AIMET ONNX Cross Layer Equalization APIs

User Guide Link

To learn more about this technique, please see Cross-Layer Equalization

Introduction

AIMET functionality for Cross Layer Equalization has 3 features-

• BatchNorm Folding

• Cross Layer Scaling

• High Bias Fold

Cross Layer Equalization API

The following API performs BatchNorm fold followed by Cross Layer Scaling followed by High Bias Fold.

Note: High Bias fold will not happen when the below API is used, if the model does not have BatchNorm layers

API for Cross Layer Equalization

Code Example

Required imports

from aimet_onnx.cross_layer_equalization import equalize_model

Cross Layer Equalization in auto mode

def cross_layer_equalization():
    onnx_model = Model()
    equalize_model(onnx_model)