We plan to apply the results of ONNX-Opimizer and Onnx-simplifier to Op Fusion in QNN. However, I asked because there seemed to be a lack of manuals for each package.
What's the difference from ONNX-Simplier? I wonder if it's better to use it together.
Based on what I read in the README for optimizer, the optimizer library is written in C++. onnx-simplifier "just" provides a Python interface and some model checking.
We plan to apply the results of ONNX-Opimizer and Onnx-simplifier to Op Fusion in QNN. However, I asked because there seemed to be a lack of manuals for each package.