Andrej
Hi @davidlfox , what you're observing is the current intended behavior, hence the name `init_from` rather than `resume_from`. The issue is that resuming _precisely_ would be a bit tricky (e.g....
Hi thank you for submitting this PR but I am hesitant to merge it to master in fear of breaking previous functionality etc, since it looks like a major change....
interesting, we could instead have a -primefile flag perhaps. This wouldn't be hard to implement, If you take a stab at it I'd be happy to merge a PR. Otherwise...
interesting. 3GB is very large by the way, I'm not even sure if a huge LSTM running on 12GB GPU could fit that. We have PR in works that will...
Hmmm, two things: 1. that PR (#74) was merged to master a while ago, so it's odd that you had to merge it manually 2. the eval() function does not...
I'd look at eval_split function in the main training code instead of the sampling script.
Hi, this looks good. Have you double checked that it also gives the same results as the old implementation?
I'm afraid not, beyond what's in the code. Or can ask here EDIT: also some docs on main convnetjs.com page
1. those two x are not same and have nothing to do with each other 2. yes 3. it's a loop going backwards I assume 4. see cs231n notes under...
You have to require deepqlearn by itself and separately, I think. Does that work? It's not part of the library as default, it's only provided on a side because I...