Hello @LorenzoLamberti94,
I recently reviewed your pulp-dronet-v1 which is really interesting. However, I have some questions about how did you eveluate your results (i.e., EVA, RMSE, Acc, F1)?
I ran the code based on https://github.com/pulp-platform/pulp-dronet, and saw the results as 16-bit fixed point as:
Hello @LorenzoLamberti94, I recently reviewed your pulp-dronet-v1 which is really interesting. However, I have some questions about how did you eveluate your results (i.e., EVA, RMSE, Acc, F1)? I ran the code based on https://github.com/pulp-platform/pulp-dronet, and saw the results as 16-bit fixed point as:
But the EVA, RMSE, Acc and F1 requires float point to calculate. I'll be really appreciate if you can help with my question. Yingxiu Chang