Change Precision Of model.hef - Yolov8

[tahseen52]

I have trained Yolov8 using the given docker, and i successfully converted it into HEF model.
Now my question is what is the default precision of the converted model i.e. HEF Model. AS per my exploration i got to know it is UINT8 but i am not sure about that.

Also my requirement is to create model with following precision modes:

• Float32
• UINT16

In Conversion, I have seen some logs regarding this but unable to get the points like where are these params. what is mixed precision etc

[info] Model received quantization params from the hn
[info] Starting Mixed Precision
[info] Mixed Precision is done (completion time is 00:00:00.06)

@hailo-ai
@nadaved1

[nadaved1]

Hi @tahseen52, I think that you find it much better to have the discussion in our forum at https://community.hailo.ai/latest.
In general, our HW doesn't support numeric representation at Float32, so the mixed is between 16/8/4 bit representations.

[tahseen52]

Hello @nadaved1, yes i got answers to most of my questions but there is a still a query regarding selection of layers i.e. See here
Can you please help with that issue also ?

For others having same issue, please go through this discussion: see here