Michael J Tanana

Wow...no memory leak when I iterate over data with the loader, even when I cuda the input. Might really be a memory leak in the model libraries

Yeah- good call breaking it down that way. I'll let you know what I find

wow...it's in the forward step before adding any other the others... I cuda'd the inputs over many iterations and no issue.... then self.model:forward(inputs) and the memory explodes

Pretty sure it has to do with the convolutions inside of a nn.Sequence() Didn't solve it...but I did find some memory, but major speed improvement by switching the convolutions to...

Haha...soved!!! From the cudnn literature: `by default, cudnn.fastest is set to false. You should set to true if memory is not an issue, and you want the fastest performance` (See...

@SeanNaren btw...like the way the aync loader works...that's a nice touch...glad that sucker wasn't leaking the memory.

Nevermind...managed to crash it again...I'll keep at it

Yeah...I think I'm realizing now that the size of the batches are just increasing because of how the loader works. As the sequence size increases, the memory is increasing as...

Also- wrote some error catching code so that if you occasionally have a talk turn that is too long for the CUDA memory, it will catch the error instead of...

Hey guys- I have a fork that does that [TorchNeuralConvo](https://github.com/mtanana/torchneuralconvo/) And that's basically how I did it. (Order the vocab by count and then replace) But, there are some tricks...