model-optimization icon indicating copy to clipboard operation
model-optimization copied to clipboard
verified publisher icon tensorflow

Quantization aware training on untrained model

Open abhiagwl4262 opened this issue 4 years ago • 0 comments

Q1. Can I train a model from scratch using Quantization aware training? Or It can only be used as fine-tuning method ?

Q2. Are QFormats for weight tensors decided before QAT or weight format keep changing based on minmax values after weight update ?

abhiagwl4262 avatar Sep 03 '21 17:09 abhiagwl4262