I’m using TVM to quantize ResNet-50.
After importing model from Tensorflow Saved Model, I simply use
mod = relay.quantize.quantize(mod, params=params)
to quantize model.
I was able to build and run with the target “llvm”, but got segment fault with the target “llvm -mcpu=skylake-avx512” and “llvm -mcpu=cascadelake” during relay.build.
Any help is greatly appreciated.