/challenges-projects/design-challenges/save-the-bees-design-challenge/b/blog/posts/honey-bee-safe-nicla-vision-againI thought I&#39;d give machine vision and identification on the Nicla Vision another try, as last time things went terribly wrong, with unicorns everywhere! This time I focused on just identifying rubber duckies, without confusing the model with the addeen-USTelligent Community 12https://community.element14.com/challenges-projects/design-challenges/save-the-bees-design-challenge/b/blog/posts/honey-bee-safe-nicla-vision-againTue, 21 Mar 2023 07:04:29 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:e4d00f2a-6530-4c47-9db7-61e9bd0fde14shabaz2<p>If it walks like a duck.. : )&nbsp;</p> <p>I&#39;ve not used Edge Impulse much (I gave it a quick shot when they went live), but I think there is a&nbsp; problem in the training if it only found ducks in that chart in that app. The training data (if all you&#39;re interested in is ducks) should be &quot;ducks&quot; and &quot;not ducks&quot;, i.e. the latter would include the background and everything else. In other words, the training data would include things like mobile phones and other random objects in there, all with the &quot;not ducks&quot; label. I&#39;m guessing (I&#39;m not an expert) that the particular model has incorrectly learned that anything that is not a background is a duck, which to be fair, is what it was trained with so it&#39;s working as expected.</p><img src="https://community.element14.com/aggbug?PostID=25477&AppID=396&AppType=Weblog&ContentType=0" width="1" height="1">