TF2-Engine/TF2

what will be quantified in TF2

Closed this issue · 1 comments

Now I am reading the code of TF2, I found in Runtime_Engine/cnn/host/src/network.cpp will call quantization function, but I also found in TransForm_Kit will do quantization,
what's the difference between them and what's the difference in the way they quantify?

Transform Kit realizes the quantization and saves the quantization parameters into quantization file. Runtime Engine reads the quantization file.