justheuristic
tl;dr soon :) Right now you can fine-tune with bitsandbytes, but it's gonna take up the same memory as 16bit - but we hope this can soon be fixed. @timdettmers...
You're perfectly correct, current implementation is " just some q-learning on a convolutional neural network with experience replay and target networks". I'll add an implementation of original DQN or prioritized...
we're planning on this (and in fact could use someone help with contributions), so far you can obtain similar speed-ups by compiling with [mode](http://deeplearning.net/software/theano/library/compile/mode.html) "FAST_COMPILE" or "DEBUG_MODE"
As for conditional version, i did a tiny rework of @TIXFeniks 's notebook to make it 'conditional' and it does work: https://gist.github.com/justheuristic/f627ae57e697b02dd8a7bb23d968e593
Could you please repeat how to upload to AWS?
Thanks for the detailed report! We're gonna check if perhaps the error goes away with older/newer versions of libp2p and report back what we found.
Hi! That's strange, what does the GPU itself print? Is the trainer process on that GPU down or running alone? Does the lost GPU see others? > And I have...
Hi! Since it says that GPU is not detected, it typically means there was some hardware or driver issue. For instance, last time i had this behavior in late summer,...
> Unable to determine the device handle for GPU 0000:01:00.0: Unknown Error To be frank: we won't be able to help you with this problem. It could be either a...