Aug 22, 2017 · 1 min read
Hey thanks for pointing this out!! You’re absolutely right! I updated the code and fixed the mistake. The funny thing is that I did this already in an earlier code version for the Udacity dataset but then refactored it due to the using your own dataset documentation when I created the Raccoon demo. And yes you’re right since I have a lot of single Raccoons this shouldn’t affect accuracy but in datasets like the Udacity ones it will cause problems. Thanks again!
