network structure and training

[ZHANGRUI666]

respected author: i have a puzzle that the three components: representation and dynamics as well as prediction network are constructed in one big conv network? if they work seperately ,how to train them jointly and in 'end to end' fashion? can you figure it out?

[YuriCat]

Hi, Constructing one big net is not necessary in this case. You can tell an optimizer the whole parameters to train. Following code will work.

---

rep, dyn, pre = Rep(), Dyn(), Pre() params = list(rep.parameters()) + list(dyn.parameters()) + list(pre.parameters()) opt = optim.SGD(params, lr=1e-3)

... (forward and backward computation in the same way)

[ZHANGRUI666]

So cute！ your reply helps me a lot and the program is exellent 😀