I have noticed that the examples (e.g. 'detect_objects_file' and 'classify_images_file') do not quantize the input tensor, read from a .rgb file, before running inference. Is it just to keep the examples minimalistic and under the assumption that std * scale ~ 1 and mean - zero_point ~ 0, or is there a different reason at hand?
Appreciate any guidance in the matter.
Click to expand!
### Issue Type
Others
### Operating System
Mac OS
### Coral Device
Dev Board Micro
### Other Devices
_No response_
### Programming Language
C++
### Relevant Log Output
_No response_
metanav
commented
10 months ago
Description
Hello,
I have noticed that the examples (e.g. 'detect_objects_file' and 'classify_images_file') do not quantize the input tensor, read from a .rgb file, before running inference. Is it just to keep the examples minimalistic and under the assumption that std * scale ~ 1 and mean - zero_point ~ 0, or is there a different reason at hand?
Appreciate any guidance in the matter.
Click to expand!
### Issue Type Others ### Operating System Mac OS ### Coral Device Dev Board Micro ### Other Devices _No response_ ### Programming Language C++ ### Relevant Log Output _No response_