pengyusi

efficiency problem of spconv library in C++ implementation

9

Hello, i'm trying to implement sparse convolution layer in c++ with tensorrt, but facing a great efficiency problem. The core step of sparse conv: ```cpp auto conv_res = ConvGemmOps::implicit_gemm( alloc2,...

Thanks for the summary of calib method. I want to test some of your algorithms but the data you provided in baidu is not accessible for me. Do you have...