quantization
quantization copied to clipboard
kingreza
A deep dive into Apple's coremltools quantization and how to reduce the size of a Core ML model without losing accuracy and performance
Now that Xcode 10 is GM, I want to try 8bit quantized models. The issue is that my models have already been quantized to 16bit, and when I run the...
Curious to see if we get speed up by using 16bit or 8bit model, or speed drop? Thanks.
For some reason when I try quantizing existing models I have, I manage to get 16-bit models working on Xcode 9.4.1, but not 8-bit or less. When I go under...