In this guide, we will run a VGG16 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.
We will use the VGG16 model in ONNX format from the ONNX Model Zoo and convert it into NNVM IR, compile it using NNVM compiler and run it on TVM runtime with LLVM backend
Get started with TVM and join the discussion now
This is a companion discussion topic for the original entry at http://iq.opengenus.org/run-vgg16-in-onnx-format-on-tvm-stack-with-llvm-backend/