Live data from Hacker News

Show HN: I built an AI that recognizes food

infino.me

31–40 of 140 posts

Re: Show HN: I built an AI that recognizes food

#31

Built using those newfangled convolutional neural network things. Trained caffe on a set of about a million food related images. Can't believe how accurate the classifier is... UI needs work. Would love feedback on how to make food logging more intuitive.

I would love a blog post about that!

Re: Show HN: I built an AI that recognizes food

#32
post #27

Earlier quoted context omitted.

Great! And think about using the new data from the users to improve the system (that should probably be in your terms). How well does it work on plates with multiple foods "kinda mixed"?

Thats another huge design challenge Ive faced, specifically because it really complicates the data model and UI. Implicitly, since the app presents a list of possible identified foods, and the user can easily check multiple boxes, thats straightforward, but then having the app pull each of those items AND ask the user to estimate portions for each .... gets a little messy. So I put that complexity off for v2. That us…

What about dividing the whole plate weight by the foods detected? (in Brazil there are many restaurants where you pay by weight, thats why I'm suggesting..)

Re: Show HN: I built an AI that recognizes food

#33

Built using those newfangled convolutional neural network things. Trained caffe on a set of about a million food related images. Can't believe how accurate the classifier is... UI needs work. Would love feedback on how to make food logging more intuitive.

Login via Facebook? Come on! See you next app.

Re: Show HN: I built an AI that recognizes food

#34

Built using those newfangled convolutional neural network things. Trained caffe on a set of about a million food related images. Can't believe how accurate the classifier is... UI needs work. Would love feedback on how to make food logging more intuitive.

Login via Facebook? Come on! See you next app.

Re: Show HN: I built an AI that recognizes food

#35

Built using those newfangled convolutional neural network things. Trained caffe on a set of about a million food related images. Can't believe how accurate the classifier is... UI needs work. Would love feedback on how to make food logging more intuitive.

Login via Facebook? Come on! See you next app.

Re: Show HN: I built an AI that recognizes food

#38
post #32

Earlier quoted context omitted.

Thats another huge design challenge Ive faced, specifically because it really complicates the data model and UI. Implicitly, since the app presents a list of possible identified foods, and the user can easily check multiple boxes, thats straightforward, but then having the app pull each of those items AND ask the user to estimate portions for each .... gets a little messy. So I put that complexity off for v2. That us…

What about dividing the whole plate weight by the foods detected? (in Brazil there are many restaurants where you pay by weight, thats why I'm suggesting..)

Theres a company in the bay area trying this approach actually! They look really interesting: https://getsmartplate.com/

Cant compete with that awesomesauce!

Re: Show HN: I built an AI that recognizes food

#39
Isn't it strange that in [1] the beginning of the "Normal" BMI has more risk of death than the beginning of the "Obese"? I'd even venture to say that the "Overweight" range has, in average, lower Mortality Risk than the "Normal".

PS, another plus for the Metric System. The Imperial System form includes Feet+Inches, while the metric one only needs Centimeters for the height.

[1] https://www.infino.me/join/

Post reply on HN