Would you please share more details about the encoder and decoder for the single pendulum case corresponding to the VISION-BASED MODEL-PREDICTIVE CONTROL (MPC) in the paper?

Hello, can I ask you how to make .npz data from a normal video?
I want to reproduce your work with my own one but I'm not sure how to process it properly.