JinyuanShao comments

Results 4 comments of


                                            JinyuanShao

我准备建立一个关于mmdetection的小组，想加入一起讨论的请留下QQ号

525551611

[Exception|implicit_gemm_pair]indices=torch.Size([0, 4]),bs=1,ss=[173, 214, 183],algo=ConvAlgo.MaskImplicitGemm,ksize=[3, 3, 3],stride=[1, 1, 1],padding=[1, 1, 1],dilation=[1, 1, 1],subm=True,transpose=False

I actually met the same problem, but I have torch 1.11, spconv with cuda 11.3 installation. Does anyone know how to solve this? I'll try to debug it.

[Exception|implicit_gemm_pair]indices=torch.Size([0, 4]),bs=1,ss=[173, 214, 183],algo=ConvAlgo.MaskImplicitGemm,ksize=[3, 3, 3],stride=[1, 1, 1],padding=[1, 1, 1],dilation=[1, 1, 1],subm=True,transpose=False

> I actually met the same problem, but I have torch 1.11, spconv with cuda 11.3 installation. Does anyone know how to solve this? I'll try to debug it. I...

[Exception|implicit_gemm_pair]indices=torch.Size([0, 4]),bs=1,ss=[173, 214, 183],algo=ConvAlgo.MaskImplicitGemm,ksize=[3, 3, 3],stride=[1, 1, 1],padding=[1, 1, 1],dilation=[1, 1, 1],subm=True,transpose=False

> @JinyuanShao did you make modifications to the code. I think the default code should not have this problem. Not really. l only change data directory. Maybe I installed a...