onnx模型优化

onnx simplifier（简称 onnxsim）,onnxsim 本身只提供 constant folding/propagation（即消除结果恒为常量的算子）的能力，而图变换（即合并 conv 和 bn 等等）的能力是由 onnxsim 调用 onnx optimizer 的各种 pass 实现的。

onnxoptimizer、onnxsim被誉为onnx的优化利器，其中onnxsim可以优化常量，onnxoptimizer可以对节点进行压缩。

https://github.com/daquexian/onnx-simplifier
https://github.com/onnx/optimizer
https://convertmodel.com/#input=onnx&output=onnx

import onnx
from onnxsim import simplify
onnx_model = onnx.load(ONNX_name)  # load onnx model
model_simp, check = simplify(onnx_model)
assert check, "Simplified ONNX model could not be validated"
onnx.save(model_simp, "resnet18_simplify.onnx")


import onnx
import onnxoptimizer
model = onnx.load(ONNX_name)
new_model = onnxoptimizer.optimize(model)
onnx.save(new_model,"resnet18_optimize.onnx")
# use model_simp as a standard ONNX model object


import onnxruntime as rt
sess_options = rt.SessionOptions()
# Set graph optimization level
sess_options.graph_optimization_level = rt.GraphOptimizationLevel.ORT_ENABLE_EXTENDED
# GraphOptimizationLevel::ORT_DISABLE_ALL -> Disables all optimizations
# GraphOptimizationLevel::ORT_ENABLE_BASIC -> Enables basic optimizations
# GraphOptimizationLevel::ORT_ENABLE_EXTENDED -> Enables basic and extended optimizations
# GraphOptimizationLevel::ORT_ENABLE_ALL -> Enables all available optimizations including layout optimizations
# To enable model serialization after graph optimization set this
sess_options.optimized_model_filepath = "<model_output_path\optimized_model.onnx>"

session = rt.InferenceSession("<model_path>", sess_options)