Pretty bad imo. Tried three objects: Diet Coke can, bottle of cleaning fluid, desktop cactus. Didn’t identify any even remotely close. Was just like a random guess.
Pretty neat, it recognized a chair even though it was obscured with clothes. Granted it does not recognize some heavily specific objects (as it says in the description) but it is a start.
this can be done in browser with tensorflow.js + a pretrained mobilenet in a couple dozen lines of code<p>example:
<a href="https://jott.live/html/tfjsmobilenet" rel="nofollow">https://jott.live/html/tfjsmobilenet</a>
code:
<a href="https://jott.live/code/tfjsmobilenet" rel="nofollow">https://jott.live/code/tfjsmobilenet</a>
> After the picture is taken, it's sent to a fast.ai CNN model running on render<p>Why does the model have to run on render? Can it be run on other servers?