Andrej

I think Ideally I'd like ConvNetJS to be a small core library that devs can rely on. Except I'm just barely familiar with Node - this complicates things :)

I think this must be because some Typed Arrays somehow got made into ordinary JS arrays. I can't remember if I properly account for this in the loading JSON. It...

sorry about this. I'm a bit of an `npm` noob as well, so that doesn't help. Any recommendations for what should be done to make this clean? I could try...

interesting! thanks for pointing this out, I wasn't previously aware of it. I think the ultimate frontier of JS DeepLearning is still on GPU. It would be ideal if there...

Nice, thanks for looking into this. Maybe it's possible to check if the user has TypedObject.float64 arrays available and if so, use them under the hood. We already do this...

Hi Martin, A network that was trained in ConvNetJS can be serialized with net.toJSON(), as mentioned in docs. And then loaded with net.fromJSON() Currently there is no support for taking...

Good question, I only had a brief look at some of these. bson and similar protocols seem like a possibility but I've never fully investigated it. I've also considered super...

Yeah the more annoying one was group convolution (the parameter group:2). That's the point where I gave up because I was too lazy to implement it, although it probably would...

The MagicNet will never stop - the idea is that the longer it runs the better its predictions will be. You have to decide for yourself when you want to...

Great, will take a look later tonight!