Suhas
Results
4
comments of
Suhas
Hi Boris, Well you are right, you need to have bigger batch size and more gpus. I think the reason you get out of memory error is because in permute...
@maciejkorzepa on what basis did you choose maxNorm as 100?. I went through maxNorm paper (http://www.jmlr.org/proceedings/papers/v28/pascanu13.pdf) . They mention to take average norm across many updates and choose half or...
You will have to modify lot of code, all the matrix multiplication (dot product) needs to be done on gpu. All the layers calculation on GPU.