This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA2SX: TDA2 TIDL Quantization

Part Number: TDA2SX
Other Parts Discussed in Thread: TDA2

Hi, Expert, 

For TDA2 TIDL, Can you pls help to share the quantization ? do we support both of per layer or per channel ? 

How to change that ? Thanks

Regards,

Fredy Zhang

  • in TDA we support only Per Layer quantization. We do not support per-channel quantization.

    Only 8-bits are supported for features, 8 -12 bits are supported for weight/Parameter quantizations. Users can set the same in import config files