Batchnorm op Fusion in TVM

Note that you are using SimplifyInfernce twice, but you want to replace the second one with SimplifyExpr.

But right, it seems bias_add and add are not folded. It seems relay.transform.CanonicalizeOps() converts bias_add to add, so you want to call it before SimplifyExpr. I tried your script but I didn’t get satisfying output after brief attempt. Maybe you need to play around it a bit more. If you believe there is a bug / missing functionality, welcome to open a github issue.