Skip to content

Tutorial for using TensorRT 8-Bit Quantization with Aidge.

Nathan Thoumine requested to merge nthm/aidge:dev into dev

Description

This MR introduces a tutorial on utilizing TensorRT's 8-bit quantization feature through the aidge_export_tensorrt module.

Key Points Covered:

  • exporting the model
  • modifying the test script for quantization
  • preparing calibration data
  • running the quantization and profile the quantized model

Merge request reports