-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
you can use caffe with time on the command line.
It gives you forward and backward time for a batch.
In my tests the batch size was not too important (I think, because the
net is quite large)...
cuDNN helps a lot in training, I did not test recently
Caffe looks like it runs the same net on CPU and GPU with no conversion. I'm
going to see if I can get it working on an AWS GPU instance this weekend.
David
> -Original Message-
> From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf
> Of Michael Markefka
> Sent: Wedn
If you are using caffe, the network evaluator is single threaded, but it spends
almost all of its time in BLAS, which uses one thread per virtual CPU.On a
somewhat slower i7, I’m seeing about 200 ms.
David
> -Original Message-
> From: Computer-go [mailto:computer-go-boun...@computer
I got the basics of Machine learning (including sample neural nets) from Andrew
Ng's course course, two or three years ago. I highly recommend it. Lots of
practical advice. The rest came from reading papers and probably some on-line
searches. Amazon's Computer Vision team uses deep neural ne
