Abhi Khobare

> > Hi @zkdfbb - This problem happens due to the mismatch in pybind, libpython versions from what I remember. To give you a clue of how this was resolved...

> @quic-klhsieh At the beginning, when I configured the config_file for the QuantizationSimModel, I set up operator fusion to merge conv and relu. Consequently, in the exported encoding file, when...

> May I also ask if my target deployment platform is SM8550, and I'm deploying with SNPE 2.13, in the form of W8A8 bias=32bit, is my current QuantizationSimModel configuration reasonable?...

Hi @alyymsong - it seems you don't have CUDA installed. Either you can run in CPU mode - use the CPU-only AIMET whl files, or install CUDA.. To install CUDA:...

> > @666DZY666 the references are LSQ (https://arxiv.org/abs/1902.08153) and LSQ+ (https://arxiv.org/abs/2004.09576 but AIMET optimizes min/max instead of scale offset so our implementation is not exactly the same. > > Why...

@roycyh - total epochs for fine-tuning are ~15. You can use the same hyper-parameters for both the fine-tuning steps.

Closing this as resolved. If there is another question please re-open for create a new issue.