Quantization Refactoring
Post Training Quantization implementation in C++, Python bindings, and tutorial for the AIDGE PTQ
-
C++ related developements -
Complete refactoring of the existing C++ code -
Add a routine for computing the activation ranges -
Add a routine for checking the graph architecture before the PTQ
-
-
Python related developements -
Refactoring of the Pybind wrapper -
Writing of a script for testing the AIDGE PTQ
-
Edited by Benjamin Halimi