I guess there is currently no inference strategy suitable for NHW16nC in TVM, which will make the inference process difficult if you have to keep your data layout :thinking:.
--- [Visit Topic](https://discuss.tvm.apache.org/t/pytorch-how-to-change-weights-layout-from-nchw-to-nhwc/10146/8) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/1170d1063b3cd12c4439490478194ca285cbce4ffae039c73392e1deb394a8ee).
