Open keqian9 opened 5 years ago
I think it is partly because in some networks BN are defined as a separate layer. I don't think NVDLA's compiler will merge or partition layers defined in caffe model. So if the model defines BN as a separate layer, the compiler will assume so, then SDP will work in a separate mode, which means loading data from SDP_RDMA, instead of from CACC.
Convolution and SDP can be fused in one HW layer in NVDLA.
If you compile your network with the fast-math flag, then BN is actually combined with the CONV layer. The basic flag which is used as default seems to treat them independently.
Hi, Does anyone known why batch normalize is implemented independently in SDP? it should be implemented with conv together.
Thanks.