Well it varies but about 1%. I figure on the GPU it won't do much, I'm hoping this will work when distributed across a bunch of CPUs.
Thanks, I'll check block_sparse and see if that helps, and post solution here if I find one. On Wednesday, August 17, 2016 at 9:41:50 AM UTC-4, nouiz wrote: > > What is the % of sparcity? On the GPU if it isn't high, it won't speed up > the computation to do sparse computation. > > We have some block sparse operation in that module, maybe it can help you: > > > http://deeplearning.net/software/theano/library/tensor/nnet/blocksparse.html?highlight=block%20sparse#module-tensor.nnet.blocksparse > > On Tue, Aug 16, 2016 at 11:31 AM, Peter O'Connor <[email protected] > <javascript:>> wrote: > >> I'm looking for an efficient way to do convolution when the input >> images/feature maps are sparse. >> >> So you'd have a sparse input (n_samples, n_features_in, n_rows, n_cols), >> a dense kernel (n_features_out, n_features_in, n_kernel_rows, >> n_kernel_cols), and produce either a sparse or dense output of shape >> (n_samples, n_features_out, n_rows +n_kernel_rows-1, >> n_cols+n_kernel_cols-1). >> >> I've seen theano's sparse sandbox >> <http://deeplearning.net/software/theano/library/sparse/sandbox.html>, >> but it's not obvious from here that it would support this kind of operation >> (it seems to be more about implementing dense convolutions as sparse matrix >> multiplications). Does anybody know of existing code that deals with this >> situation? >> >> -- >> >> --- >> You received this message because you are subscribed to the Google Groups >> "theano-users" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to [email protected] <javascript:>. >> For more options, visit https://groups.google.com/d/optout. >> > > -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
