Context/Use case:
We are working on the time-series sensor data project using MFE as processing block.
Question/Issue:
We wanted to know more about the implementation_version used in the MFE code to get more clarity as we din find any doc related to implementation_version
For the cpp implementation, when you download the cpp library, when you extract the archive, look after this file edge-impulse-sdk → classifier->ei_run_dsp.h.
For example, if you used the mfe dsp block in the studio, you will find the cpp implementation in the function:
Hi @ajithkjajith we use the implementation_version property to introduce breaking changes in the algorithm (e.g. if we change the way we create the spectrogram) w/o changing behavior for older projects. You just need to make sure it’s in sync between Studio and SDK (which happens automatically in the export of the project).