Hi, I am using TVM to load an MXNet model and saw there is two consecutive add that do not get constant folded. Below are three screenshots showing (1) the Original MXNet model (2) the model without FoldConstant and FoldScaleAxis (3) with the relay transforms as below, which has two consecutive add
relay.transform.RemoveUnusedFunctions(),
relay.transform.CanonicalizeOps(),
relay.transform.InferType(),
relay.transform.SimplifyInference(),
relay.transform.FoldConstant(), # Commented out in (2)
relay.transform.FoldScaleAxis(), # Commented out in (2)
relay.transform.EliminateCommonSubexpr(),
(1) the Original MXNet model
(2) the model without FoldConstant and FoldScaleAxis
relay.transform.RemoveUnusedFunctions(),
relay.transform.CanonicalizeOps(),
relay.transform.InferType(),
relay.transform.SimplifyInference(),
relay.transform.EliminateCommonSubexpr(),
(3) with the relay transforms as below, which has two consecutive add
relay.transform.RemoveUnusedFunctions(),
relay.transform.CanonicalizeOps(),
relay.transform.InferType(),
relay.transform.SimplifyInference(),
relay.transform.FoldConstant(), # Commented out in (2)
relay.transform.FoldScaleAxis(), # Commented out in (2)
relay.transform.EliminateCommonSubexpr(),
Some suggestions about how to fold two add will be awesome!


