zegenerative

Thansk for your reply. Apologies if this is a stupid question, but what do you mean with the script running in snowflake first?

> You want to start with a higher learning rate to get close to the optimal point quicker. But once you get close, you have to slow down in order...

I am reading this and I am super intrigued by it. I was wondering if you continued to work on this and if you made any progress in the stereo...

I am running it on paperspace (GPU enabled, let me know if you want to be more specific, but believe me, this virtual machine is a beast). Took 2,5 days...

You have to use gpu for this, cpu is too slow. If that is not the problem, try changing the training parameters. Hope it helps. Op vr 14 feb. 2020...